MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recognition

Kaiyu Shan, Yongtao Wang, Zhi Tang, Ying Chen, Yangyan Li

Responsive image

Auto-TLDR; Mixed Temporal Convolution for Action Recognition

Slides Poster

To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone. However, they all exploit 1D temporal convolution of fixed kernel size (i.e., 3) in the network building block, thus have suboptimal temporal modeling capability to handle both long term and short-term actions. To address this problem, we first investigate the impacts of different kernel sizes for the 1D temporal convolutional filters. Then, we propose a simple yet efficient operation called Mixed Temporal Convolution (MixTConv) in methodology, which consists of multiple depthwise 1D convolutional filters with different kernel sizes. By plugging MixTConv into the conventional 2D CNN backbone ResNet-50, we further propose an efficient and effective network architecture named MSTNet for action recognition, and achieve state-of-the-art results on multiple large-scale benchmarks.

Similar papers

MFI: Multi-Range Feature Interchange for Video Action Recognition

Sikai Bai, Qi Wang, Xuelong Li

Responsive image

Auto-TLDR; Multi-range Feature Interchange Network for Action Recognition in Videos

Slides Poster Similar

Short-range motion features and long-range dependencies are two complementary and vital cues for action recognition in videos, but it remains unclear how to efficiently and effectively extract these two features. In this paper, we propose a novel network to capture these two features in a unified 2D framework. Specifically, we first construct a Short-range Temporal Interchange (STI) block, which contains a Channels-wise Temporal Interchange (CTI) module for encoding short-range motion features. Then a Graph-based Regional Interchange (GRI) module is built to present long-range dependencies using graph convolution. Finally, we replace original bottleneck blocks in the ResNet with STI blocks and insert several GRI modules between STI blocks, to form a Multi-range Feature Interchange (MFI) Network. Practically, extensive experiments are conducted on three action recognition datasets (i.e., Something-Something V1, HMDB51, and UCF101), which demonstrate that the proposed MFI network achieves impressive results with very limited computing cost.

Learnable Higher-Order Representation for Action Recognition

Jie Shao, Xiangyang Xue

Responsive image

Auto-TLDR; Learningable Higher-Order Operations for Spatiotemporal Dynamics in Video Recognition

Similar

Capturing spatiotemporal dynamics is an essential topic in video recognition. In this paper, we present learnable higher-order operations as a generic family of building blocks for capturing spatiotemporal dynamics from RGB input video space. Similar to higher-order functions, the weights of higher-order operations are themselves derived from the data with learnable parameters. Classical architectures such as residual learning and network-in-network are first-order operations where weights are directly learned from the data. Higher-order operations make it easier to capture context-sensitive patterns, such as motion. Self-attention models are also higher-order operations, but the attention weights are mostly computed from an affine operation or dot product. The learnable higher-order operations can be more generic and flexible. Experimentally, we show that on the task of video recognition, our higher-order models can achieve results on par with or better than the existing state-of-the-art methods on Something-Something (V1 and V2), Kinetics and Charades datasets.

Region-Based Non-Local Operation for Video Classification

Guoxi Huang, Adrian Bors

Responsive image

Auto-TLDR; Regional-based Non-Local Operation for Deep Self-Attention in Convolutional Neural Networks

Slides Poster Similar

Convolutional Neural Networks (CNNs) model long-range dependencies by deeply stacking convolution operations with small window sizes, which makes the optimizations difficult. This paper presents region-based non-local operation (RNL), a family of self-attention mechanisms, which can directly capture long-range dependencies without a deep stack of local operations. Given an intermediate feature map, our method recalibrates the feature at a position by aggregating information from the neighboring regions of all positions. By combining a channel attention module with the proposed RNL, we design an attention chain, which can be integrated into off-the-shelf CNNs for end-to-end training. We evaluate our method on two video classification benchmarks. The experimental result of our method outperforms other attention mechanisms, and we achieve state-of-the-art performance on Something-Something V1.

Motion Complementary Network for Efficient Action Recognition

Ke Cheng, Yifan Zhang, Chenghua Li, Jian Cheng, Hanqing Lu

Responsive image

Auto-TLDR; Efficient Motion Complementary Network for Action Recognition

Slides Poster Similar

Both two-stream ConvNet and 3D ConvNet are widely used in action recognition. However, both methods are not efficient for deployment: calculating optical flow is very slow, while 3D convolution is computationally expensive. Our key insight is that the motion information from optical flow maps is complementary to the motion information from 3D ConvNet. Instead of simply combining these two methods, we propose two novel techniques to enhance the performance with less computational cost: \textit{fixed-motion-accumulation} and \textit{balanced-motion-policy}. With these two techniques, we propose a novel framework called Efficient Motion Complementary Network(EMC-Net) that enjoys both high efficiency and high performance. We conduct extensive experiments on Kinetics, UCF101, and Jester datasets. We achieve notably higher performance while consuming 4.7$\times$ less computation than I3D, 11.6$\times$ less computation than ECO, 17.8$\times$ less computation than R(2+1)D. On Kinetics dataset, we achieve 2.6\% better performance than the recent proposed TSM with 1.4$\times$ fewer FLOPs and 10ms faster on K80 GPU.

SCA Net: Sparse Channel Attention Module for Action Recognition

Hang Song, Yonghong Song, Yuanlin Zhang

Responsive image

Auto-TLDR; SCA Net: Efficient Group Convolution for Sparse Channel Attention

Slides Poster Similar

Channel attention has shown its great performance recently when it was incorporated into deep convolutional neural networks. However, existing methods usually require extensive computing resources due to their involuted structure, which is hard for 3D CNNs to take full advantage of. In this paper, a lightweight sparse channel attention (SCA) module implemented by efficient group convolution is proposed, which adopts the idea of sparse channel connection and involves much less parameters but brings clear performance gain. Meanwhile, to solve the lack of local channel interaction brought by group convolution, a dominant function called Aggregate-Shuffle-Diverge (ASD) is leveraged to enhance information flow over each group with no additional parameters. We also adjust the existing mainstream 3D CNNs by employing 3D convolution factorization, so as to further reduce the parameters. Our SCA module can be flexibly incorporated into most existing 3D CNNs, all of which can achieve a perfect trade-off between performance and complexity on action recognition task with factorized I3D or 3D ResNet backbone networks. The experimental results also indicate that the resulting network, namely, SCA Net can achieve an outstanding performance on UCF-101 and HMDB-51 datasets.

