ICPR2020 Paper Browser

Paper download is intended for registered attendees only, and is subjected to the IEEE Copyright Policy. Any other use is strongly forbidden.

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

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

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

Abstract Slides Poster

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.

Similar papers

Learning Object Deformation and Motion Adaption for Semi-Supervised Video Object Segmentation

Xiaoyang Zheng, Xin Tan, Jianming Guo, Lizhuang Ma

Auto-TLDR; Semi-supervised Video Object Segmentation with Mask-propagation-based Model

Abstract Slides Poster Similar

We propose a novel method to solve the task of semi-supervised video object segmentation in this paper, where the mask annotation is only given at the first frame of the video sequence. A mask-propagation-based model is applied to learn the past and current information for segmentation. Besides, due to the scarcity of training data, image/mask pairs that model object deformation and shape variance are generated for the training phase. In addition, we generate the key flips between two adjacent frames for motion adaptation. The method works in an end-to-end way, without any online fine-tuning on test videos. Extensive experiments demonstrate that our method achieves competitive performance against state-of-the-art algorithms on benchmark datasets, covering cases with single object or multiple objects. We also conduct extensive ablation experiments to analyze the effectiveness of our proposed method.

Siamese Dynamic Mask Estimation Network for Fast Video Object Segmentation

Dexiang Hong, Guorong Li, Kai Xu, Li Su, Qingming Huang

Auto-TLDR; Siamese Dynamic Mask Estimation for Video Object Segmentation

Abstract Slides Poster Similar

Video object segmentation(VOS) has been a fundamental topic in recent years, and many deep learning-based methods have achieved state-of-the-art performance on multiple benchmarks. However, most of these methods rely on pixel-level matching between the template and the searched frames on the whole image while the targets only occupy a small region. Calculating on the entire image brings lots of additional computation cost. Besides, the whole image may contain some distracting information resulting in many false-positive matching points. To address this issue, motivated by one-stage instance object segmentation methods, we propose an efficient siamese dynamic mask estimation network for fast video object segmentation. The VOS is decoupled into two tasks, i.e. mask feature learning and dynamic kernel prediction. The former is responsible for learning high-quality features to preserve structural geometric information, and the latter learns a dynamic kernel which is used to convolve with the mask feature to generate a mask output. We use Siamese neural network as a feature extractor and directly predict masks after correlation. In this way, we can avoid using pixel-level matching, making our framework more simple and efficient. Experiment results on DAVIS 2016 /2017 datasets show that our proposed methods can run at 35 frames per second on NVIDIA RTX TITAN while preserving competitive accuracy.

Revisiting Sequence-To-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory

Fatemeh Azimi, Benjamin Bischke, Sebastian Palacio, Federico Raue, Jörn Hees, Andreas Dengel

Auto-TLDR; Sequence-to-Sequence Learning for Video Object Segmentation

Abstract Slides Poster Similar

Video Object Segmentation (VOS) is an active research area of the visual domain. One of its fundamental sub-tasks is semi-supervised / one-shot learning: given only the segmentation mask for the first frame, the task is to provide pixel-accurate masks for the object over the rest of the sequence. Despite much progress in the last years, we noticed that many of the existing approaches lose objects in longer sequences, especially when the object is small or briefly occluded. In this work, we build upon a sequence-to-sequence approach that employs an encoder-decoder architecture together with a memory module for exploiting the sequential data. We further improve this approach by proposing a model that manipulates multi-scale spatio-temporal information using memory-equipped skip connections. Furthermore, we incorporate an auxiliary task based on distance classification which greatly enhances the quality of edges in segmentation masks. We compare our approach to the state of the art and show considerable improvement in the contour accuracy metric and the overall segmentation accuracy.

Video Semantic Segmentation Using Deep Multi-View Representation Learning

Akrem Sellami, Salvatore Tabbone

Auto-TLDR; Deep Multi-view Representation Learning for Video Object Segmentation

Abstract Slides Poster Similar

In this paper, we propose a deep learning model based on deep multi-view representation learning, to address the video object segmentation task. The proposed model emphasizes the importance of the inherent correlation between video frames and incorporates a multi-view representation learning based on deep canonically correlated autoencoders. The multi-view representation learning in our model provides an efficient mechanism for capturing inherent correlations by jointly extracting useful features and learning better representation into a joint feature space, i.e., shared representation. To increase the training data and the learning capacity, we train the proposed model with pairs of video frames, i.e., $F_{a}$ and $F_{b}$. During the segmentation phase, the deep canonically correlated autoencoders model encodes useful features by processing multiple reference frames together, which is used to detect the frequently reappearing. Our model enhances the state-of-the-art deep learning-based methods that mainly focus on learning discriminative foreground representations over appearance and motion. Experimental results over two large benchmarks demonstrate the ability of the proposed method to outperform competitive approaches and to reach good performances, in terms of semantic segmentation.

