Are Multiple Cross-Correlation Identities Better Than Just Two? Improving the Estimate of Time Differences-Of-Arrivals from Blind Audio Signals

Danilo Greco, Jacopo Cavazza, Alessio Del Bue

Responsive image

Auto-TLDR; Improving Blind Channel Identification Using Cross-Correlation Identity for Time Differences-of-Arrivals Estimation

Slides Poster

Given an unknown audio source, the estimation of time differences-of-arrivals (TDOAs) can be efficiently and robustly solved using blind channel identification and exploiting the cross-correlation identity (CCI). Prior "blind" works have improved the estimate of TDOAs by means of different algorithmic solutions and optimization strategies, while always sticking to the case N = 2 microphones. But what if we can obtain a direct improvement in performance by just increasing N? In this paper we try to investigate this direction, showing that, despite the arguable simplicity, this is capable of (sharply) improving upon state-of-the-art blind channel identification methods based on CCI, without modifying the computational pipeline. Inspired by our results, we seek to warm up the community and the practitioners by paving the way (with two concrete, yet preliminary, examples) towards joint approaches in which advances in the optimization are combined with an increased number of microphones, in order to achieve further improvements.

Similar papers

Which are the factors affecting the performance of audio surveillance systems?

Antonio Greco, Antonio Roberto, Alessia Saggese, Mario Vento

Responsive image

Auto-TLDR; Sound Event Recognition Using Convolutional Neural Networks and Visual Representations on MIVIA Audio Events

Slides Similar

Sound event recognition systems are rapidly becoming part of our life, since they can be profitably used in several vertical markets, ranging from audio security applications to scene classification and multi-modal analysis in social robotics. In the last years, a not negligible part of the scientific community started to apply Convolutional Neural Networks (CNNs) to image-based representations of the audio stream, due to their successful adoption in almost all the computer vision tasks. In this paper, we carry out a detailed benchmark of various widely used CNN architectures and visual representations on a popular dataset, namely the MIVIA Audio Events database. Our analysis is aimed at understanding how these factors affect the sound event recognition performance with a particular focus on the false positive rate, very relevant in audio surveillance solutions. In fact, although most of the proposed solutions achieve a high recognition rate, the capability of distinguishing the events-of-interest from the background is often not yet sufficient for real systems, and prevent its usage in real applications. Our comprehensive experimental analysis investigates this aspect and allows to identify useful design guidelines for increasing the specificity of sound event recognition systems.

Improving Mix-And-Separate Training in Audio-Visual Sound Source Separation with an Object Prior

Quan Nguyen, Simone Frintrop, Timo Gerkmann, Mikko Lauri, Julius Richter

Responsive image

Auto-TLDR; Object-Prior: Learning the 1-to-1 correspondence between visual and audio signals by audio- visual sound source methods

Slides Similar

The performance of an audio-visual sound source separation system is determined by its ability to separate audio sources given images of the sources and the audio mixture. The goal of this study is to investigate the ability to learn the mapping between the sounds and the images of instruments by audio- visual sound source separation methods based on the state-of-the- art PixelPlayer [1]. Theoretical and empirical analyses illustrate that the PixelPlayer is not properly trained to learn the 1-to- 1 correspondence between visual and audio signals during its mix-and-separate training process. Based on the insights from this analysis, a weakly-supervised method called Object-Prior is proposed and evaluated on two audio-visual datasets. The experimental results show that the proposed Object-Prior method outperforms the PixelPlayer and other baselines in the audio- visual sound source separation task. It is also more robust against asynchronized data, where the frame and the audio do not come from the same video, and recognizes musical instruments based on their sound with higher accuracy than the PixelPlayer. This indicates that learning the 1-to-1 correspondence between visual and audio features of an instrument improves the effectiveness of audio-visual sound source separation.

ESResNet: Environmental Sound Classification Based on Visual Domain Models

Andrey Guzhov, Federico Raue, Jörn Hees, Andreas Dengel

Responsive image

Auto-TLDR; Environmental Sound Classification with Short-Time Fourier Transform Spectrograms

Slides Poster Similar

Environmental Sound Classification (ESC) is an active research area in the audio domain and has seen a lot of progress in the past years. However, many of the existing approaches achieve high accuracy by relying on domain-specific features and architectures, making it harder to benefit from advances in other fields (e.g., the image domain). Additionally, some of the past successes have been attributed to a discrepancy of how results are evaluated (i.e., on unofficial splits of the UrbanSound8K (US8K) dataset), distorting the overall progression of the field. The contribution of this paper is twofold. First, we present a model that is inherently compatible with mono and stereo sound inputs. Our model is based on simple log-power Short-Time Fourier Transform (STFT) spectrograms and combines them with several well-known approaches from the image domain (i.e., ResNet, Siamese-like networks and attention). We investigate the influence of cross-domain pre-training, architectural changes, and evaluate our model on standard datasets. We find that our model out-performs all previously known approaches in a fair comparison by achieving accuracies of 97.0 % (ESC-10), 91.5 % (ESC-50) and 84.2 % / 85.4 % (US8K mono / stereo). Second, we provide a comprehensive overview of the actual state of the field, by differentiating several previously reported results on the US8K dataset between official or unofficial splits. For better reproducibility, our code (including any re-implementations) is made available.

Computational Data Analysis for First Quantization Estimation on JPEG Double Compressed Images

Sebastiano Battiato, Oliver Giudice, Francesco Guarnera, Giovanni Puglisi

Responsive image

Auto-TLDR; Exploiting Discrete Cosine Transform Coefficients for Multimedia Forensics

Slides Poster Similar

Multimedia Forensics experts work consists in providing answers about integrity of a specific media content and from where it comes from. Exploitation of any traces from JPEG double compressed images is often one of the main investigative path to be used for these purposes. Thus it is fundamental to have tools and algorithms able to safely estimate the first quantization matrix to further proceed with camera model identification and related tasks. In this paper, a technique based on extensive simulation is proposed, with the aim to infer the first quantization for a certain numbers of Discrete Cosine Transform (DCT) coefficients exploiting local image statistics without using any a-priori knowledge. The method provides also a reliable confidence value for the estimation which is of great importance for forensic purposes. Experimental results w.r.t. the state-of-the-art demonstrate the effectiveness of the proposed technique both in terms of precision and overall reliability.

DenseRecognition of Spoken Languages

Jaybrata Chakraborty, Bappaditya Chakraborty, Ujjwal Bhattacharya

Responsive image

Auto-TLDR; DenseNet: A Dense Convolutional Network Architecture for Speech Recognition in Indian Languages

Slides Poster Similar

In the present study, we have, for the first time, con- sidered a large number of Indian languages for recog- nition from their audio signals of different sources. A dense convolutional network architecture (DenseNet) has been proposed for this classification problem. Dy- namic elimination of low energy frames from the input speech signal has been considered as a preprocessing operation. Mel-spectrogram of pre-processed speech signal is fed to a DenseNet architecture for recogni- tion of its language. Recognition performance of the proposed architecture has been compared with that of several state-of-the-art deep architectures which include a traditional convolutional neural network (CNN), multiple ResNet architectures, CNN-BLSTM and DenseNet-BLSTM hybrid architectures. Addition- ally, we obtained recognition performances of a stacked BLSTM architecture fed with different sets of hand- crafted features for comparison purpose. Simulations have been performed on two different standard datasets which include (i) IITKGP-MLILSC dataset of news clips in 27 different Indian languages and (ii) Linguistic Data Consortium (LDC) dataset of telephonic conver- sations in 5 different Indian languages. Recognition performance of the proposed framework has been found to be consistently and significantly better than all other frameworks implemented in this study.