You Ought to Look Around: Precise, Large Span Action Detection

Ge Pan, Zhang Han, Fan Yu, Yonghong Song, Yuanlin Zhang, Han Yuan

Responsive image

Auto-TLDR; YOLA: Local Feature Extraction for Action Localization with Variable receptive field

Slides Similar

For the action localization task, pre-defined action anchors are the cornerstone of mainstream techniques. State-of-the-art models mostly rely on a dense segmenting scheme, where anchors are sampled uniformly over the temporal domain with a predefined set of scales. However, it is not sufficient because action duration varies greatly. Therefore, it is necessary for the anchors or proposals to have a variable receptive field. In this paper, we propose a method called YOLA (You Ought to Look Around) which includes three parts: 1) a robust backbone SPN-I3D for extracting spatio-temporal features. In this part, we employ a stronger backbone I3D with SPN (Segment Pyramid Network) instead of C3D to obtain multi-scale features; 2) a simple but useful feature fusion module named LFE (Local Feature Extraction). Compared with the fully connected layer and global average pooling, our LFE model is more advantageous for network to fit and fuse features. 3) a new feature segment aligning method called TPGC (Two Pathway Graph Convolution), which allows one proposal to leverage semantic features of adjacent proposals to update its content and make sure the proposals have a variable receptive field. YOLA add only a small overhead to the baseline network, and is easy to train in an end-to-end manner, running at a speed of 1097 fps. YOLA achieves a mAP of 58.3%, outperforming all existing models including both RGB-based and two stream on THUMOS'14, and achieves competitive results on ActivityNet 1.3.

Single View Learning in Action Recognition

Gaurvi Goyal, Nicoletta Noceti, Francesca Odone

Responsive image

Auto-TLDR; Cross-View Action Recognition Using Domain Adaptation for Knowledge Transfer

Slides Poster Similar

Viewpoint is an essential aspect of how an action is visually perceived, with the motion appearing substantially different for some viewpoint pairs. Data driven action recognition algorithms compensate for this by including a variety of viewpoints in their training data, adding to the cost of data acquisition as well as training. We propose a novel methodology that leverages deeply pretrained features to learn actions from a single viewpoint using domain adaptation for knowledge transfer. We demonstrate the effectiveness of this pipeline on 3 different datasets: IXMAS, MoCA and NTU RGBD+, and compare with both classical and deep learning methods. Our method requires low training data and demonstrates unparalleled cross-view action recognition accuracies for single view learning.

3D Attention Mechanism for Fine-Grained Classification of Table Tennis Strokes Using a Twin Spatio-Temporal Convolutional Neural Networks

Pierre-Etienne Martin, Jenny Benois-Pineau, Renaud Péteri, Julien Morlier

Responsive image

Auto-TLDR; Attentional Blocks for Action Recognition in Table Tennis Strokes

Slides Poster Similar

The paper addresses the problem of recognition of actions in video with low inter-class variability such as Table Tennis strokes. Two stream, "twin" convolutional neural networks are used with 3D convolutions both on RGB data and optical flow. Actions are recognized by classification of temporal windows. We introduce 3D attention modules and examine their impact on classification efficiency. In the context of the study of sportsmen performances, a corpus of the particular actions of table tennis strokes is considered. The use of attention blocks in the network speeds up the training step and improves the classification scores up to 5% with our twin model. We visualize the impact on the obtained features and notice correlation between attention and player movements and position. Score comparison of state-of-the-art action classification method and proposed approach with attentional blocks is performed on the corpus. Proposed model with attention blocks outperforms previous model without them and our baseline.

TinyVIRAT: Low-Resolution Video Action Recognition

Ugur Demir, Yogesh Rawat, Mubarak Shah

Responsive image

Auto-TLDR; TinyVIRAT: A Progressive Generative Approach for Action Recognition in Videos

Slides Poster Similar

The existing research in action recognition is mostly focused on high-quality videos where the action is distinctly visible. In real-world surveillance environments, the actions in videos are captured at a wide range of resolutions. Most activities occur at a distance with a small resolution and recognizing such activities is a challenging problem. In this work, we focus on recognizing tiny actions in videos. We introduce a benchmark dataset, TinyVIRAT, which contains natural low-resolution activities. The actions in TinyVIRAT videos have multiple labels and they are extracted from surveillance videos which makes them realistic and more challenging. We propose a novel method for recognizing tiny actions in videos which utilizes a progressive generative approach to improve the quality of low-resolution actions. The proposed method also consists of a weakly trained attention mechanism which helps in focusing on the activity regions in the video. We perform extensive experiments to benchmark the proposed TinyVIRAT dataset and observe that the proposed method significantly improves the action recognition performance over baselines. We also evaluate the proposed approach on synthetically resized action recognition datasets and achieve state-of-the-art results when compared with existing methods. The dataset and code will be publicly available.

2D Deep Video Capsule Network with Temporal Shift for Action Recognition

Théo Voillemin, Hazem Wannous, Jean-Philippe Vandeborre

Responsive image

Auto-TLDR; Temporal Shift Module over Capsule Network for Action Recognition in Continuous Videos

Slides Similar

Action recognition in continuous video streams is a growing field since the past few years. Deep learning techniques and in particular Convolutional Neural Networks (CNNs) achieved good results in this topic. However, intrinsic CNNs limitations begin to cap the results since 2D CNN cannot capture temporal information and 3D CNN are to much resource demanding for real-time applications. Capsule Network, evolution of CNN, already proves its interesting benefits on small and low informational datasets like MNIST but yet its true potential has not emerged. In this paper we tackle the action recognition problem by proposing a new architecture combining Temporal Shift module over deep Capsule Network. Temporal Shift module permits us to insert temporal information over 2D Capsule Network with a zero computational cost to conserve the lightness of 2D capsules and their ability to connect spatial features. Our proposed approach outperforms or brings near state-of-the-art results on color and depth information on public datasets like First Person Hand Action and DHG 14/28 with a number of parameters 10 to 40 times less than existing approaches.

Channel-Wise Dense Connection Graph Convolutional Network for Skeleton-Based Action Recognition

Michael Lao Banteng, Zhiyong Wu

Responsive image

Auto-TLDR; Two-stream channel-wise dense connection GCN for human action recognition

Slides Poster Similar

Skeleton-based action recognition task has drawn much attention for many years. Graph Convolutional Network (GCN) has proved its effectiveness in this task. However, how to improve the model's robustness to different human actions and how to make effective use of features produced by the network are main topics needed to be further explored. Human actions are time series sequence, meaning that temporal information is a key factor to model the representation of data. The ranges of body parts involved in small actions (e.g. raise a glass or shake head) and big actions (e.g. walking or jumping) are diverse. It's crucial for the model to generate and utilize more features that can be adaptive to a wider range of actions. Furthermore, feature channels are specific with the action class, the model needs to weigh their importance and pay attention to more related ones. To address these problems, in this work, we propose a two-stream channel-wise dense connection GCN (2s-CDGCN). Specifically, the skeleton data was extracted and processed into spatial and temporal information for better feature representation. A channel-wise attention module was used to select and emphasize the more useful features generated by the network. Moreover, to ensure maximum information flow, dense connection was introduced to the network structure, which enables the network to reuse the skeleton features and generate more information adaptive and related to different human actions. Our model has shown its ability to improve the accuracy of human action recognition task on two large datasets, NTU-RGB+D and Kinetics. Extensive evaluations were conducted to prove the effectiveness of our model.