Residual Learning of Video Frame Interpolation Using Convolutional LSTM

Keito Suzuki, Masaaki Ikehara

Auto-TLDR; Video Frame Interpolation Using Residual Learning and Convolutional LSTMs

Abstract Slides Poster Similar

Video frame interpolation aims to generate interme- diate frames between the original frames. This produces videos with a higher frame r ate and creates smoother motion. Many video frame interpolation methods first estimate the motion vector between the input frames and then synthesizes the intermediate frame based on the motion. However, these methods rely on the accuracy of the motion estimation step and fail to accurately generate the interpolated frame when the estimated motion vectors are inaccurate. Therefore, to avoid the uncertainties caused by motion estimation, this paper proposes a method that directly generates the intermediate frame. Since two consecutive frames are relatively similar, our method takes the average of these two frames and utilizes residual learning to learn the difference between the average of these frames and the ground truth middle frame. In addition, our method uses Convolutional LSTMs and four input frames to better incorporate spatiotemporal information. This neural network can be easily trained end to end without difficult to obtain data such as optical flow. Our experimental results show that the proposed method can perform favorably against other state-of-the-art frame interpolation methods.

Object Segmentation Tracking from Generic Video Cues

Amirhossein Kardoost, Sabine Müller, Joachim Weickert, Margret Keuper

Auto-TLDR; A Light-Weight Variational Framework for Video Object Segmentation in Videos

Abstract Slides Poster Similar

We propose a light-weight variational framework for online tracking of object segmentations in videos based on optical flow and image boundaries. While high-end computer vision methods on this task rely on sequence specific training of dedicated CNN architectures, we show the potential of a variational model, based on generic video information from motion and color. Such cues are usually required for tasks such as robot navigation or grasp estimation. We leverage them directly for video object segmentation and thus provide accurate segmentations at potentially very low extra cost. Our simple method can provide competitive results compared to the costly CNN-based methods with parameter tuning. Furthermore, we show that our approach can be combined with state-of-the-art CNN-based segmentations in order to improve over their respective results. We evaluate our method on the datasets DAVIS 16,17 and SegTrack v2.

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

Jingwen Yang, Guanwen Zhang, Wei Zhou

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

Abstract 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.

Human Segmentation with Dynamic LiDAR Data

Tao Zhong, Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi

Auto-TLDR; Spatiotemporal Neural Network for Human Segmentation with Dynamic Point Clouds

Abstract Slides Similar

Consecutive LiDAR scans and depth images compose dynamic 3D sequences, which contain more abundant spatiotemporal information than a single frame. Similar to the development history of image and video perception, dynamic 3D sequence perception starts to come into sight after inspiring research on static 3D data perception. This work proposes a spatiotemporal neural network for human segmentation with the dynamic LiDAR point clouds. It takes a sequence of depth images as input. It has a two-branch structure, i.e., the spatial segmentation branch and the temporal velocity estimation branch. The velocity estimation branch is designed to capture motion cues from the input sequence and then propagates them to the other branch. So that the segmentation branch segments humans according to both spatial and temporal features. These two branches are jointly learned on a generated dynamic point cloud data set for human recognition. Our works fill in the blank of dynamic point cloud perception with the spherical representation of point cloud and achieves high accuracy. The experiments indicate that the introduction of temporal feature benefits the segmentation of dynamic point cloud perception.

Boundary-Aware Graph Convolution for Semantic Segmentation

Hanzhe Hu, Jinshi Cui, Jinshi Hongbin Zha

Auto-TLDR; Boundary-Aware Graph Convolution for Semantic Segmentation

Abstract Slides Poster Similar

Recent works have made great progress in semantic segmentation by exploiting contextual information in a local or global manner with dilated convolutions, pyramid pooling or self-attention mechanism. However, few works have focused on harvesting boundary information to improve the segmentation performance. In order to enhance the feature similarity within the object and keep discrimination from other objects, we propose a boundary-aware graph convolution (BGC) module to propagate features within the object. The graph reasoning is performed among pixels of the same object apart from the boundary pixels. Based on the proposed BGC module, we further introduce the Boundary-aware Graph Convolution Network(BGCNet), which consists of two main components including a basic segmentation network and the BGC module, forming a coarse-to-fine paradigm. Specifically, the BGC module takes the coarse segmentation feature map as node features and boundary prediction to guide graph construction. After graph convolution, the reasoned feature and the input feature are fused together to get the refined feature, producing the refined segmentation result. We conduct extensive experiments on three popular semantic segmentation benchmarks including Cityscapes, PASCAL VOC 2012 and COCO Stuff, and achieve state-of-the-art performance on all three benchmarks.