Deep Universal Blind Image Denoising

Jae Woong Soh, Nam Ik Cho

Responsive image

Auto-TLDR; Image Denoising with Deep Convolutional Neural Networks

Slides Similar

Image denoising is an essential part of many image processing and computer vision tasks due to inevitable noise corruption during image acquisition. Traditionally, many researchers have investigated image priors for the denoising, within the Bayesian perspective based on image properties and statistics. Recently, deep convolutional neural networks (CNNs) have shown great success in image denoising by incorporating large-scale synthetic datasets. However, they both have pros and cons. While the deep CNNs are powerful for removing the noise with known statistics, they tend to lack flexibility and practicality for the blind and real-world noise. Moreover, they cannot easily employ explicit priors. On the other hand, traditional non-learning methods can involve explicit image priors, but they require considerable computation time and cannot exploit large-scale external datasets. In this paper, we present a CNN-based method that leverages the advantages of both methods based on the Bayesian perspective. Concretely, we divide the blind image denoising problem into sub-problems and conquer each inference problem separately. As the CNN is a powerful tool for inference, our method is rooted in CNNs and propose a novel design of network for efficient inference. With our proposed method, we can successfully remove blind and real-world noise, with a moderate number of parameters of universal CNN.

Digit Recognition Applied to Reconstructed Audio Signals Using Deep Learning

Anastasia-Sotiria Toufa, Constantine Kotropoulos

Responsive image

Auto-TLDR; Compressed Sensing for Digit Recognition in Audio Reconstruction

Poster Similar

Compressed sensing allows signal reconstruction from a few measurements. This work proposes a complete pipeline for digit recognition applied to audio reconstructed signals. The reconstruction procedure exploits the assumption that the original signal lies in the range of a generator. A pretrained generator of a Generative Adversarial Network generates audio digits. A new method for reconstruction is proposed, using only the most active segment of the signal, i.e., the segment with the highest energy. The underlying assumption is that such segment offers a more compact representation, preserving the meaningful content of signal. Cases when the reconstruction produces noise, instead of digit, are treated as outliers. In order to detect and reject them, three unsupervised indicators are used, namely, the total energy of reconstructed signal, the predictions of an one-class Support Vector Machine, and the confidence of a pretrained classifier used for recognition. This classifier is based on neural networks architectures and is pretrained on original audio recordings, employing three input representations, i.e., raw audio, spectrogram, and gammatonegram. Experiments are conducted, analyzing both the quality of reconstruction and the performance of classifiers in digit recognition, demonstrating that the proposed method yields higher performance in both the quality of reconstruction and digit recognition accuracy.

Classification and Feature Selection Using a Primal-Dual Method and Projections on Structured Constraints

Michel Barlaud, Antonin Chambolle, Jean_Baptiste Caillau

Responsive image

Auto-TLDR; A Constrained Primal-dual Method for Structured Feature Selection on High Dimensional Data

Slides Poster Similar

This paper deals with feature selection using supervised classification on high dimensional datasets. A classical approach is to project data on a low dimensional space and classify by minimizing an appropriate quadratic cost. Our first contribution is to introduce a matrix of centers in the definition of this cost. Moreover, as quadratic costs are not robust to outliers, we propose to use an $\ell_1$ cost instead (or Huber loss to mitigate overfitting issues). While control on sparsity is commonly obtained by adding an $\ell_1$ constraint on the vectorized matrix of weights used for projecting the data, our second contribution is to enforce structured sparsity. To this end we propose constraints that take into account the matrix structure of the data, based either on the nuclear norm, on the $\ell_{2,1}$ norm, or on the $\ell_{1,2}$ norm for which we provide a new projection algorithm. We optimize simultaneously the projection matrix and the matrix of centers thanks to a new tailored constrained primal-dual method. The primal-dual framework is general enough to encompass the various robust losses and structured constraints we use, and allows a convergence analysis. We demonstrate the effectiveness of the approach on three biological datasets. Our primal-dual method with robust losses, adaptive centers and structured constraints does significantly better than classical methods, both in terms of accuracy and computational time.

Wireless Localisation in WiFi Using Novel Deep Architectures

Peizheng Li, Han Cui, Aftab Khan, Usman Raza, Robert Piechocki, Angela Doufexi, Tim Farnham

Responsive image

Auto-TLDR; Deep Neural Network for Indoor Localisation of WiFi Devices in Indoor Environments

Slides Poster Similar

This paper studies the indoor localisation of WiFi devices based on a commodity chipset and standard channel sounding. First, we present a novel shallow neural network (SNN) in which features are extracted from the channel state information (CSI) corresponding to WiFi subcarriers received on different antennas and used to train the model. The single layer architecture of this localisation neural network makes it lightweight and easy-to-deploy on devices with stringent constraints on computational resources. We further investigate for localisation the use of deep learning models and design novel architectures for convolutional neural network (CNN) and long-short term memory (LSTM). We extensively evaluate these localisation algorithms for continuous tracking in indoor environments. Experimental results prove that even an SNN model, after a careful handcrafted feature extraction, can achieve accurate localisation. Meanwhile, using a well-organised architecture, the neural network models can be trained directly with raw data from the CSI and localisation features can be automatically extracted to achieve accurate position estimates. We also found that the performance of neural network-based methods are directly affected by the number of anchor access points (APs) regardless of their structure. With three APs, all neural network models proposed in this paper can obtain localisation accuracy of around 0.5 metres. In addition the proposed deep NN architecture reduces the data pre-processing time by 6.5 hours compared with a shallow NN using the data collected in our testbed. In the deployment phase, the inference time is also significantly reduced to 0.1 ms per sample. We also demonstrate the generalisation capability of the proposed method by evaluating models using different target movement characteristics to the ones in which they were trained.

Adversarially Training for Audio Classifiers

Raymel Alfonso Sallo, Mohammad Esmaeilpour, Patrick Cardinal

Responsive image

Auto-TLDR; Adversarially Training for Robust Neural Networks against Adversarial Attacks

Slides Poster Similar

In this paper, we investigate the potential effect of the adversarially training on the robustness of six advanced deep neural networks against a variety of targeted and non-targeted adversarial attacks. We firstly show that, the ResNet-56 model trained on the 2D representation of the discrete wavelet transform appended with the tonnetz chromagram outperforms other models in terms of recognition accuracy. Then we demonstrate the positive impact of adversarially training on this model as well as other deep architectures against six types of attack algorithms (white and black-box) with the cost of the reduced recognition accuracy and limited adversarial perturbation. We run our experiments on two benchmarking environmental sound datasets and show that without any imposed limitations on the budget allocations for the adversary, the fooling rate of the adversarially trained models can exceed 90%. In other words, adversarial attacks exist in any scales, but they might require higher adversarial perturbations compared to non-adversarially trained models.