Temporal Extension Module for Skeleton-Based Action Recognition

Yuya Obinata, Takuma Yamamoto

Responsive image

Auto-TLDR; Extended Temporal Graph for Action Recognition with Kinetics-Skeleton

Slides Poster Similar

We present a module that extends the temporal graph of a graph convolutional network (GCN) for action recognition with a sequence of skeletons. Existing methods attempt to represent a more appropriate spatial graph on an intra-frame, but disregard optimization of the temporal graph on the inter-frame. Concretely, these methods connect between vertices corresponding only to the same joint on the inter-frame. In this work, we focus on adding connections to neighboring multiple vertices on the inter-frame and extracting additional features based on the extended temporal graph. Our module is a simple yet effective method to extract correlated features of multiple joints in human movement. Moreover, our module aids in further performance improvements, along with other GCN methods that optimize only the spatial graph. We conduct extensive experiments on two large datasets, NTU RGB+D and Kinetics-Skeleton, and demonstrate that our module is effective for several existing models and our final model achieves state-of-the-art performance.

Improved Residual Networks for Image and Video Recognition

Ionut Cosmin Duta, Li Liu, Fan Zhu, Ling Shao

Responsive image

Auto-TLDR; Residual Networks for Deep Learning

Slides Poster Similar

Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address all three main components of a ResNet: the flow of information through the network layers, the residual building block, and the projection shortcut. We are able to show consistent improvements in accuracy and learning convergence over the baseline. For instance, on ImageNet dataset, using the ResNet with 50 layers, for top-1 accuracy we can report a 1.19% improvement over the baseline in one setting and around 2% boost in another. Importantly, these improvements are obtained without increasing the model complexity. Our proposed approach allows us to train extremely deep networks, while the baseline shows severe optimization issues. We report results on three tasks over six datasets: image classification (ImageNet, CIFAR-10 and CIFAR-100), object detection (COCO) and video action recognition (Kinetics-400 and Something-Something-v2). In the deep learning era, we establish a new milestone for the depth of a CNN. We successfully train a 404-layer deep CNN on the ImageNet dataset and a 3002-layer network on CIFAR-10 and CIFAR-100, while the baseline is not able to converge at such extreme depths. Code is available at: https://github.com/iduta/iresnet

RWF-2000: An Open Large Scale Video Database for Violence Detection

Ming Cheng, Kunjing Cai, Ming Li

Responsive image

Auto-TLDR; Flow Gated Network for Violence Detection in Surveillance Cameras

Slides Poster Similar

In recent years, surveillance cameras are widely deployed in public places, and the general crime rate has been reduced significantly due to these ubiquitous devices. Usually, these cameras provide cues and evidence after crimes were conducted, while they are rarely used to prevent or stop criminal activities in time. It is both time and labor consuming to manually monitor a large amount of video data from surveillance cameras. Therefore, automatically recognizing violent behaviors from video signals becomes essential. In this paper, we summarize several existing video datasets for violence detection and propose a new video dataset with 2,000 videos all captured by surveillance cameras in real-world scenes. Also, we present a new method that utilizes both the merits of 3D-CNNs and optical flow, namely Flow Gated Network. The proposed approach obtains an accuracy of 87.25% on the test set of our proposed RWF-2000 database. The proposed database and source codes of this paper are currently open to access.

RMS-Net: Regression and Masking for Soccer Event Spotting

Matteo Tomei, Lorenzo Baraldi, Simone Calderara, Simone Bronzin, Rita Cucchiara

Responsive image

Auto-TLDR; An Action Spotting Network for Soccer Videos

Slides Poster Similar

The recently proposed action spotting task consists in finding the exact timestamp in which an event occurs. This task fits particularly well for soccer videos, where events correspond to salient actions strictly defined by soccer rules (a goal occurs when the ball crosses the goal line). In this paper, we devise a lightweight and modular network for action spotting, which can simultaneously predict the event label and its temporal offset using the same underlying features. We enrich our model with two training strategies: the first one for data balancing and uniform sampling, the second for masking ambiguous frames and keeping the most discriminative visual cues. When tested on the SoccerNet dataset and using standard features, our full proposal exceeds the current state of the art by 3 Average-mAP points. Additionally, it reaches a gain of more than 10 Average-mAP points on the test set when fine-tuned in combination with a strong 2D backbone.

A Grid-Based Representation for Human Action Recognition

Soufiane Lamghari, Guillaume-Alexandre Bilodeau, Nicolas Saunier

Responsive image

Auto-TLDR; GRAR: Grid-based Representation for Action Recognition in Videos

Slides Poster Similar

Human action recognition (HAR) in videos is a fundamental research topic in computer vision. It consists mainly in understanding actions performed by humans based on a sequence of visual observations. In recent years, HAR have witnessed significant progress, especially with the emergence of deep learning models. However, most of existing approaches for action recognition rely on information that is not always relevant for the task, and are limited in the way they fuse temporal information. In this paper, we propose a novel method for human action recognition that encodes efficiently the most discriminative appearance information of an action with explicit attention on representative pose features, into a new compact grid representation. Our GRAR (Grid-based Representation for Action Recognition) method is tested on several benchmark datasets that demonstrate that our model can accurately recognize human actions, despite intra-class appearance variations and occlusion challenges.

Temporal Attention-Augmented Graph Convolutional Network for Efficient Skeleton-Based Human Action Recognition

Negar Heidari, Alexandros Iosifidis

Responsive image

Auto-TLDR; Temporal Attention Module for Efficient Graph Convolutional Network-based Action Recognition

Slides Poster Similar

Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep feed-forward networks with high computational complexity to process all skeletons in an action. This leads to a high number of floating point operations (ranging from 16G to 100G FLOPs) to process a single sample, making their adoption in restricted computation application scenarios infeasible. In this paper, we propose a temporal attention module (TAM) for increasing the efficiency in skeleton-based action recognition by selecting the most informative skeletons of an action at the early layers of the network. We incorporate the TAM in a light-weight GCN topology to further reduce the overall number of computations. Experimental results on two benchmark datasets show that the proposed method outperforms with a large margin the baseline GCN-based method while having 2.9 times less number of computations. Moreover, it performs on par with the state-of-the-art with up to 9.6 times less number of computations.

Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos

Mamshad Nayeem Rizve, Ugur Demir, Praveen Praveen Tirupattur, Aayush Jung Rana, Kevin Duarte, Ishan Rajendrakumar Dave, Yogesh Rawat, Mubarak Shah

Responsive image

Auto-TLDR; Gabriella: A Real-Time Online System for Activity Detection in Surveillance Videos

Slides Similar

Activity detection in surveillance videos is a difficult problem due to multiple factors such as large field of view, presence of multiple activities, varying scales and viewpoints, and its untrimmed nature. The existing research in activity detection is mainly focused on datasets, such as UCF-101, JHMDB, THUMOS, and AVA, which partially address these issues. The requirement of processing the surveillance videos in real-time makes this even more challenging. In this work we propose Gabriella, a real-time online system to perform activity detection on untrimmed surveillance videos. The proposed method consists of three stages: tubelet extraction, activity classification, and online tubelet merging. For tubelet extraction, we propose a localization network which takes a video clip as input and spatio-temporally detects potential foreground regions at multiple scales to generate action tubelets. We propose a novel Patch-Dice loss to handle large variations in actor size. Our online processing of videos at a clip level drastically reduces the computation time in detecting activities. The detected tubelets are assigned activity class scores by the classification network and merged together using our proposed Tubelet-Merge Action-Split (TMAS) algorithm to form the final action detections. The TMAS algorithm efficiently connects the tubelets in an online fashion to generate action detections which are robust against varying length activities. We perform our experiments on the VIRAT and MEVA (Multiview Extended Video with Activities) datasets and demonstrate the effectiveness of the proposed approach in terms of speed ($\sim$100 fps) and performance with state-of-the-art results. The code and models will be made publicly available.