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

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

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

Abstract 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.

Early Wildfire Smoke Detection in Videos

Taanya Gupta, Hengyue Liu, Bir Bhanu

Auto-TLDR; Semi-supervised Spatio-Temporal Video Object Segmentation for Automatic Detection of Smoke in Videos during Forest Fire

Abstract Poster Similar

Recent advances in unmanned aerial vehicles and camera technology have proven useful for the detection of smoke that emerges above the trees during a forest fire. Automatic detection of smoke in videos is of great interest to Fire department. To date, in most parts of the world, the fire is not detected in its early stage and generally it turns catastrophic. This paper introduces a novel technique that integrates spatial and temporal features in a deep learning framework using semi-supervised spatio-temporal video object segmentation and dense optical flow. However, detecting this smoke in the presence of haze and without the labeled data is difficult. Considering the visibility of haze in the sky, a dark channel pre-processing method is used that reduces the amount of haze in video frames and consequently improves the detection results. Online training is performed on a video at the time of testing that reduces the need for ground-truth data. Tests using the publicly available video datasets show that the proposed algorithms outperform previous work and they are robust across different wildfire-threatened locations.

Video Object Detection Using Object's Motion Context and Spatio-Temporal Feature Aggregation

Jaekyum Kim, Junho Koh, Byeongwon Lee, Seungji Yang, Jun Won Choi

Auto-TLDR; Video Object Detection Using Spatio-Temporal Aggregated Features and Gated Attention Network

Abstract Slides Poster Similar

The deep learning technique has recently led to significant improvement in object-detection accuracy. Numerous object detection schemes have been designed to process each frame independently. However, in many applications, object detection is performed using video data, which consists of a sequence of two-dimensional (2D) image frames. Thus, the object detection accuracy can be improved by exploiting the temporal context of the video sequence. In this paper, we propose a novel video object detection method that exploits both the motion context of the object and spatio-temporal aggregated features in the video sequence to enhance the object detection performance. First, the motion of the object is captured by the correlation between the spatial feature maps of two adjacent frames. Then, the embedding vector, representing the motion context, is obtained by feeding the N correlation maps to long short term memory (LSTM). In addition to generating the motion context vector, the spatial feature maps for N adjacent frames are aggregated to boost the quality of the feature map. The gated attention network is employed to selectively combine only highly correlated feature maps based on their relevance. While most video object detectors are applied to two-stage detectors, our proposed method is applicable to one-stage detectors, which tend to be preferred for practical applications owing to reduced computational complexity. Our numerical evaluation conducted on the ImageNet VID dataset shows that our network offers significant performance gain over baseline algorithms, and it outperforms the existing state-of-the-art one-stage video object detection methods.

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

Ming Cheng, Kunjing Cai, Ming Li

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

Abstract 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.

Real-Time Semantic Segmentation Via Region and Pixel Context Network

Yajun Li, Yazhou Liu, Quansen Sun

Auto-TLDR; A Dual Context Network for Real-Time Semantic Segmentation

Abstract Slides Poster Similar

Real-time semantic segmentation is a challenging task as both segmentation accuracy and inference speed need to be considered at the same time. In this paper, we present a Dual Context Network (DCNet) to address this challenge. It contains two independent sub-networks: Region Context Network and Pixel Context Network. Region Context Network is main network with low-resolution input and feature re-weighting module to achieve sufficient receptive field. Meanwhile, Pixel Context Network with location attention module to capture the location dependencies of each pixel for assisting the main network to recover spatial detail. A contextual feature fusion is introduced to combine output features of these two sub-networks. The experiments show that DCNet can achieve high-quality segmentation while keeping a high speed. Specifically, for Cityscapes test dataset, we achieve 76.1% Mean IOU with the speed of 82 FPS on a single GTX 2080Ti GPU when using ResNet50 as backbone, and 71.2% Mean IOU with the speed of 142 FPS when using ResNet18 as backbone.

Flow-Guided Spatial Attention Tracking for Egocentric Activity Recognition

Tianshan Liu, Kin-Man Lam

Auto-TLDR; flow-guided spatial attention tracking for egocentric activity recognition

Abstract Slides Poster Similar

The popularity of wearable cameras has opened up a new dimension for egocentric activity recognition. While some methods introduce attention mechanisms into deep learning networks to capture fine-grained hand-object interactions, they often neglect exploring the spatio-temporal relationships. Generating spatial attention, without adequately exploiting temporal consistency, will result in potentially sub-optimal performance in the video-based task. In this paper, we propose a flow-guided spatial attention tracking (F-SAT) module, which is based on enhancing motion patterns and inter-frame information, to highlight the discriminative features from regions of interest across a video sequence. A new form of input, namely the optical-flow volume, is presented to provide informative cues from moving parts for spatial attention tracking. The proposed F-SAT module is deployed to a two-branch-based deep architecture, which fuses complementary information for egocentric activity recognition. Experimental results on three egocentric activity benchmarks show that the proposed method achieves state-of-the-art performance.