Sketch-Based Community Detection Via Representative Node Sampling

Mahlagha Sedghi, Andre Beckus, George Atia

Responsive image

Auto-TLDR; Sketch-based Clustering of Community Detection Using a Small Sketch

Slides Poster Similar

This paper proposes a sketch-based approach to the community detection problem which clusters the full graph through the use of an informative and concise sketch. The reduced sketch is built through an effective sampling approach which selects few nodes that best represent the complete graph and operates on a pairwise node similarity measure based on the average commute time. After sampling, the proposed algorithm clusters the nodes in the sketch, and then infers the cluster membership of the remaining nodes in the full graph based on their aggregate similarity to nodes in the partitioned sketch. By sampling nodes with strong representation power, our approach can improve the success rates over full graph clustering. In challenging cases with large node degree variation, our approach not only maintains competitive accuracy with full graph clustering despite using a small sketch, but also outperforms existing sampling methods. The use of a small sketch allows considerable storage savings, and computational and timing improvements for further analysis such as clustering and visualization. We provide numerical results on synthetic data based on the homogeneous, heterogeneous and degree corrected versions of the stochastic block model, as well as experimental results on real-world data.

Generic Merging of Structure from Motion Maps with a Low Memory Footprint

Gabrielle Flood, David Gillsjö, Patrik Persson, Anders Heyden, Kalle Åström

Responsive image

Auto-TLDR; A Low-Memory Footprint Representation for Robust Map Merge

Slides Poster Similar

With the development of cheap image sensors, the amount of available image data have increased enormously, and the possibility of using crowdsourced collection methods has emerged. This calls for development of ways to handle all these data. In this paper, we present new tools that will enable efficient, flexible and robust map merging. Assuming that separate optimisations have been performed for the individual maps, we show how only relevant data can be stored in a low memory footprint representation. We use these representations to perform map merging so that the algorithm is invariant to the merging order and independent of the choice of coordinate system. The result is a robust algorithm that can be applied to several maps simultaneously. The result of a merge can also be represented with the same type of low-memory footprint format, which enables further merging and updating of the map in a hierarchical way. Furthermore, the method can perform loop closing and also detect changes in the scene between the capture of the different image sequences. Using both simulated and real data — from both a hand held mobile phone and from a drone — we verify the performance of the proposed method.

Learning Sparse Deep Neural Networks Using Efficient Structured Projections on Convex Constraints for Green AI

Michel Barlaud, Frederic Guyard

Responsive image

Auto-TLDR; Constrained Deep Neural Network with Constrained Splitting Projection

Slides Poster Similar

In recent years, deep neural networks (DNN) have been applied to different domains and achieved dramatic performance improvements over state-of-the-art classical methods. These performances of DNNs were however often obtained with networks containing millions of parameters and which training required heavy computational power. In order to cope with this computational issue a huge literature deals with proximal regularization methods which are time consuming.\\ In this paper, we propose instead a constrained approach. We provide the general framework for our new splitting projection gradient method. Our splitting algorithm iterates a gradient step and a projection on convex sets. We study algorithms for different constraints: the classical $\ell_1$ unstructured constraint and structured constraints such as the nuclear norm, the $\ell_{2,1} $ constraint (Group LASSO). We propose a new $\ell_{1,1} $ structured constraint for which we provide a new projection algorithm We demonstrate the effectiveness of our method on three popular datasets (MNIST, Fashion MNIST and CIFAR). Experiments on these datasets show that our splitting projection method with our new $\ell_{1,1} $ structured constraint provides the best reduction of memory and computational power. Experiments show that fully connected linear DNN are more efficient for green AI.

Hybrid Network for End-To-End Text-Independent Speaker Identification

Wajdi Ghezaiel, Luc Brun, Olivier Lezoray

Responsive image

Auto-TLDR; Text-Independent Speaker Identification with Scattering Wavelet Network and Convolutional Neural Networks

Slides Poster Similar

Deep learning has recently improved the performance of Speaker Identification (SI) systems. Promising results have been obtained with Convolutional Neural Networks (CNNs). This success are mostly driven by the advent of large datasets. However in the context of commercial applications, collection of large amount of training data is not always possible. In addition, robustness of a SI system is adversely effected by short utterances. SI with only a few and short utterances is a challenging problem. Therefore, in this paper, we propose a novel text-independent speaker identification system. The proposed system can identify speakers by learning from only few training short utterances examples. To achieve this, we combine CNN with Scattering Wavelet Network. We propose a two-stage feature extraction framework using a two-layer wavelet scattering network coupled with a CNN for SI system. The proposed architecture takes variable length speech segments. To evaluate the effectiveness of the proposed approach, Timit and Librispeech datasets are used in the experiments. These conducted experiments show that our hybrid architecture performs successfully for SI, even with a small number and short duration of training samples. In comparaison with related methods, the obtained results shows that an hybrid architecture achieve better performance.

Learning Sign-Constrained Support Vector Machines

Kenya Tajima, Kouhei Tsuchida, Esmeraldo Ronnie Rey Zara, Naoya Ohta, Tsuyoshi Kato

Responsive image

Auto-TLDR; Constrained Sign Constraints for Learning Linear Support Vector Machine

Poster Similar

Domain knowledge is useful to improve the generalization performance of learning machines. Sign constraints are a handy representation to combine domain knowledge with learning machine. In this paper, we consider constraining the signs of the weight coefficients in learning the linear support vector machine, and develop two optimization algorithms for minimizing the empirical risk under the sign constraints. One of the two algorithms is based on the projected gradient method, in which each iteration of the projected gradient method takes O(nd) computational cost and the sublinear convergence of the objective error is guaranteed. The second algorithm is based on the Frank-Wolfe method that also converges sublinearly and possesses a clear termination criterion. We show that each iteration of the Frank-Wolfe also requires O(nd) cost. Furthermore, we derive the explicit expression for the minimal iteration number to ensure an epsilon-accurate solution by analyzing the curvature of the objective function. Finally, we empirically demonstrate that the sign constraints are a promising technique when similarities to the training examples compose the feature vector.

The Effect of Spectrogram Reconstruction on Automatic Music Transcription: An Alternative Approach to Improve Transcription Accuracy

Kin Wai Cheuk, Yin-Jyun Luo, Emmanouil Benetos, Herremans Dorien

Responsive image

Auto-TLDR; Exploring the effect of spectrogram reconstruction loss on automatic music transcription

Slides Similar

Most of the state-of-the-art automatic music transcription (AMT) models break down the main transcription task into sub-tasks such as onset prediction and offset prediction and train them with onset and offset labels. These predictions are then concatenated together and used as the input to train another model with the pitch labels to obtain the final transcription. We attempt to use only the pitch labels (together with spectrogram reconstruction loss) and explore how far this model can go without introducing supervised sub-tasks. In this paper, we do not aim at achieving state-of-the-art transcription accuracy, instead, we explore the effect that spectrogram reconstruction has on our AMT model. Our proposed model consists of two U-nets: the first U-net transcribes the spectrogram into a posteriorgram, and a second U-net transforms the posteriorgram back into a spectrogram. A reconstruction loss is applied between the original spectrogram and the reconstructed spectrogram to constrain the second U-net to focus only on reconstruction. We train our model on different datasets including MAPS, MAESTRO, and MusicNet. Our experiments show that adding the reconstruction loss can generally improve the note-level transcription accuracy when compared to the same model without the reconstruction part. Moreover, it can also boost the frame-level precision to be higher than the state-of-the-art models. The feature maps learned by our u-net contain gridlike structures (not present in the baseline model) which implies that with the present of reconstruction loss, the model is probably trying to count along both the time and frequency axis, resulting in a higher note-level transcription accuracy.