Recurrent Graph Convolutional Networks for Skeleton-Based Action Recognition

Guangming Zhu, Lu Yang, Liang Zhang, Peiyi Shen, Juan Song

Responsive image

Auto-TLDR; Recurrent Graph Convolutional Network for Human Action Recognition

Slides Poster Similar

Human action recognition is one of the challenging and active research fields due to its wide applications. Recently, graph convolutions for skeleton-based action recognition have attracted much attention. Generally, the adjacency matrices of the graph are fixed to the hand-crafted physical connectivity of the human joints, or learned adaptively via deep learining. The hand-crafted or learned adjacency matrices are fixed when processing each frame of an action sequence. However, the interactions of different subsets of joints may play a core role at different phases of an action. Therefore, it is reasonable to evolve the graph topology with time. In this paper, a recurrent graph convolution is proposed, in which the graph topology is evolved via a long short-term memory (LSTM) network. The proposed recurrent graph convolutional network (R-GCN) can recurrently learn the data-dependent graph topologies for different layers, different time steps and different kinds of actions. Experimental results on the NTU RGB+D and Kinetics-Skeleton datasets demonstrate the advantages of the proposed R-GCN.

Attention Pyramid Module for Scene Recognition

Zhinan Qiao, Xiaohui Yuan, Chengyuan Zhuang, Abolfazl Meyarian

Responsive image

Auto-TLDR; Attention Pyramid Module for Multi-Scale Scene Recognition

Slides Poster Similar

The unrestricted open vocabulary and diverse substances of scenery images bring significant challenges to scene recognition. However, most deep learning architectures and attention methods are developed on general-purpose datasets and omit the characteristics of scene data. In this paper, we exploit the attention pyramid module (APM) to tackle the predicament of scene recognition. Our method streamlines the multi-scale scene recognition pipeline, learns comprehensive scene features at various scales and locations, addresses the interdependency among scales, and further assists feature re-calibration as well as aggregation process. APM is extremely light-weighted and can be easily plugged into existing network architectures in a parameter-efficient manner. By simply integrating APM into ResNet-50, we obtain a 3.54\% boost in terms of top-1 accuracy on the benchmark scene dataset. Comprehensive experiments show that APM achieves better performance comparing with state-of-the-art attention methods using significant less computation budget. Code and pre-trained models will be made publicly available.

Towards Practical Compressed Video Action Recognition: A Temporal Enhanced Multi-Stream Network

Bing Li, Longteng Kong, Dongming Zhang, Xiuguo Bao, Di Huang, Yunhong Wang

Responsive image

Auto-TLDR; TEMSN: Temporal Enhanced Multi-Stream Network for Compressed Video Action Recognition

Slides Poster Similar

Current compressed video action recognition methods are mainly based on completely received compressed videos. However, in real transmission, the compressed video packets are usually disorderly received and lost due to network jitters or congestion. It is of great significance to recognize actions in early phases with limited packets, e.g. forecasting the potential risks from videos quickly. In this paper, we proposed a Temporal Enhanced Multi-Stream Network (TEMSN) for practical compressed video action recognition. First, we use three compressed modalities as complementary cues and build a multi-stream network to capture the rich information from compressed video packets. Second, we design a temporal enhanced module based on Encoder-Decoder structure applied on each stream to infer the missing packets, and generate more complete action dynamics. Thanks to the rich modalities and temporal enhancement, our approach is able to better modeling the action with limited compressed packets. Experiments on HMDB-51 and UCF-101 dataset validate its effectiveness and efficiency.

Dynamic Multi-Path Neural Network

Yingcheng Su, Yichao Wu, Ken Chen, Ding Liang, Xiaolin Hu

Responsive image

Auto-TLDR; Dynamic Multi-path Neural Network

Slides Similar

Although deeper and larger neural networks have achieved better performance, due to overwhelming burden on computation, they cannot meet the demands of deployment on resource-limited devices. An effective strategy to address this problem is to make use of dynamic inference mechanism, which changes the inference path for different samples at runtime. Existing methods only reduce the depth by skipping an entire specific layer, which may lose important information in this layer. In this paper, we propose a novel method called Dynamic Multi-path Neural Network (DMNN), which provides more topology choices in terms of both width and depth on the fly. For better modelling the inference path selection, we further introduce previous state and object category information to guide the training process. Compared to previous dynamic inference techniques, the proposed method is more flexible and easier to incorporate into most modern network architectures. Experimental results on ImageNet and CIFAR-100 demonstrate the superiority of our method on both efficiency and classification accuracy.

JT-MGCN: Joint-Temporal Motion Graph Convolutional Network for Skeleton-Based Action Recognition

Suekyeong Nam, Seungkyu Lee

Responsive image

Auto-TLDR; Joint-temporal Motion Graph Convolutional Networks for Action Recognition

Slides Similar

Recently, action recognition methods using graph convolutional networks (GCN) have shown remarkable performance thanks to its concise but effective representation of human body motion. Prior methods construct human body motion graph building edges between neighbor or distant body joints. On the other hand, human action contains lots of temporal variations showing strong temporal correlations between joint motions. Thus the characterization of an action requires a comprehensive analysis of joint motion correlations on spatial and temporal domains. In this paper, we propose Joint-temporal Motion Graph Convolutional Networks (JT-MGCN) in which joint-temporal edges learn the correlations between different joints at different time. Experimental evaluation on large public data sets such as NTU rgb+d data set and kinetics-skeleton data set show outstanding action recognition performance.

Self-Supervised Joint Encoding of Motion and Appearance for First Person Action Recognition

Mirco Planamente, Andrea Bottino, Barbara Caputo

Responsive image

Auto-TLDR; A Single Stream Architecture for Egocentric Action Recognition from the First-Person Point of View

Slides Poster Similar

Wearable cameras are becoming more and more popular in several applications, increasing the interest of the research community in developing approaches for recognizing actions from the first-person point of view. An open challenge in egocentric action recognition is that videos lack detailed information about the main actor's pose and thus tend to record only parts of the movement when focusing on manipulation tasks. Thus, the amount of information about the action itself is limited, making crucial the understanding of the manipulated objects and their context. Many previous works addressed this issue with two-stream architectures, where one stream is dedicated to modeling the appearance of objects involved in the action, and another to extracting motion features from optical flow. In this paper, we argue that learning features jointly from these two information channels is beneficial to capture the spatio-temporal correlations between the two better. To this end, we propose a single stream architecture able to do so, thanks to the addition of a self-supervised block that uses a pretext motion prediction task to intertwine motion and appearance knowledge. Experiments on several publicly available databases show the power of our approach.