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

Zhihua Li, Zheng Zhang, Lijun Yin

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

Abstract 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).

PSDNet: A Balanced Architecture of Accuracy and Parameters for Semantic Segmentation

Yue Liu, Zhichao Lian

Auto-TLDR; Pyramid Pooling Module with SE1Cblock and D2SUpsample Network (PSDNet)

Abstract Slides Poster Similar

Abstract—In this paper, we present our Pyramid Pooling Module （PPM） with SE1Cblock and D2SUpsample Network (PSDNet), a novel architecture for accurate semantic segmentation. Started from the known work called Pyramid Scene Parsing Network (PSPNet), PSDNet takes advantage of pyramid pooling structure with channel attention module and feature transform module in Pyramid Pooling Module (PPM). The enhanced PPM with these two components can strengthen context information flowing in the network instead of damaging it. The channel attention module we mentioned is an improved “Squeeze and Excitation with 1D Convolution” (SE1C) block which can explicitly model interrelationship between channels with fewer number of parameters. We propose a feature transform module named “Depth to Space Upsampling” (D2SUpsample) in the PPM which keeps integrity of features by transforming features while interpolating features, at the same time reducing parameters. In addition, we introduce a joint strategy in SE1Cblock which combines two variants of global pooling without increasing parameters. Compared with PSPNet, our work achieves higher accuracy on public datasets with 73.97% mIoU and 82.89% mAcc accuracy on Cityscapes Dataset based on ResNet50 backbone.

Tracking Fast Moving Objects by Segmentation Network

Ales Zita, Filip Sroubek

Auto-TLDR; Fast Moving Objects Tracking by Segmentation Using Deep Learning

Abstract Slides Poster Similar

Tracking Fast Moving Objects (FMO), which appear as blurred streaks in video sequences, is a difficult task for standard trackers, as the object position does not overlap in consecutive video frames and texture information of the objects is blurred. Up-to-date approaches tuned for this task are based on background subtraction with a static background and slow deblurring algorithms. In this article, we present a tracking-by-segmentation approach implemented using modern deep learning methods that perform near real-time tracking on real-world video sequences. We have developed a physically plausible FMO sequence generator to be a robust foundation for our training pipeline and demonstrate straightforward network adaptation for different FMO scenarios with varying foreground.

PHNet: Parasite-Host Network for Video Crowd Counting

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

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

Abstract 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.

Enhanced Feature Pyramid Network for Semantic Segmentation

Mucong Ye, Ouyang Jinpeng, Ge Chen, Jing Zhang, Xiaogang Yu

Auto-TLDR; EFPN: Enhanced Feature Pyramid Network for Semantic Segmentation

Abstract Slides Poster Similar

Multi-scale feature fusion has been an effective way for improving the performance of semantic segmentation. However, current methods generally fail to consider the semantic gaps between the shallow (low-level) and deep (high-level) features and thus the fusion methods may not be optimal. In this paper, to address the issues of the semantic gap between the feature from different layers, we propose a unified framework based on the U-shape encoder-decoder architecture, named Enhanced Feature Pyramid Network (EFPN). Specifically, the semantic enhancement module (SEM), boundary extraction module (BEM), and context aggregation model (CAM) are incorporated into the decoder network to improve the robustness of the multi-level features aggregation. In addition, a global fusion model (GFM) in encoder branch is proposed to capture more semantic information in the deep layers and effectively transmit the high-level semantic features to each layer. Extensive experiments are conducted and the results show that the proposed framework achieves the state-of-the-art results on three public datasets, namely PASCAL VOC 2012, Cityscapes, and PASCAL Context. Furthermore, we also demonstrate that the proposed method is effective for other visual tasks that require frequent fusing features and upsampling.

Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting

Pongpisit Thanasutives, Ken-Ichi Fukui, Masayuki Numao, Boonserm Kijsirikul

Auto-TLDR; M-SFANet and M-SegNet for Crowd Counting Using Multi-Scale Fusion Networks

Abstract Slides Poster Similar

In this paper, we proposed two modified neural networks based on dual path multi-scale fusion networks (SFANet) and SegNet for accurate and efficient crowd counting. Inspired by SFANet, the first model, which is named M-SFANet, is attached with atrous spatial pyramid pooling (ASPP) and context-aware module (CAN). The encoder of M-SFANet is enhanced with ASPP containing parallel atrous convolutional layers with different sampling rates and hence able to extract multi-scale features of the target object and incorporate larger context. To further deal with scale variation throughout an input image, we leverage the CAN module which adaptively encodes the scales of the contextual information. The combination yields an effective model for counting in both dense and sparse crowd scenes. Based on the SFANet decoder structure, M-SFANet's decoder has dual paths, for density map and attention map generation. The second model is called M-SegNet, which is produced by replacing the bilinear upsampling in SFANet with max unpooling that is used in SegNet. This change provides a faster model while providing competitive counting performance. Designed for high-speed surveillance applications, M-SegNet has no additional multi-scale-aware module in order to not increase the complexity. Both models are encoder-decoder based architectures and are end-to-end trainable. We conduct extensive experiments on five crowd counting datasets and one vehicle counting dataset to show that these modifications yield algorithms that could improve state-of-the-art crowd counting methods.

MFI: Multi-Range Feature Interchange for Video Action Recognition

Sikai Bai, Qi Wang, Xuelong Li

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

Abstract 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.

Motion U-Net: Multi-Cue Encoder-Decoder Network for Motion Segmentation

Gani Rahmon, Filiz Bunyak, Kannappan Palaniappan

Auto-TLDR; Motion U-Net: A Deep Learning Framework for Robust Moving Object Detection under Challenging Conditions

Abstract Slides Poster Similar

Detection of moving objects is a critical first step in many computer vision applications. Several algorithms for motion and change detection were proposed. However, many of these approaches lack the ability to handle challenging real-world scenarios. Recently, deep learning approaches started to produce impressive solutions to computer vision tasks, particularly for detection and segmentation. Many existing deep learning networks proposed for moving object detection rely only on spatial appearance cues. In this paper, we propose a novel multi-cue and multi-stream network, Motion U-Net (MU-Net), which integrates motion, change, and appearance cues using a deep learning framework for robust moving object detection under challenging conditions. The proposed network consists of a two-stream encoder module followed by feature concatenation and a decoder module. Motion and change cues are computed through our tensor-based motion estimation and a multi-modal background subtraction modules. The proposed system was tested and evaluated on the change detection challenge datasets (CDnet-2014) and compared to state-of-the-art methods. On CDnet-2014 dataset, our approach reaches an average overall F-measure of 0.9852 and outperforms all current state-of-the-art methods. The network was also tested on the unseen SBI-2015 dataset and produced promising results.

Coarse-To-Fine Foreground Segmentation Based on Co-Occurrence Pixel-Block and Spatio-Temporal Attention Model

Xinyu Liu, Dong Liang

Auto-TLDR; Foreground Segmentation from coarse to Fine Using Co-occurrence Pixel-Block Model for Dynamic Scene

Abstract Slides Poster Similar

Foreground segmentation in dynamic scene is an important task in video surveillance. The unsupervised background subtraction method based on background statistics modeling has difficulties in updating. On the other hand, the supervised foreground segmentation method based on deep learning relies on the large-scale of accurately annotated training data, which limits its cross-scene performance. In this paper, we propose a foreground segmentation method from coarse to fine. First, a across-scenes trained Spatio-Temporal Attention Model (STAM) is used to achieve coarse segmentation, which does not require training on specific scene. Then the coarse segmentation is used as a reference to help Co-occurrence Pixel-Block Model (CPB) complete the fine segmentation, and at the same time help CPB to update its background model. This method is more flexible than those deep-learning-based methods which depends on the specific-scene training, and realizes the accurate online dynamic update of the background model. Experimental results on WallFlower and LIMU validate our method outperforms STAM, CPB and other methods of participating in comparison.

Triplet-Path Dilated Network for Detection and Segmentation of General Pathological Images

Jiaqi Luo, Zhicheng Zhao, Fei Su, Limei Guo

Auto-TLDR; Triplet-path Network for One-Stage Object Detection and Segmentation in Pathological Images

Abstract Slides Similar

Deep learning has been widely applied in the field of medical image processing. However, compared with flourishing visual tasks in natural images, the progress achieved in pathological images is not remarkable, and detection and segmentation, which are among basic tasks of computer vision, are regarded as two independent tasks. In this paper, we make full use of existing datasets and construct a triplet-path network using dilated convolutions to cooperatively accomplish one-stage object detection and nuclei segmentation for general pathological images. First, in order to meet the requirement of detection and segmentation, a novel structure called triplet feature generation (TFG) is designed to extract high-resolution and multiscale features, where features from different layers can be properly integrated. Second, considering that pathological datasets are usually small, a location-aware and partially truncated loss function is proposed to improve the classification accuracy of datasets with few images and widely varying targets. We compare the performance of both object detection and instance segmentation with state-of-the-art methods. Experimental results demonstrate the effectiveness and efficiency of the proposed network on two datasets collected from multiple organs.