RNN Training along Locally Optimal Trajectories via Frank-Wolfe Algorithm

Yun Yue, Ming Li, Venkatesh Saligrama, Ziming Zhang

Responsive image

Auto-TLDR; Frank-Wolfe Algorithm for Efficient Training of RNNs

Slides Poster Similar

We propose a novel and efficient training method for RNNs by iteratively seeking a local minima on the loss surface within a small region, and leverage this directional vector for the update, in an outer-loop. We propose to utilize the Frank-Wolfe (FW) algorithm in this context. Although, FW implicitly involves normalized gradients, which can lead to a slow convergence rate, we develop a novel RNN training method that, surprisingly, even with the additional cost, the overall training cost is empirically observed to be lower than back-propagation. Our method leads to a new Frank-Wolfe method, that is in essence an SGD algorithm with a restart scheme. We prove that under certain conditions our algorithm has a sublinear convergence rate of $O(1/\epsilon)$ for $\epsilon$ error. We then conduct empirical experiments on several benchmark datasets including those that exhibit long-term dependencies, and show significant performance improvement. We also experiment with deep RNN architectures and show efficient training performance. Finally, we demonstrate that our training method is robust to noisy data.

Temporal Pattern Detection in Time-Varying Graphical Models

Federico Tomasi, Veronica Tozzo, Annalisa Barla

Responsive image

Auto-TLDR; A dynamical network inference model that leverages on kernels to consider general temporal patterns

Slides Poster Similar

Graphical models allow to describe the interplay among variables of a system through a compact representation, suitable when relations evolve over time. For example, in a biological setting, genes interact differently depending on external environmental or metabolic factors. To incorporate this dynamics a viable strategy is to estimate a sequence of temporally related graphs assuming similarity among samples in different time points. While adjacent time points may direct the analysis towards a robust estimate of the underlying graph, the resulting model will not incorporate long-term or recurrent temporal relationships. In this work we propose a dynamical network inference model that leverages on kernels to consider general temporal patterns (such as circadian rhythms or seasonality). We show how our approach may also be exploited when the recurrent patterns are unknown, by coupling the network inference with a clustering procedure that detects possibly non-consecutive similar networks. Such clusters are then used to build similarity kernels. The convexity of the functional is determined by whether we impose or infer the kernel. In the first case, the optimisation algorithm exploits efficiently proximity operators with closed-form solutions. In the other case, we resort to an alternating minimisation procedure which jointly learns the temporal kernel and the underlying network. Extensive analysis on synthetic data shows the efficacy of our models compared to state-of-the-art methods. Finally, we applied our approach on two real-world applications to show how considering long-term patterns is fundamental to have insights on the behaviour of a complex system.

Motion Segmentation with Pairwise Matches and Unknown Number of Motions

Federica Arrigoni, Tomas Pajdla, Luca Magri

Responsive image

Auto-TLDR; Motion Segmentation using Multi-Modelfitting andpermutation synchronization

Slides Poster Similar

In this paper we address motion segmentation, that is the problem of clustering points in multiple images according to a number of moving objects. Two-frame correspondences are assumed as input without prior knowledge about trajectories. Our method is based on principles from ''multi-model fitting'' and ''permutation synchronization'', and - differently from previous techniques working under the same assumptions - it can handle an unknown number of motions. The proposed approach is validated on standard datasets, showing that it can correctly estimate the number of motions while maintaining comparable or better accuracy than the state of the art.

3D Pots Configuration System by Optimizing Over Geometric Constraints

Jae Eun Kim, Muhammad Zeeshan Arshad, Seong Jong Yoo, Je Hyeong Hong, Jinwook Kim, Young Min Kim

Responsive image

Auto-TLDR; Optimizing 3D Configurations for Stable Pottery Restoration from irregular and noisy evidence

Slides Poster Similar

While potteries are common artifacts excavated in archaeological sites, the restoration process relies on the manual cleaning and reassembling shattered pieces. Since the number of possible 3D configurations is considerably large, the exhaustive manual trial may result in an abrasion on fractured surfaces and even failure to find the correct matches. As a result, many recent works suggest virtual reassembly from 3D scans of the fragments. The problem is challenging in the view of the conventional 3D geometric analysis, as it is hard to extract reliable shape features from the thin break lines. We propose to optimize the global configuration by combining geometric constraints with information from noisy shape features. Specifically, we enforce bijection and continuity of sequence of correspondences given estimates of corners and pair-wise matching scores between multiple break lines. We demonstrate that our pipeline greatly increases the accuracy of correspondences, resulting in the stable restoration of 3D configurations from irregular and noisy evidence.

Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning

Giancarlo Paoletti, Jacopo Cavazza, Cigdem Beyan, Alessio Del Bue

Responsive image

Auto-TLDR; Unsupervised Learning for Human Action Recognition from Skeletal Data

Slides Similar

This paper tackles the problem of human action recognition, defined as classifying which action is displayed in a trimmed sequence, from skeletal data. Albeit state-of-the-art approaches designed for this application are all supervised, in this paper we pursue a more challenging direction: Solving the problem with unsupervised learning. To this end, we propose a novel subspace clustering method, which exploits covariance matrix to enhance the action’s discriminability and a timestamp pruning approach that allow us to better handle the temporal dimension of the data. Through a broad experimental validation, we show that our computational pipeline surpasses existing unsupervised approaches but also can result in favorable performances as compared to supervised methods.

Computing Stable Resultant-Based Minimal Solvers by Hiding a Variable

Snehal Bhayani, Zuzana Kukelova, Janne Heikkilä

Responsive image

Auto-TLDR; Sparse Permian-Based Method for Solving Minimal Systems of Polynomial Equations

Slides Similar

Many computer vision applications require robust and efficient estimation of camera geometry. The robust estimation is usually based on solving camera geometry problems from a minimal number of input data measurements, i.e., solving minimal problems, in a RANSAC-style framework. Minimal problems often result in complex systems of polynomial equations. The existing state-of-the-art methods for solving such systems are either based on Groebner Basis and the action matrix method, which have been extensively studied and optimized in the recent years or recently proposed approach based on a resultant computation using an extra variable. In this paper, we study an interesting alternative resultant-based method for solving sparse systems of polynomial equations by hiding one variable. This approach results in a larger eigenvalue problem than the action matrix and extra variable resultant-based methods; however, it does not need to compute an inverse or elimination of large matrices that may be numerically unstable. The proposed approach includes several improvements to the standard sparse resultant algorithms, which significantly improves the efficiency and stability of the hidden variable resultant-based solvers as we demonstrate on several interesting computer vision problems. We show that for the studied problems, our sparse resultant based approach leads to more stable solvers than the state-of-the-art Groebner Basis as well as existing resultant-based solvers, especially in close to critical configurations. Our new method can be fully automated and incorporated into existing tools for the automatic generation of efficient minimal solvers.

Minimal Solvers for Indoor UAV Positioning

Marcus Valtonen Örnhag, Patrik Persson, Mårten Wadenbäck, Kalle Åström, Anders Heyden

Responsive image

Auto-TLDR; Relative Pose Solvers for Visual Indoor UAV Navigation

Slides Poster Similar

In this paper we consider a collection of relative pose problems which arise naturally in applications for visual indoor UAV navigation. We focus on cases where additional information from an onboard IMU is available and thus provides a partial extrinsic calibration through the gravitational vector. The solvers are designed for a partially calibrated camera, for a variety of realistic indoor scenarios, which makes it possible to navigate using images of the ground floor. Current state-of-the-art solvers use more general assumptions, such as using arbitrary planar structures; however, these solvers do not yield adequate reconstructions for real scenes, nor do they perform fast enough to be incorporated in real-time systems. We show that the proposed solvers enjoy better numerical stability, are faster, and require fewer point correspondences, compared to state-of-the-art solvers. These properties are vital components for robust navigation in real-time systems, and we demonstrate on both synthetic and real data that our method outperforms other methods, and yields superior motion estimation.