Pose-Based Body Language Recognition for Emotion and Psychiatric Symptom Interpretation

Zhengyuan Yang, Amanda Kay, Yuncheng Li, Wendi Cross, Jiebo Luo

Responsive image

Auto-TLDR; Body Language Based Emotion Recognition for Psychiatric Symptoms Prediction

Slides Poster Similar

Inspired by the human ability to infer emotions from body language, we propose an automated framework for body language based emotion recognition starting from regular RGB videos. In collaboration with psychologists, we further extend the framework for psychiatric symptom prediction. Because a specific application domain of the proposed framework may only supply a limited amount of data, the framework is designed to work on a small training set and possess a good transferability. The proposed system in the first stage generates sequences of body language predictions based on human poses estimated from input videos. In the second stage, the predicted sequences are fed into a temporal network for emotion interpretation and psychiatric symptom prediction. We first validate the accuracy and transferability of the proposed body language recognition method on several public action recognition datasets. We then evaluate the framework on a proposed URMC dataset, which consists of conversations between a standardized patient and a behavioral health professional, along with expert annotations of body language, emotions, and potential psychiatric symptoms. The proposed framework outperforms other methods on the URMC dataset.

GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Semantic Segmentation

Zhuoying Wang, Yongtao Wang, Zhi Tang, Yangyan Li, Ying Chen, Haibin Ling, Weisi Lin

Responsive image

Auto-TLDR; Gated Scale-Transfer Operation for Semantic Segmentation

Slides Poster Similar

Existing CNN-based methods for semantic segmentation heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation. State-of-the-art segmentation networks widely exploit conventional scale-transfer operations, i.e., up-sampling and down-sampling to learn multi-scale features. In this work, we find that these operations lead to scale-confused features and suboptimal performance because they are spatial-invariant and directly transit all feature information cross scales without spatial selection. To address this issue, we propose the Gated Scale-Transfer Operation (GSTO) to properly transit spatial-filtered features to another scale. Specifically, GSTO can work either with or without extra supervision. Unsupervised GSTO is learned from the feature itself while the supervised one is guided by the supervised probability matrix. Both forms of GSTO are lightweight and plug-and-play, which can be flexibly integrated into networks or modules for learning better multi-scale features. In particular, by plugging GSTO into HRNet, we get a more powerful backbone (namely GSTO-HRNet) for pixel labeling, and it achieves new state-of-the-art results on multiple benchmarks for semantic segmentation including Cityscapes, LIP and Pascal Context, with negligible extra computational cost. Moreover, experiment results demonstrate that GSTO can also significantly boost the performance of multi-scale feature aggregation modules like PPM and ASPP.

Attention-Oriented Action Recognition for Real-Time Human-Robot Interaction

Ziyang Song, Ziyi Yin, Zejian Yuan, Chong Zhang, Wanchao Chi, Yonggen Ling, Shenghao Zhang

Responsive image

Auto-TLDR; Attention-Oriented Multi-Level Network for Action Recognition in Interaction Scenes

Slides Poster Similar

Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task in interaction scenes and propose an attention-oriented multi-level network framework to meet the need for real-time interaction. Specifically, a Pre-Attention network is employed to roughly focus on the interactor in the scene at low resolution firstly and then perform fine-grained pose estimation at high resolution. The other compact CNN receives the extracted skeleton sequence as input for action recognition, utilizing attention-like mechanisms to capture local spatial-temporal patterns and global semantic information effectively. To evaluate our approach, we construct a new action dataset specially for the recognition task in interaction scenes. Experimental results on our dataset and high efficiency (112 fps at 640 x 480 RGBD) on the mobile computing platform (Nvidia Jetson AGX Xavier) demonstrate excellent applicability of our method on action recognition in real-time human-robot interaction.

Attention-Driven Body Pose Encoding for Human Activity Recognition

Bappaditya Debnath, Swagat Kumar, Marry O'Brien, Ardhendu Behera

Responsive image

Auto-TLDR; Attention-based Body Pose Encoding for Human Activity Recognition

Slides Poster Similar

This article proposes a novel attention-based body pose encoding for human activity recognition. Most of the existing human activity recognition approaches based on 3D pose data often enrich the input data using additional handcrafted representations such as velocity, super normal vectors, pairwise relations, and so on. The enriched data complements the 3D body joint position data and improves the model performance. In this paper, we propose a novel approach that learns enhanced feature representations from a given sequence of 3D body joints. To achieve this, the approach exploits two body pose streams: 1) a spatial stream which encodes the spatial relationship between various body joints at each time point to learn spatial structure involving the spatial distribution of different body joints 2) a temporal stream that learns the temporal variation of individual body joints over the entire sequence duration to present a temporally enhanced representation. Afterwards, these two pose streams are fused with a multi-head attention mechanism. We also capture the contextual information from the RGB video stream using a deep Convolutional Neural Network (CNN) model combined with a multi-head attention and a bidirectional Long Short-Term Memory (LSTM) network. Finally, the RGB video stream is combined with the fused body pose stream to give a novel end-to-end deep model for effective human activity recognition. The proposed model is evaluated on three datasets including the challenging NTU-RGBD dataset and achieves state-of-the-art results.

What and How? Jointly Forecasting Human Action and Pose

Yanjun Zhu, Yanxia Zhang, Qiong Liu, Andreas Girgensohn

Responsive image

Auto-TLDR; Forecasting Human Actions and Motion Trajectories with Joint Action Classification and Pose Regression

Slides Poster Similar

Forecasting human actions and motion trajectories addresses the problem of predicting what a person is going to do next and how they will perform it. This is crucial in a wide range of applications such as assisted living and future co-robotic settings. We propose to simultaneously learn actions and action-related human motion dynamics, while existing works perform them independently. In this paper, we present a method to jointly forecast categories of human action and the pose of skeletal joints in the hope that the two tasks can help each other. As a result, our system can predict not only the future actions but also the motion trajectories that will result. To achieve this, we define a task of joint action classification and pose regression. We employ a sequence to sequence encoder-decoder model combined with multi-task learning to forecast future actions and poses progressively before the action happens. Experimental results on two public datasets, IkeaDB and OAD, demonstrate the effectiveness of the proposed method.

Context Aware Group Activity Recognition

Avijit Dasgupta, C. V. Jawahar, Karteek Alahari

Responsive image

Auto-TLDR; A Two-Stream Architecture for Group Activity Recognition in Multi-Person Videos

Slides Poster Similar

This paper addresses the task of group activity recognition in multi-person videos. Existing approaches decompose this task into feature learning and relational reasoning. Despite showing progress, these methods only rely on appearance features for people and overlook the available contextual information, which can play an important role in group activity understanding. In this work, we focus on the feature learning aspect and propose a two-stream architecture that not only considers person-level appearance features, but also makes use of contextual information present in videos for group activity recognition. In particular, we propose to use two types of contextual information beneficial for two different scenarios: \textit{pose context} and \textit{scene context} that provide crucial cues for group activity understanding. We combine appearance and contextual features to encode each person with an enriched representation. Finally, these combined features are used in relational reasoning for predicting group activities. We evaluate our method on two benchmarks, Volleyball and Collective Activity and show that joint modeling of contextual information with appearance features benefits in group activity understanding.