Siamese Fully Convolutional Tracker with Motion Correction

Mathew Francis, Prithwijit Guha

Auto-TLDR; A Siamese Ensemble for Visual Tracking with Appearance and Motion Components

Abstract Slides Poster Similar

Visual tracking algorithms use cues like appearance, structure, motion etc. for locating an object in a video. We propose an ensemble tracker with appearance and motion components. A siamese tracker that learns object appearance from a static image and motion vectors computed between consecutive frames with a flow network forms the ensemble. Motion predicted object localization is used to correct the appearance component in the ensemble. Complementary nature of the components bring performance improvement as observed in experiments performed on VOT2018 and VOT2019 datasets.

Fast and Accurate Real-Time Semantic Segmentation with Dilated Asymmetric Convolutions

Leonel Rosas-Arias, Gibran Benitez-Garcia, Jose Portillo-Portillo, Gabriel Sanchez-Perez, Keiji Yanai

Auto-TLDR; FASSD-Net: Dilated Asymmetric Pyramidal Fusion for Real-Time Semantic Segmentation

Abstract Slides Poster Similar

Recent works have shown promising results applied to real-time semantic segmentation tasks. To maintain fast inference speed, most of the existing networks make use of light decoders, or they simply do not use them at all. This strategy helps to maintain a fast inference speed; however, their accuracy performance is significantly lower in comparison to non-real-time semantic segmentation networks. In this paper, we introduce two key modules aimed to design a high-performance decoder for real-time semantic segmentation for reducing the accuracy gap between real-time and non-real-time segmentation networks. Our first module, Dilated Asymmetric Pyramidal Fusion (DAPF), is designed to substantially increase the receptive field on the top of the last stage of the encoder, obtaining richer contextual features. Our second module, Multi-resolution Dilated Asymmetric (MDA) module, fuses and refines detail and contextual information from multi-scale feature maps coming from early and deeper stages of the network. Both modules exploit contextual information without excessively increasing the computational complexity by using asymmetric convolutions. Our proposed network entitled “FASSD-Net” reaches 78.8% of mIoU accuracy on the Cityscapes validation dataset at 41.1 FPS on full resolution images (1024x2048). Besides, with a light version of our network, we reach 74.1% of mIoU at 133.1 FPS (full resolution) on a single NVIDIA GTX 1080Ti card with no additional acceleration techniques. The source code and pre-trained models are available at https://github.com/GibranBenitez/FASSD-Net.

STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation

Pierre Godet, Alexandre Boulch, Aurélien Plyer, Guy Le Besnerais

Auto-TLDR; STaRFlow: A lightweight CNN-based algorithm for optical flow estimation

Abstract Slides Poster Similar

We present a new lightweight CNN-based algorithm for multi-frame optical flow estimation. Our solution introduces a double recurrence over spatial scale and time through repeated use of a generic "STaR" (SpatioTemporal Recurrent) cell. It includes (i) a temporal recurrence based on conveying learned features rather than optical flow estimates; (ii) an occlusion detection process which is coupled with optical flow estimation and therefore uses a very limited number of extra parameters. The resulting STaRFlow algorithm gives state-of-the-art performances on MPI Sintel and Kitti2015 and involves significantly less parameters than all other methods with comparable results.

Object Detection Model Based on Scene-Level Region Proposal Self-Attention

Yu Quan, Zhixin Li, Canlong Zhang, Huifang Ma

Auto-TLDR; Exploiting Semantic Informations for Object Detection

Abstract Slides Poster Similar

The improvement of object detection performance is mostly focused on the extraction of local information near the region of interest in the image, which results in detection performance in this area being unable to achieve the desired effect. First, a depth-wise separable convolution network(D_SCNet-127 R-CNN) is built on the backbone network. Considering the importance of scene and semantic informations for visual recognition, the feature map is sent into the branch of the semantic segmentation module, region proposal network module, and the region proposal self-attention module to build the network of scene-level and region proposal self-attention module. Second, a deep reinforcement learning was utilized to achieve accurate positioning of border regression, and the calculation speed of the whole model was improved through implementing a light-weight head network. This model can effectively solve the limitation of feature extraction in traditional object detection and obtain more comprehensive detailed features. The experimental verification on MSCOCO17, VOC12, and Cityscapes datasets shows that the proposed method has good validity and scalability.