Spatial Bias in Vision-Based Voice Activity Detection

Kalin Stefanov, Mohammad Adiban, Giampiero Salvi

Responsive image

Auto-TLDR; Spatial Bias in Vision-based Voice Activity Detection in Multiparty Human-Human Interactions

Poster Similar

We present models for automatic vision-based voice activity detection (VAD) in multiparty human-human interactions that are aimed at complementing the acoustic VAD methods. We provide evidence that this type of vision-based VAD models are susceptible to spatial bias in the datasets. The physical settings of the interaction, usually constant throughout data acquisition, determines the distribution of head poses of the participants. Our results show that when the head pose distributions are significantly different in the training and test sets, the performance of the models drops significantly. This suggests that previously reported results on datasets with a fixed physical configuration may overestimate the generalization capabilities of this type of models. We also propose a number of possible remedies to the spatial bias, including data augmentation, input masking and dynamic features, and provide an in-depth analysis of the visual cues used by our models.

On the Use of Benford's Law to Detect GAN-Generated Images

Nicolo Bonettini, Paolo Bestagini, Simone Milani, Stefano Tubaro

Responsive image

Auto-TLDR; Using Benford's Law to Detect GAN-generated Images from Natural Images

Slides Poster Similar

The advent of Generative Adversarial Network (GAN) architectures has given anyone the ability of generating incredibly realistic synthetic imagery. The malicious diffusion of GAN-generated images may lead to serious social and political consequences (e.g., fake news spreading, opinion formation, etc.). It is therefore important to regulate the widespread distribution of synthetic imagery by developing solutions able to detect them. In this paper, we study the possibility of using Benford’s law to discriminate GAN-generated images from natural photographs. Benford’s law describes the distribution of the most significant digit for quantized Discrete Cosine Transform (DCT) coefficients. Extending and generalizing this property, we show that it is possible to extract a compact feature vector from an image. This feature vector can be fed to an extremely simple classifier for GAN-generated image detection purpose even in data scarcity scenarios where Convolutional Neural Network (CNN) architectures tend to fail.

A Globally Optimal Method for the PnP Problem with MRP Rotation Parameterization

Manolis Lourakis, George Terzakis

Responsive image

Auto-TLDR; A Direct least squares, algebraic PnP solver with modified Rodrigues parameters

Poster Similar

The perspective-n-point (PnP) problem is of fundamental importance in computer vision. A global optimality condition for PnP that is independent of a particular rotation parameterization was recently developed by Nakano. This paper puts forward a direct least squares, algebraic PnP solution that extends Nakano's work by combining his optimality condition with the modified Rodrigues parameters (MRPs) for parameterizing rotation. The result is a system of polynomials that is solved using the Groebner basis approach. An MRP vector has twice the rotational range of the classical Rodrigues (i.e., Cayley) vector used by Nakano to represent rotation. The proposed solver provides strong guarantees that the full rotation singularity associated with MRPs is avoided. Furthermore, detailed experiments provide evidence that our solver attains accuracy that is indistinguishable from Nakano's Cayley-based solution with a moderate increase in computational cost.

Audio-Visual Speech Recognition Using a Two-Step Feature Fusion Strategy

Hong Liu, Wanlu Xu, Bing Yang

Responsive image

Auto-TLDR; A Two-Step Feature Fusion Network for Speech Recognition

Slides Poster Similar

Lip-reading methods and fusion strategy are crucial for audio-visual speech recognition. In recent years, most approaches involve two separate audio and visual streams with early or late fusion strategies. Such a single-stage fusion method may fail to guarantee the integrity and representativeness of fusion information simultaneously. This paper extends a traditional single-stage fusion network to a two-step feature fusion network by adding an audio-visual early feature fusion (AV-EFF) stream to the baseline model. This method can learn the fusion information of different stages, preserving the original features as much as possible and ensuring the independence of different features. Besides, to capture long-range dependencies of video information, a non-local block is added to the feature extraction part of the visual stream (NL-Visual) to obtain the long-term spatio-temporal features. Experimental results on the two largest public datasets in English (LRW) and Mandarin (LRW-1000) demonstrate our method is superior to other state-of-the-art methods.

3D Audio-Visual Speaker Tracking with a Novel Particle Filter

Hong Liu, Yongheng Sun, Yidi Li, Bing Yang

Responsive image

Auto-TLDR; 3D audio-visual speaker tracking using particle filter based method

Slides Poster Similar

3D speaker tracking using co-located audio-visual sensors has received much attention recently. Though various methods have been attempted to this field, it is still challenging to obtain a reliable 3D tracking result since the position of co-located sensors are restricted to a small area. In this paper, a novel particle filter (PF) based method is proposed for 3D audio-visual speaker tracking. Compared with traditional PF based audio-visual speaker tracking method, our 3D audio-visual tracker has two main characteristics. In the prediction stage, we use audio-visual information at current frame to further adjust the direction of the particles after the particle state transition process, which can make the particles more concentrated around the speaker direction. In the update stage, the particle likelihood is calculated by fusing both the visual distance and audio-visual direction information. Specially, the distance likelihood is obtained according to the camera projection model and the adaptively estimated size of speaker face or head, and the direction likelihood is determined by audio-visual particle fitness. In this way, the particle likelihood can better represent the speaker presence probability in 3D space. Experimental results show that the proposed tracker outperforms other methods and provides a favorable speaker tracking performance both in 3D space and on the image plane.

Total Estimation from RGB Video: On-Line Camera Self-Calibration, Non-Rigid Shape and Motion

Antonio Agudo

Responsive image

Auto-TLDR; Joint Auto-Calibration, Pose and 3D Reconstruction of a Non-rigid Object from an uncalibrated RGB Image Sequence

Slides Poster Similar

In this paper we present a sequential approach to jointly retrieve camera auto-calibration, camera pose and the 3D reconstruction of a non-rigid object from an uncalibrated RGB image sequence, without assuming any prior information about the shape structure, nor the need for a calibration pattern, nor the use of training data at all. To this end, we propose a Bayesian filtering approach based on a sum-of-Gaussians filter composed of a bank of extended Kalman filters (EKF). For every EKF, we make use of dynamic models to estimate its state vector, which later will be Gaussianly combined to achieve a global solution. To deal with deformable objects, we incorporate a mechanical model solved by using the finite element method. Thanks to these ingredients, the resulting method is both efficient and robust to several artifacts such as missing and noisy observations as well as sudden camera motions, while being available for a wide variety of objects and materials, including isometric and elastic shape deformations. Experimental validation is proposed in real experiments, showing its strengths with respect to competing approaches.

Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks

Michele Alberti, Angela Botros, Schuetz Narayan, Rolf Ingold, Marcus Liwicki, Mathias Seuret

Responsive image

Auto-TLDR; Trainable and Spectrally Initializable Matrix Transformations for Neural Networks

Slides Poster Similar

In this work, we introduce a new architectural component to Neural Networks (NN), i.e., trainable and spectrally initializable matrix transformations on feature maps. While previous literature has already demonstrated the possibility of adding static spectral transformations as feature processors, our focus is on more general trainable transforms. We study the transforms in various architectural configurations on four datasets of different nature: from medical (ColorectalHist, HAM10000) and natural (Flowers) images to historical documents (CB55). With rigorous experiments that control for the number of parameters and randomness, we show that networks utilizing the introduced matrix transformations outperform vanilla neural networks. The observed accuracy increases appreciably across all datasets. In addition, we show that the benefit of spectral initialization leads to significantly faster convergence, as opposed to randomly initialized matrix transformations. The transformations are implemented as auto-differentiable PyTorch modules that can be incorporated into any neural network architecture. The entire code base is open-source.

D3Net: Joint Demosaicking, Deblurring and Deringing

Tomas Kerepecky, Filip Sroubek

Responsive image

Auto-TLDR; Joint demosaicking deblurring and deringing network with light-weight architecture inspired by the alternating direction method of multipliers

Slides Similar

Images acquired with standard digital cameras have Bayer patterns and suffer from lens blur. A demosaicking step is implemented in every digital camera, yet blur often remains unattended due to computational cost and instability of deblurring algorithms. Linear methods, which are computationally less demanding, produce ringing artifacts in deblurred images. Complex non-linear deblurring methods avoid artifacts, however their complexity imply offline application after camera demosaicking, which leads to sub-optimal performance. In this work, we propose a joint demosaicking deblurring and deringing network with a light-weight architecture inspired by the alternating direction method of multipliers. The proposed network has a transparent and clear interpretation compared to other black-box data driven approaches. We experimentally validate its superiority over state-of-the-art demosaicking methods with offline deblurring.

Expectation-Maximization for Scheduling Problems in Satellite Communication

Werner Bailer, Martin Winter, Johannes Ebert, Joel Flavio, Karin Plimon

Responsive image

Auto-TLDR; Unsupervised Machine Learning for Satellite Communication Using Expectation-Maximization

Slides Poster Similar

In this paper we address unsupervised machine learning for two use cases in satellite communication, which are scheduling problems: (i) Ka-band frequency plan optimization and (ii) dynamic configuration of an active antenna array satellite. We apply approaches based on the Expectation-Maximization (EM) framework to both of them. We compare against baselines of currently deployed solutions, and show that they can be significantly outperformed by the EM-based approach. In addition, the approaches can be applied incrementally, thus supporting fast adaptation to small changes in the input configuration.

Improving Gravitational Wave Detection with 2D Convolutional Neural Networks

Siyu Fan, Yisen Wang, Yuan Luo, Alexander Michael Schmitt, Shenghua Yu

Responsive image

Auto-TLDR; Two-dimensional Convolutional Neural Networks for Gravitational Wave Detection from Time Series with Background Noise

Poster Similar

Sensitive gravitational wave (GW) detectors such as that of Laser Interferometer Gravitational-wave Observatory (LIGO) realize the direct observation of GW signals that confirm Einstein's general theory of relativity. However, it remains challenges to quickly detect faint GW signals from a large number of time series with background noise under unknown probability distributions. Traditional methods such as matched-filtering in general assume Additive White Gaussian Noise (AWGN) and are far from being real-time due to its high computational complexity. To avoid these weaknesses, one-dimensional (1D) Convolutional Neural Networks (CNNs) are introduced to achieve fast online detection in milliseconds but do not have enough consideration on the trade-off between the frequency and time features, which will be revisited in this paper through data pre-processing and subsequent two-dimensional (2D) CNNs during offline training to improve the online detection sensitivity. In this work, the input data is pre-processed to form a 2D spectrum by Short-time Fourier transform (STFT), where frequency features are extracted without learning. Then, carrying out two 1D convolutions across time and frequency axes respectively, and concatenating the time-amplitude and frequency-amplitude feature maps with equal proportion subsequently, the frequency and time features are treated equally as the input of our following two-dimensional CNNs. The simulation of our above ideas works on a generated data set with uniformly varying SNR (2-17), which combines the GW signal generated by PYCBC and the background noise sampled directly from LIGO. Satisfying the real-time online detection requirement without noise distribution assumption, the experiments of this paper demonstrate better performance in average compared to that of 1D CNNs, especially in the cases of lower SNR (4-9).

Electroencephalography Signal Processing Based on Textural Features for Monitoring the Driver’s State by a Brain-Computer Interface

Giulia Orrù, Marco Micheletto, Fabio Terranova, Gian Luca Marcialis

Responsive image

Auto-TLDR; One-dimensional Local Binary Pattern Algorithm for Estimating Driver Vigilance in a Brain-Computer Interface System

Slides Poster Similar

In this study we investigate a textural processing method of electroencephalography (EEG) signal as an indicator to estimate the driver's vigilance in a hypothetical Brain-Computer Interface (BCI) system. The novelty of the solution proposed relies on employing the one-dimensional Local Binary Pattern (1D-LBP) algorithm for feature extraction from pre-processed EEG data. From the resulting feature vector, the classification is done according to three vigilance classes: awake, tired and drowsy. The claim is that the class transitions can be detected by describing the variations of the micro-patterns' occurrences along the EEG signal. The 1D-LBP is able to describe them by detecting mutual variations of the signal temporarily "close" as a short bit-code. Our analysis allows to conclude that the 1D-LBP adoption has led to significant performance improvement. Moreover, capturing the class transitions from the EEG signal is effective, although the overall performance is not yet good enough to develop a BCI for assessing the driver's vigilance in real environments.

Feature Engineering and Stacked Echo State Networks for Musical Onset Detection

Peter Steiner, Azarakhsh Jalalvand, Simon Stone, Peter Birkholz

Responsive image

Auto-TLDR; Echo State Networks for Onset Detection in Music Analysis

Slides Poster Similar

In music analysis, one of the most fundamental tasks is note onset detection - detecting the beginning of new note events. As the target function of onset detection is related to other tasks, such as beat tracking or tempo estimation, onset detection is the basis for such related tasks. Furthermore, it can help to improve Automatic Music Transcription (AMT). Typically, different approaches for onset detection follow a similar outline: An audio signal is transformed into an Onset Detection Function (ODF), which should have rather low values (i.e. close to zero) for most of the time but with pronounced peaks at onset times, which can then be extracted by applying peak picking algorithms on the ODF. In the recent years, several kinds of neural networks were used successfully to compute the ODF from feature vectors. Currently, Convolutional Neural Networks (CNNs) define the state of the art. In this paper, we build up on an alternative approach to obtain a ODF by Echo State Networks (ESNs), which have achieved comparable results to CNNs in several tasks, such as speech and image recognition. In contrast to the typical iterative training procedures of deep learning architectures, such as CNNs or networks consisting of Long-Short-Term Memory Cells (LSTMs), in ESNs only a very small part of the weights is easily trained in one shot using linear regression. By comparing the performance of several feature extraction methods, pre-processing steps and introducing a new way to stack ESNs, we expand our previous approach to achieve results that fall between a bidirectional LSTM network and a CNN with relative improvements of 1.8% and -1.4%, respectively. For the evaluation, we used exactly the same 8-fold cross validation setup as for the reference results.