DeepPear: Deep Pose Estimation and Action Recognition

Wen-Jiin Tsai, You-Ying Jhuang

Responsive image

Auto-TLDR; Human Action Recognition Using RGB Video Using 3D Human Pose and Appearance Features

Slides Poster Similar

Human action recognition has been a popular issue recently because it can be applied in many applications such as intelligent surveillance systems, human-robot interaction, and autonomous vehicle control. Human action recognition using RGB video is a challenging task because the learning of actions is easily affected by the cluttered background. To cope with this problem, the proposed method estimates 3D human poses first which can help remove the cluttered background and focus on the human body. In addition to the human poses, the proposed method also utilizes appearance features nearby the predicted joints to make our action prediction context-aware. Instead of using 3D convolutional neural networks as many action recognition approaches did, the proposed method uses a two-stream architecture that aggregates the results from skeleton-based and appearance-based approaches to do action recognition. Experimental results show that the proposed method achieved state-of-the-art performance on NTU RGB+D which is a largescale dataset for human action recognition.

Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatio-Temporal Graph Convolutional Network for Action Recognition

Konstantinos Papadopoulos, Enjie Ghorbel, Djamila Aouada, Bjorn Ottersten

Responsive image

Auto-TLDR; Spatio-Temporal Graph Convolutional Network for Skeleton-Based Action Recognition

Slides Poster Similar

Spatio-temporal Graph Convolutional Networks (ST-GCNs) have shown great performance in the context of skeleton-based action recognition. Nevertheless, ST-GCNs use raw skeleton data as vertex features. Such features have low dimensionality and might not be optimal for action discrimination. Moreover, a single layer of temporal convolution is used to model short-term temporal dependencies but can be insufficient for capturing both long-term. In this paper, we extend the Spatio-Temporal Graph Convolutional Network for skeleton-based action recognition by introducing two novel modules, namely, the Graph Vertex Feature Encoder (GVFE) and the Dilated Hierarchical Temporal Convolutional Network (DH-TCN). On the one hand, the GVFE module learns appropriate vertex features for action recognition by encoding raw skeleton data into a new feature space. On the other hand, the DH-TCN module is capable of capturing both short-term and long-term temporal dependencies using a hierarchical dilated convolutional network. Experiments have been conducted on the challenging NTU RGB-D 60, NTU RGB-D 120 and Kinetics datasets. The obtained results show that our method competes with state-of-the-art approaches while using a smaller number of layers and parameters; thus reducing the required training time and memory.

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.

Efficient-Receptive Field Block with Group Spatial Attention Mechanism for Object Detection

Jiacheng Zhang, Zhicheng Zhao, Fei Su

Responsive image

Auto-TLDR; E-RFB: Efficient-Receptive Field Block for Deep Neural Network for Object Detection

Slides Poster Similar

Object detection has been paid rising attention in computer vision field. Convolutional Neural Networks (CNNs) extract high-level semantic features of images, which directly determine the performance of object detection. As a common solution, embedding integration modules into CNNs can enrich extracted features and thereby improve the performance. However, the instability and inconsistency of internal multiple branches exist in these modules. To address this problem, we propose a novel multibranch module called Efficient-Receptive Field Block (E-RFB), in which multiple levels of features are combined for network optimization. Specifically, by downsampling and increasing depth, the E-RFB provides sufficient RF. Second, in order to eliminate the inconsistency across different branches, a novel spatial attention mechanism, namely, Group Spatial Attention Module (GSAM) is proposed. The GSAM gradually narrows a feature map by channel grouping; thus it encodes the information between spatial and channel dimensions into the final attention heat map. Third, the proposed module can be easily joined in various CNNs to enhance feature representation as a plug-and-play component. With SSD-style detectors, our method halves the parameters of the original detection head and achieves high accuracy on the PASCAL VOC and MS COCO datasets. Moreover, the proposed method achieves superior performance compared with state-of-the-art methods based on similar framework.

Temporal Binary Representation for Event-Based Action Recognition

Simone Undri Innocenti, Federico Becattini, Federico Pernici, Alberto Del Bimbo

Responsive image

Auto-TLDR; Temporal Binary Representation for Gesture Recognition

Slides Poster Similar

In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision algorithms. The proposed method first generates sequences of intermediate binary representations, which are then losslessly transformed into a compact format by simply applying a binary-to-decimal conversion. This strategy allows us to encode temporal information directly into pixel values, which are then interpreted by deep learning models. We apply our strategy, called Temporal Binary Representation, to the task of Gesture Recognition, obtaining state of the art results on the popular DVS128 Gesture Dataset. To underline the effectiveness of the proposed method compared to existing ones, we also collect an extension of the dataset under more challenging conditions on which to perform experiments.

SAT-Net: Self-Attention and Temporal Fusion for Facial Action Unit Detection

Zhihua Li, Zheng Zhang, Lijun Yin

Responsive image

Auto-TLDR; Temporal Fusion and Self-Attention Network for Facial Action Unit Detection

Slides Poster Similar

Research on facial action unit detection has shown remarkable performances by using deep spatial learning models in recent years, however, it is far from reaching its full capacity in learning due to the lack of use of temporal information of AUs across time. Since the AU occurrence in one frame is highly likely related to previous frames in a temporal sequence, exploring temporal correlation of AUs across frames becomes a key motivation of this work. In this paper, we propose a novel temporal fusion and AU-supervised self-attention network (a so-called SAT-Net) to address the AU detection problem. First of all, we input the deep features of a sequence into a convolutional LSTM network and fuse the previous temporal information into the feature map of the last frame, and continue to learn the AU occurrence. Second, considering the AU detection problem is a multi-label classification problem that individual label depends only on certain facial areas, we propose a new self-learned attention mask by focusing the detection of each AU on parts of facial areas through the learning of individual attention mask for each AU, thus increasing the AU independence without the loss of any spatial relations. Our extensive experiments show that the proposed framework achieves better results of AU detection over the state-of-the-arts on two benchmark databases (BP4D and DISFA).

A Duplex Spatiotemporal Filtering Network for Video-Based Person Re-Identification

Chong Zheng, Ping Wei, Nanning Zheng

Responsive image

Auto-TLDR; Duplex Spatiotemporal Filtering Network for Person Re-identification in Videos

Slides Poster Similar

Video-based person re-identification plays important roles in surveillance video analysis. This paper proposes a novel Duplex Spatiotemporal Filtering Network (DSFN) to re-identify persons in videos. A video sequence is represented as a duplex spatiotemporal matrix. DSFN model containing a group of filters performs filtering at feature level in both temporal and spatial dimensions, by which the model focuses on feature-level semantic information rather than image-level information as in the traditional filters. We propose sparse-orthogonal constraints to enforce the model to extract more discriminative features. DSFN characterizes not only the appearance features but also dynamic information such as gaits embedded in video sequences and obtains a better performance as a result. Experiments show that the proposed method outperforms state-of-the-art approaches.