VTT: Long-Term Visual Tracking with Transformers

Tianling Bian, Yang Hua, Tao Song, Zhengui Xue, Ruhui Ma, Neil Robertson, Haibing Guan

Auto-TLDR; Visual Tracking Transformer with transformers for long-term visual tracking

Abstract Slides Similar

Long-term visual tracking is a challenging problem. State-of-the-art long-term trackers, e.g., GlobalTrack, utilize region proposal networks (RPNs) to generate target proposals. However, the performance of the trackers is affected by occlusions and large scale or ratio variations. To address these issues, in this paper, we are the first to propose a novel architecture with transformers for long-term visual tracking. Specifically, the proposed Visual Tracking Transformer (VTT) utilizes a transformer encoder-decoder architecture for aggregating global information to deal with occlusion and large scale or ratio variation. Furthermore, it also shows better discriminative power against instance-level distractors without the need for extra labeling and hard-sample mining. We conduct extensive experiments on three largest long-term tracking dataset and have achieved state-of-the-art performance.

Temporal Feature Enhancement Network with External Memory for Object Detection in Surveillance Video

Masato Fujitake, Akihiro Sugimoto

Auto-TLDR; Temporal Attention Based External Memory Network for Surveillance Object Detection

Abstract Poster Similar

Video object detection is challenging and essential in practical applications, such as surveillance cameras for traffic control and public security. Unlike the video in natural scenes, the surveillance video tends to contain dense, and small objects (typically vehicles) in their appearances. Therefore, existing methods for surveillance object detection utilize still-image object detection approaches with rich feature extractors at the expense of their run-time speeds. The run-time speed, however, becomes essential when the video is being streamed. In this paper, we exploit temporal information in videos to enrich the feature maps, proposing the first temporal attention based external memory network for the live stream of video. Extensive experiments on real-world traffic surveillance benchmarks demonstrate the real-time performance of the proposed model while keeping comparable accuracy with state-of-the-art.

Not 3D Re-ID: Simple Single Stream 2D Convolution for Robust Video Re-Identification

Toby Breckon, Aishah Alsehaim

Auto-TLDR; ResNet50-IBN for Video-based Person Re-Identification using Single Stream 2D Convolution Network

Abstract Slides Poster Similar

Video-based person re-identification has received increasing attention recently, as it plays an important role within the surveillance video analysis. Video-based Re-ID is an expansion of earlier image-based re-identification methods by learning features from a video via multiple image frames for each person. Most contemporary video Re-ID methods utilise complex CNN-based network architectures using 3D convolution or multi-branch networks to extract spatial-temporal features from the video. By contrast, in this paper, we will illustrate superior performance from a simple single stream 2D convolution network leveraging the ResNet50-IBN architecture to extract frame-level features followed by temporal attention for clip level features. These clip level features can be generalised to extract video level features by averaging clip level features without any additional cost. Our model, uses best video Re-ID practice and transfer learning between datasets, outperforms existing state-of-the-art approaches on MARS, PRID2011 and iLIDSVID datasets with 89:62%, 97:75%, 97:33% rank-1 accuracy respectively and with 84:61% mAP for MARS, without reliance on complex and memory intensive 3D convolutions or multistream networks architectures as found in other contemporary work. Conversely, this work shows that global features extracted by the 2D convolution network are a sufficient representation for robust state of the art video Re-ID.

A Boundary-Aware Distillation Network for Compressed Video Semantic Segmentation

Hongchao Lu

Auto-TLDR; A Boundary-Aware Distillation Network for Video Semantic Segmentation

Abstract Slides Poster Similar

In recent years optical flow is often estimated to reuse features so as to accelerate video semantic segmentation. With addition of optical flow network, however, extra cost may incur and accuracy may thus be degraded because of repeated warping operation. In this paper, we propose a boundary-aware distillation network (BDNet) that replaces optical flow network with block motion vectors encoded in compressed video, resulting in negligible computational complexity. In order to make salient features, an auxiliary boundary-aware stream is added to the main stream to jointly estimate silhouette and segmentation of objects. To further correct warped features, a well-trained teacher network is employed to transfer knowledge to the main stream. Both boundary-aware stream and the teacher network are neglected during inference stage, so that video segmentation network enables to get faster without increasing any computational burden. By splitting the task into three components, our BDNet shows almost 10% time saving as well as 1.6% accuracy improvement over baseline on the Cityscapes dataset.