DSPNet: Deep Learning-Enabled Blind Reduction of Speckle Noise

Yuxu Lu, Meifang Yang, Liu Wen

Responsive image

Auto-TLDR; Deep Blind DeSPeckling Network for Imaging Applications

Poster Similar

Blind reduction of speckle noise has become a long-standing unsolved problem in several imaging applications, such as medical ultrasound imaging, synthetic aperture radar (SAR) imaging, and underwater sonar imaging, etc. The unwanted noise could lead to negative effects on the reliable detection and recognition of objects of interest. From a statistical point of view, speckle noise could be assumed to be multiplicative, significantly different from the common additive Gaussian noise. The purpose of this study is to blindly reduce the speckle noise under non-ideal imaging conditions. The multiplicative relationship between latent sharp image and random noise will be first converted into an additive version through a logarithmic transformation. To promote imaging performance, we introduced the feature pyramid network (FPN) and atrous spatial pyramid pooling (ASPP), contributing to a more powerful deep blind DeSPeckling Network (named as DSPNet). In particular, DSPNet is mainly composed of two subnetworks, i.e., Log-NENet (i.e., noise estimation network in logarithmic domain) and Log-DNNet (i.e., denoising network in logarithmic domain). Log-NENet and Log-DNNet are, respectively, proposed to estimate noise level map and reduce random noise in logarithmic domain. The multi-scale mixed loss function is further proposed to improve the robust generalization of DSPNet. The proposed deep blind despeckling network is capable of reducing random noise and preserving salient image details. Both synthetic and realistic experiments have demonstrated the superior performance of our DSPNet in terms of quantitative evaluations and visual image qualities.

Detection of Calls from Smart Speaker Devices

Vinay Maddali, David Looney, Kailash Patil

Responsive image

Auto-TLDR; Distinguishing Between Smart Speaker and Cell Devices Using Only the Audio Using a Feature Set

Slides Poster Similar

The ubiquity of smart speakers is increasing, with a growing number of households utilising these devices to make calls over the telephony network. As the technology is typically configured to retain the cellular phone number of the user, it presents challenges in applications where knowledge of the true call origin is required. There are a wide range of makes and models for these devices, as is the case with cell phones, and it is challenging to detect the general category as a smart speaker or cell, independent of the designated phone number. In this paper, we present an approach to differentiate between calls originating from smart speakers and ones from cellular devices using only the audio. We present a feature set that characterises the relevant acoustic information, such as the degree of reverberation and noise, to distinguish between these categories. When evaluated on a dataset spanning multiple models for each device category, as well as different modes-of-usage and microphone-speaker distances, the method yields an Equal Error Rate (EER) of 12.6%.

Embedding Shared Low-Rank and Feature Correlation for Multi-View Data Analysis

Zhan Wang, Lizhi Wang, Hua Huang

Responsive image

Auto-TLDR; embedding shared low-rank and feature correlation for multi-view data analysis

Slides Poster Similar

The diversity of multimedia data in the real-world usually forms multi-view features. How to explore the structure information and correlations among multi-view features is still an open problem. In this paper, we propose a novel multi-view subspace learning method, named embedding shared low-rank and feature correlation (ESLRFC), for multi-view data analysis. First, in the embedding subspace, we propose a robust low-rank model on each feature set and enforce a shared low-rank constraint to characterize the common structure information of multiple feature data. Second, we develop an enhanced correlation analysis in the embedding subspace for simultaneously removing the redundancy of each feature set and exploring the correlations of multiple feature data. Finally, we incorporate the low-rank model and the correlation analysis into a unified framework. The shared low-rank constraint not only depicts the data distribution consistency among multiple feature data, but also assists robust subspace learning. Experimental results on recognition tasks demonstrate the superior performance and noise robustness of the proposed method.

Phase Retrieval Using Conditional Generative Adversarial Networks

Tobias Uelwer, Alexander Oberstraß, Stefan Harmeling

Responsive image

Auto-TLDR; Conditional Generative Adversarial Networks for Phase Retrieval

Slides Poster Similar

In this paper, we propose the application of conditional generative adversarial networks to solve various phase retrieval problems. We show that including knowledge of the measurement process at training time leads to an optimization at test time that is more robust to initialization than existing approaches involving generative models. In addition, conditioning the generator network on the measurements enables us to achieve much more detailed results. We empirically demonstrate that these advantages provide meaningful solutions to the Fourier and the compressive phase retrieval problem and that our method outperforms well-established projection-based methods as well as existing methods that are based on neural networks. Like other deep learning methods, our approach is very robust to noise and can therefore be very useful for real-world applications.

Wasserstein k-Means with Sparse Simplex Projection

Takumi Fukunaga, Hiroyuki Kasai

Responsive image

Auto-TLDR; SSPW $k$-means: Sparse Simplex Projection-based Wasserstein $ k$-Means Algorithm

Slides Poster Similar

This paper presents a proposal of a faster Wasserstein $k$-means algorithm for histogram data by reducing Wasserstein distance computations exploiting sparse simplex projection. We shrink data samples, centroids and ground cost matrix, which enables significant reduction of the computations to solve optimal transport problems without loss of clustering quality. Furthermore, we dynamically reduce computational complexity by removing lower-valued data samples harnessing sparse simplex projection while keeping degradation of clustering quality lower. We designate this proposed algorithm as sparse simplex projection-based Wasserstein $k$-means, for short, SSPW $k$-means. Numerical evaluations against Wasserstein $k$-means algorithm demonstrate the effectiveness of the proposed SSPW $k$-means on real-world datasets.

P2D: A Self-Supervised Method for Depth Estimation from Polarimetry

Marc Blanchon, Desire Sidibe, Olivier Morel, Ralph Seulin, Daniel Braun, Fabrice Meriaudeau

Responsive image

Auto-TLDR; Polarimetric Regularization for Monocular Depth Estimation

Slides Poster Similar

Monocular depth estimation is a recurring subject in the field of computer vision. Its ability to describe scenes via a depth map while reducing the constraints related to the formulation of perspective geometry tends to favor its use. However, despite the constant improvement of algorithms, most methods exploit only colorimetric information. Consequently, robustness to events to which the modality is not sensitive to, like specularity or transparency, is neglected. In response to this phenomenon, we propose using polarimetry as an input for a self-supervised monodepth network. Therefore, we propose exploiting polarization cues to encourage accurate reconstruction of scenes. Furthermore, we include a term of polarimetric regularization to state-of-the-art method to take specific advantage of the data. Our method is evaluated both qualitatively and quantitatively demonstrating that the contribution of this new information as well as an enhanced loss function improves depth estimation results, especially for specular areas.

Mutual Alignment between Audiovisual Features for End-To-End Audiovisual Speech Recognition

Hong Liu, Yawei Wang, Bing Yang

Responsive image

Auto-TLDR; Mutual Iterative Attention for Audio Visual Speech Recognition

Slides Poster Similar

Asynchronization issue caused by different types of modalities is one of the major problems in audio visual speech recognition (AVSR) research. However, most AVSR systems merely rely on up sampling of video or down sampling of audio to align audio and visual features, assuming that the feature sequences are aligned frame-by-frame. These pre-processing steps oversimplify the asynchrony relation between acoustic signal and lip motion, lacking flexibility and impairing the performance of the system. Although there are systems modeling the asynchrony between the modalities, sometimes they fail to align speech and video precisely in some even all noise conditions. In this paper, we propose a mutual feature alignment method for AVSR which can make full use of cross modility information to address the asynchronization issue by introducing Mutual Iterative Attention (MIA) mechanism. Our method can automatically learn an alignment in a mutual way by performing mutual attention iteratively between the audio and visual features, relying on the modified encoder structure of Transformer. Experimental results show that our proposed method obtains absolute improvements up to 20.42% over the audio modality alone depending upon the signal-to-noise-ratio (SNR) level. Better recognition performance can also be achieved comparing with the traditional feature concatenation method under both clean and noisy conditions. It is expectable that our proposed mutual feature alignment method can be easily generalized to other multimodal tasks with semantically correlated information.