Feature Pyramid Hierarchies for Multi-Scale Temporal Action Detection

Jiayu He, Guohui Li, Jun Lei

Responsive image

Auto-TLDR; Temporal Action Detection using Pyramid Hierarchies and Multi-scale Feature Maps

Slides Poster Similar

Temporal action detection is a challenging but promising task in video content analysis. It is in great demand in the field of public safety. The main difficulty of the task is precisely localizing activities in the video especially those short duration activities. And most of the existing methods can not achieve a satisfactory detection result. Our method addresses a key point to improve detection accuracy, which is to use multi-scale feature maps for regression and classification. In this paper, we introduce a novel network based on classification following proposal framework. In our network, a 3D feature pyramid hierarchies is built to enhance the ability of detecting short duration activities. The input RGB/Flow frames are first encoded by a 3D feature pyramid hierarchies, and this subnet produces multi-level feature maps. Then temporal proposal subnet uses these features to pick out proposals which might contain activity segments. Finally a pyramid region of interest (RoI) pooling pipeline and two fully connected layers reuse muti-level feature maps to refine the temporal boundaries of proposals and classify them. We use late feature fusion scheme to combine RGB and Flow information. The network is trained end-to-end and we evaluate it in THUMOS'14 dataset. Our network achieves a good result among typical methods. A further ablation test demonstrate that pyramid hierarchies is effective to improve detecting short duration activity segments.

Feature-Supervised Action Modality Transfer

Fida Mohammad Thoker, Cees Snoek

Responsive image

Auto-TLDR; Cross-Modal Action Recognition and Detection in Non-RGB Video Modalities by Learning from Large-Scale Labeled RGB Data

Slides Poster Similar

This paper strives for action recognition and detection in video modalities like RGB, depth maps or 3D-skeleton sequences when only limited modality-specific labeled examples are available. For the RGB, and derived optical-flow, modality many large-scale labeled datasets have been made available. They have become the de facto pre-training choice when recognizing or detecting new actions from RGB datasets that have limited amounts of labeled examples available. Unfortunately, large-scale labeled action datasets for other modalities are unavailable for pre-training. In this paper, our goal is to recognize actions from limited examples in non-RGB video modalities, by learning from large-scale labeled RGB data. To this end, we propose a two-step training process: (i) we extract action representation knowledge from an RGB-trained teacher network and adapt it to a non-RGB student network. (ii) we then fine-tune the transfer model with available labeled examples of the target modality. For the knowledge transfer we introduce feature-supervision strategies, which rely on unlabeled pairs of two modalities (the RGB and the target modality) to transfer feature level representations from the teacher to the the student network. Ablations and generalizations with two RGB source datasets and two non-RGB target datasets demonstrate that an optical-flow teacher provides better action transfer features than RGB for both depth maps and 3D-skeletons, even when evaluated on a different target domain, or for a different task. Compared to alternative cross-modal action transfer methods we show a good improvement in performance especially when labeled non-RGB examples to learn from are scarce.

PHNet: Parasite-Host Network for Video Crowd Counting

Shiqiao Meng, Jiajie Li, Weiwei Guo, Jinfeng Jiang, Lai Ye

Responsive image

Auto-TLDR; PHNet: A Parasite-Host Network for Video Crowd Counting

Slides Poster Similar

Crowd counting plays an increasingly important role in public security. Recently, many crowd counting methods for a single image have been proposed but few studies have focused on using temporal information from image sequences of videos to improve prediction performance. In the existing methods using videos for crowd estimation, temporal features and spatial features are modeled jointly for the prediction, which makes the model less efficient in extracting spatiotemporal features and difficult to improve the performance of predictions. In order to solve these problems, this paper proposes a Parasite-Host Network(PHNet) which is composed of Parasite branch and Host branch to extract temporal features and spatial features respectively. To specifically extract the transform features in the time domain, we propose a novel architecture termed as “Relational Extractor”(RE) which models the multiplicative interaction features of adjacent frames. In addition, the Host branch extracts the spatial features from a current frame which can be replaced with any model that uses a single image for the prediction. We conducted experiments by using our PHNet on four video crowd counting benchmarks: Venice,UCSD,FDST and CrowdFlow. Experimental results show that PHnet achieves superior performance on these four datasets to the state-of-the-art methods.

A Multi-Task Neural Network for Action Recognition with 3D Key-Points

Rongxiao Tang, Wang Luyang, Zhenhua Guo

Responsive image

Auto-TLDR; Multi-task Neural Network for Action Recognition and 3D Human Pose Estimation

Slides Poster Similar

Action recognition and 3D human pose estimation are the fundamental problems in computer vision and closely related. In this work, we propose a multi-task neural network for action recognition and 3D human pose estimation. The results of the previous methods are still error-prone especially when tested against the images taken in-the-wild, leading error results in action recognition. To solve this problem, we propose a principled approach to generate high quality 3D pose ground truth given any in-the-wild image with a person inside. We achieve this by first devising a novel stereo inspired neural network to directly map any 2D pose to high quality 3D counterpart. Based on the high-quality 3D labels, we carefully design the multi-task framework for action recognition and 3D human pose estimation. The proposed architecture can utilize the shallow, deep features of the images, and the in-the-wild 3D human key-points to guide a more precise result. High quality 3D key-points can fully reflect the morphological features of motions, thus boosting the performance on action recognition. Experiments demonstrate that 3D pose estimation leads to significantly higher performance on action recognition than separated learning. We also evaluate the generalization ability of our method both quantitatively and qualitatively. The proposed architecture performs favorably against the baseline 3D pose estimation methods. In addition, the reported results on Penn Action and NTU datasets demonstrate the effectiveness of our method on the action recognition task.

Video Representation Fusion Network For Multi-Label Movie Genre Classification

Tianyu Bi, Dmitri Jarnikov, Johan Lukkien

Responsive image

Auto-TLDR; A Video Representation Fusion Network for Movie Genre Classification

Slides Poster Similar

In this paper, we introduce a Video Representation Fusion Network (VRFN) for movie genre classification. Different from the previous works, which use frame-level features for movie genre classification, our approach uses video classification architecture to create video-level features from a group of frames and fuse these features temporally to learn long-term spatiotemporal information for the movie genre classification task. We use a pre-trained I3D model to generate intermediate video representations and connect it with a C3D-LSTM model for feature fusion and movie genre classification. LMTD-9 dataset which contains 4007 trailers multi-labeled with 9 movie genres is used for training and evaluation of the model. The experimental results demonstrate that learning long-term temporal dependencies by fusing video representations improves the performance in movie genre classification. Our best model outperforms the state-of-the-art methods by 3.4% improvement in AUPRC (macro).

An Improved Bilinear Pooling Method for Image-Based Action Recognition

Wei Wu, Jiale Yu

Responsive image

Auto-TLDR; An improved bilinear pooling method for image-based action recognition

Slides Poster Similar

Action recognition in still images is a challenging task because of the complexity of human motions and the variance of background in the same action category. And some actions typically occur in fine-grained categories, with little visual differences between these categories. So extracting discriminative features or modeling various semantic parts is essential for image-based action recognition. Many methods apply expensive manual annotations to learn discriminative parts information for action recognition, which may severely discourage potential applications in real life. In recent years, bilinear pooling method has shown its effectiveness for image classification due to its learning distinctive features automatically. Inspired by this model, in this paper, an improved bilinear pooling method is proposed for avoiding the shortcomings of traditional bilinear pooling methods. The previous bilinear pooling approaches contain lots of noisy background or harmful feature information, which limit their application for action recognition. In our method, the attention mechanism is introduced into hierarchical bilinear pooling framework with mask aggregation for action recognition. The proposed model can generate the distinctive and ROI-aware feature information by combining multiple attention mask maps from the channel and spatial-wise attention features. To be more specific, our method makes the network to better pay attention to discriminative region of the vital objects in an image. We verify our model on the two challenging datasets: 1) Stanford 40 action dataset and 2) our action dataset that includes 60 categories. Experimental results demonstrate the effectiveness of our approach, which is superior to the traditional and state-of-the-art methods.

Learning Group Activities from Skeletons without Individual Action Labels

Fabio Zappardino, Tiberio Uricchio, Lorenzo Seidenari, Alberto Del Bimbo

Responsive image

Auto-TLDR; Lean Pose Only for Group Activity Recognition

Similar

To understand human behavior we must not just recognize individual actions but model possibly complex group activity and interactions. Hierarchical models obtain the best results in group activity recognition but require fine grained individual action annotations at the actor level. In this paper we show that using only skeletal data we can train a state-of-the art end-to-end system using only group activity labels at the sequence level. Our experiments show that models trained without individual action supervision perform poorly. On the other hand we show that pseudo-labels can be computed from any pre-trained feature extractor with comparable final performance. Finally our carefully designed lean pose only architecture shows highly competitive results versus more complex multimodal approaches even in the self-supervised variant.

TSMSAN: A Three-Stream Multi-Scale Attentive Network for Video Saliency Detection

Jingwen Yang, Guanwen Zhang, Wei Zhou

Responsive image

Auto-TLDR; Three-stream Multi-scale attentive network for video saliency detection in dynamic scenes

Slides Poster Similar

Video saliency detection is an important low-level task that has been used in a large range of high-level applications. In this paper, we proposed a three-stream multi-scale attentive network (TSMSAN) for saliency detection in dynamic scenes. TSMSAN integrates motion vector representation, static saliency map, and RGB information in multi-scales together into one framework on the basis of Fully Convolutional Network (FCN) and spatial attention mechanism. On the one hand, the respective motion features, spatial features, as well as the scene features can provide abundant information for video saliency detection. On the other hand, spatial attention mechanism can combine features with multi-scales to focus on key information in dynamic scenes. In this manner, the proposed TSMSAN can encode the spatiotemporal features of the dynamic scene comprehensively. We evaluate the proposed approach on two public dynamic saliency data sets. The experimental results demonstrate TSMSAN is able to achieve the state-of-the-art performance as well as the excellent generalization ability. Furthermore, the proposed TSMSAN can provide more convincing video saliency information, in line with human perception.

Attention-Based Deep Metric Learning for Near-Duplicate Video Retrieval

Kuan-Hsun Wang, Chia Chun Cheng, Yi-Ling Chen, Yale Song, Shang-Hong Lai

Responsive image

Auto-TLDR; Attention-based Deep Metric Learning for Near-duplicate Video Retrieval

Slides Similar

Near-duplicate video retrieval (NDVR) is an important and challenging problem due to the increasing amount of videos uploaded to the Internet. In this paper, we propose an attention-based deep metric learning method for NDVR. Our method is based on well-established principles: We leverage two-stream networks to combine RGB and optical flow features, and incorporate an attention module to effectively deal with distractor frames commonly observed in near duplicate videos. We further aggregate the features corresponding to multiple video segments to enhance the discriminative power. The whole system is trained using a deep metric learning objective with a Siamese architecture. Our experiments show that the attention module helps eliminate redundant and noisy frames, while focusing on visually relevant frames for solving NVDR. We evaluate our approach on recent large-scale NDVR datasets, CC_WEB_VIDEO, VCDB, FIVR and SVD. To demonstrate the generalization ability of our approach, we report results in both within- and cross-dataset settings, and show that the proposed method significantly outperforms state-of-the-art approaches.

Applying (3+2+1)D Residual Neural Network with Frame Selection for Hong Kong Sign Language Recognition

Zhenxing Zhou, King-Shan Lui, Vincent W.L. Tam, Edmund Y. Lam

Responsive image

Auto-TLDR; Hong Kong Sign Language Recognition with 3D Residual Neural Network and Resilience Model

Slides Poster Similar

As reported by Hong Kong Government in 2017, there are more than 1.5 million residents suffering from hearing impairment in Hong Kong. Most of them rely on Hong Kong Sign Language for daily communication while there are only 63 registered sign language interpreters in Hong Kong. To address this specific social issue and also facilitate the effective communication between the hearing impaired and other people, this paper introduces a word-level Hong Kong Sign Language(HKSL) dataset which currently includes 45 isolated words and at least 30 sign videos per word performed by different signers(more than 1500 videos in total now and still enlarging). Based on this dataset, this paper systemically compares the performances of various deep learning approaches, including (1) 2D histogram of oriented gradients(HOG) feature/pose estimation/feature extraction with long-short term memory(LSTM) layer; (2) 3D Residual Neural Network(ResNet) (3) (2+1)D Residual Neural Network, in HKSL recognition. Meanwhile, to further improve the accuracy of sign language recognition, this paper proposes a novel method called (3+2+1)D ResNet Model with Frame Selection which adopts blurriness detection with Laplacian kernel to construct highquality video clips and also combines both (2+1)D and 3D ResNet for recognizing the sign language. At the end, the experimental results show that the proposed method outperforms other deep learning approaches and attain an impressive accuracy of 94.6% in our dataset.

ACCLVOS: Atrous Convolution with Spatial-Temporal ConvLSTM for Video Object Segmentation

Muzhou Xu, Shan Zong, Chunping Liu, Shengrong Gong, Zhaohui Wang, Yu Xia

Responsive image

Auto-TLDR; Semi-supervised Video Object Segmentation using U-shape Convolution and ConvLSTM

Slides Poster Similar

Semi-supervised video object segmentation aims at segmenting the target of interest throughout a video sequence when only the annotated mask of the first frame is given. A feasible method for segmentation is to capture the spatial-temporal coherence between frames. However, it may suffer from mask drift when the spatial-temporal coherence is unreliable. To relieve this problem, we propose an encoder-decoder-recurrent model for semi-supervised video object segmentation. The model adopts a U-shape architecture that combines atrous convolution and ConvLSTM to establish the coherence in both the spatial and temporal domains. Furthermore, the weight ratio for each block is also reconstructed to make the model more suitable for the VOS task. We evaluate our method on two benchmarks, DAVIS-2017 and Youtube-VOS, where state-of-the-art segmentation accuracy with a real-time inference speed of 21.3 frames per second on a Tesla P100 is obtained.