2D Discrete Mirror Transform for Image Non-Linear Approximation

Alessandro Gnutti, Fabrizio Guerrini, Riccardo Leonardi

Responsive image

Auto-TLDR; Discrete Mirror Transform (DMT)

Slides Poster Similar

In this paper, a new 2D transform named Discrete Mirror Transform (DMT) is presented. The DMT is computed by decomposing a signal into its even and odd parts around an optimal location in a given direction so that the signal energy is maximally split between the two components. After minimizing the information required to regenerate the original signal by removing redundant structures, the process is iterated leading the signal energy to distribute into a continuously smaller set of coefficients. The DMT can be displayed as a binary tree, where each node represents the single (even or odd) signal derived from the decomposition in the previous level. An optimized version of the DMT (ODMT) is also introduced, by exploiting the possibility to choose different directions at which performing the decomposition. Experimental simulations have been carried out in order to test the sparsity properties of the DMT and ODMT when applied on images: referring to both transforms, the results show a superior performance with respect to the popular Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) in terms of non-linear approximation.

Directionally Paired Principal Component Analysis for Bivariate Estimation Problems

Navdeep Dahiya, Yifei Fan, Samuel Bignardi, Tony Yezzi, Romeil Sandhu

Responsive image

Auto-TLDR; Asymmetrically-Paired Principal Component Analysis for Linear Dimension-Reduction

Slides Poster Similar

We propose Asymmetrically-Paired Principal Component Analysis (APPCA), a novel linear dimension-reduction model for estimating coupled yet partially available variable sets. Unlike partial least square methods (e.g., partial least square regression and canonical correlation analysis) which maximize correlation/covariance between the two datasets, our APPCA directly minimizes, either conditionally or unconditionally, the reconstruction and prediction errors for the observable and unobservable part, respectively. We demonstrate the optimality of the proposed APPCA approach, we compare and evaluate relevant linear cross-decomposition methods with data reconstruction and prediction experiments on synthetic Gaussian data, multi-target regression datasets and single-channel image datasets. Results show that when only a single pair of bases is allowed, the conditional APPCA achieves lowest reconstruction error on the observable part and the total variable sets as a whole, meanwhile the unconditional APPCA reaches lowest prediction errors on the unobservable part. When extra budget is allowed for the PCA basis of the observable part, one can reach optimal solution using a combine method: standard PCA for the observable part and unconditional APPCA for the unobservable part.

DR2S: Deep Regression with Region Selection for Camera Quality Evaluation

Marcelin Tworski, Stéphane Lathuiliere, Salim Belkarfa, Attilio Fiandrotti, Marco Cagnazzo

Responsive image

Auto-TLDR; Texture Quality Estimation Using Deep Learning

Slides Poster Similar

In this work, we tackle the problem of estimating a camera capability to preserve fine texture details at a given lighting condition. Importantly, our texture preservation measurement should coincide with human perception. Consequently, we formulate our problem as a regression one and we introduce a deep convolutional network to estimate texture quality score. At training time, we use ground-truth quality scores provided by expert human annotators in order to obtain a subjective quality measure. In addition, we propose a region selection method to identify the image regions that are better suited at measuring perceptual quality. Finally, our experimental evaluation shows that our learning-based approach outperforms existing methods and that our region selection algorithm consistently improves the quality estimation.

Webly Supervised Image-Text Embedding with Noisy Tag Refinement

Niluthpol Mithun, Ravdeep Pasricha, Evangelos Papalexakis, Amit Roy-Chowdhury

Responsive image

Auto-TLDR; Robust Joint Embedding for Image-Text Retrieval Using Web Images

Slides Similar

In this paper, we address the problem of utilizing web images in training robust joint embedding models for the image-text retrieval task. Prior webly supervised approaches directly leverage weakly annotated web images in the joint embedding learning framework. The objective of these approaches would suffer significantly when the ratio of noisy and missing tags associated with the web images is very high. In this regard, we propose a CP decomposition based tensor completion framework to refine the tags of web images by modeling observed ternary inter-relations between the sets of labeled images, tags, and web images as a tensor. To effectively deal with the high ratio of missing entries likely in our case, we incorporate intra-modal correlation as side information in the proposed framework. Our tag refinement approach combined with existing web supervised image-text embedding approaches provide a more principled way for learning the joint embedding models in the presence of significant noise from web data and limited clean labeled data. Experiments on benchmark datasets demonstrate that the proposed approach helps to achieve a significant performance gain in image-text retrieval.

Exploiting Non-Linear Redundancy for Neural Model Compression

Muhammad Ahmed Shah, Raphael Olivier, Bhiksha Raj

Responsive image

Auto-TLDR; Compressing Deep Neural Networks with Linear Dependency

Slides Poster Similar

Deploying deep learning models with millions, even billions, of parameters is challenging given real world memory, power and compute constraints. In an effort to make these models more practical, in this paper, we propose a novel model compression approach that exploits linear dependence between the activations in a layer to eliminate entire structural units (neurons/convolutional filters). Our approach also adjusts the weights of the layer in a manner that is provably lossless while training if the removed neuron was perfectly predictable. We combine this approach with an annealing algorithm that may be applied during training, or even on a trained model, and demonstrate, using popular datasets, that our technique can reduce the parameters of VGG and AlexNet by more than 97\% on \cifar, 85\% on \caltech, and 19\% on ImageNet at less than 2\% loss in accuracy. Furthermore, we provide theoretical results showing that in overparametrized, locally linear (ReLU) neural networks where redundant features exist, and with correct hyperparameter selection, our method is indeed able to capture and suppress those dependencies.

Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation

Dimche Kostadinov, Davide Scarammuza

Responsive image

Auto-TLDR; Unsupervised Representation Learning from Local Event Data for Pattern Recognition

Slides Poster Similar

Event-based cameras record asynchronous streamof per-pixel brightness changes. As such, they have numerous advantages over the common frame-based cameras, including high temporal resolution, high dynamic range, and no motion blur. Due to the asynchronous nature, efficient learning of compact representation for event data is challenging. While the extend to which the spatial and temporal event "information" is useful for pattern recognition tasks is not fully explored. In this paper, we focus on single layer architectures. We analyze the performance of two general problem formulations,i.e., the direct and the inverse, for unsupervised feature learning from local event data,i.e., local volumes of events that are described in space and time. We identify and show the main advantages of each approach. Theoretically, we analyze guarantees for local optimal solution, possibility for asynchronous and parallel parameter update as well as the computational complexity. We present numerical experiments for the task of object recognition, where we evaluate the solution under the direct and the inverse problem.We give a comparison with the state-of-the-art methods. Our empirical results highlight the advantages of the both approaches for representation learning from event data. Moreover, we show improvements of up to 9% in the recognition accuracy compared to the state-of-the-art methods from the same class of methods.