Multi-Scale Residual Pyramid Attention Network for Monocular Depth Estimation

Jing Liu, Xiaona Zhang, Zhaoxin Li, Tianlu Mao

Auto-TLDR; Multi-scale Residual Pyramid Attention Network for Monocular Depth Estimation

Abstract Slides Poster Similar

Monocular depth estimation is a challenging problem in computer vision and is crucial for understanding 3D scene geometry. Recently, deep convolutional neural networks (DCNNs) based methods have improved the estimation accuracy significantly. However, existing methods fail to consider complex textures and geometries in scenes, thereby resulting in loss of local details, distorted object boundaries, and blurry reconstruction. In this paper, we proposed an end-to-end Multi-scale Residual Pyramid Attention Network (MRPAN) to mitigate these problems.First,we propose a Multi-scale Attention Context Aggregation (MACA) module, which consists of Spatial Attention Module (SAM) and Global Attention Module (GAM). By considering the position and scale correlation of pixels from spatial and global perspectives, the proposed module can adaptively learn the similarity between pixels so as to obtain more global context information of the image and recover the complex structure in the scene. Then we proposed an improved Residual Refinement Module (RRM) to further refine the scene structure, giving rise to deeper semantic information and retain more local details. Experimental results show that our method achieves more promisin performance in object boundaries and local details compared with other state-of-the-art methods.

Context Visual Information-Based Deliberation Network for Video Captioning

Min Lu, Xueyong Li, Caihua Liu

Auto-TLDR; Context visual information-based deliberation network for video captioning

Abstract Slides Poster Similar

Video captioning is to automatically and accurately generate a textual description for a video. The typical methods following the encoder-decoder architecture directly utilized hidden states to predict words. Nevertheless, these methods did not amend the inaccurate hidden states before feeding those states into word prediction. This led to a cascade of errors on generating word by word. In this paper, the context visual information-based deliberation network is proposed, abbreviated as CVI-DelNet. Its key idea is to introduce the deliberator into the encoder-decoder framework. The encoder-decoder firstly generates a raw hidden state sequence. Unlike the existing methods, the raw hidden state is no more directly used for word prediction but is fed into the deliberator to generate the refined hidden state. The words are then predicted according to the refined hidden states and the contextual visual features. Results on two datasets shows that the proposed method significantly outperforms the baselines.

Multiscale Attention-Based Prototypical Network for Few-Shot Semantic Segmentation

Yifei Zhang, Desire Sidibe, Olivier Morel, Fabrice Meriaudeau

Auto-TLDR; Few-shot Semantic Segmentation with Multiscale Feature Attention

Abstract Slides Similar

Deep learning-based image understanding techniques require a large number of labeled images for training. Few-shot semantic segmentation, on the contrary, aims at generalizing the segmentation ability of the model to new categories given only a few labeled samples. To tackle this problem, we propose a novel prototypical network (MAPnet) with multiscale feature attention. To fully exploit the representative features of target classes, we firstly extract rich contextual information of labeled support images via a multiscale feature enhancement module. The learned prototypes from support features provide further semantic guidance on the query image. Then we adaptively integrate multiple similarity-guided probability maps by attention mechanism, yielding an optimal pixel-wise prediction. Furthermore, the proposed method was validated on the PASCAL-5i dataset in terms of 1-way N-shot evaluation. We also test the model with weak annotations, including scribble and bounding box annotations. Both the qualitative and quantitative results demonstrate the advantages of our approach over other state-of-the-art methods.

DE-Net: Dilated Encoder Network for Automated Tongue Segmentation

Hui Tang, Bin Wang, Jun Zhou, Yongsheng Gao

Auto-TLDR; Automated Tongue Image Segmentation using De-Net

Abstract Slides Poster Similar

Automated tongue recognition is a growing research field due to global demand for personal health care. Using mobile devices to take tongue pictures is convenient and of low cost for tongue recognition. It is particularly suitable for self-health evaluation of the public. However, images taken by mobile devices are easily affected by various imaging environment, which makes fine segmentation a more challenging task compared with those taken by specialized acquisition devices. Deep learning approaches are promising for tongue image segmentation because they have powerful feature learning and representation capability. However, the successive pooling operations in these methods lead to loss of information on image details, making them fail when segmenting low-quality images captured by mobile devices. To address this issue, we propose a dilated encoder network (DE-Net) to capture more high-level features and get high-resolution output for automated tongue image segmentation. In addition, we construct two tongue image datasets which contain images taken by specialized devices and mobile devices, respectively, to verify the effectiveness of the proposed method. Experimental results on both datasets demonstrate that the proposed method outperforms the state-of-the-art methods in tongue image segmentation.

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

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

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

Abstract 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.

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

Mirco Planamente, Andrea Bottino, Barbara Caputo

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

Abstract 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.

What and How? Jointly Forecasting Human Action and Pose

Yanjun Zhu, Yanxia Zhang, Qiong Liu, Andreas Girgensohn

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

Abstract 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.

Learning a Dynamic High-Resolution Network for Multi-Scale Pedestrian Detection

Mengyuan Ding, Shanshan Zhang, Jian Yang

Auto-TLDR; Learningable Dynamic HRNet for Pedestrian Detection

Abstract Slides Poster Similar

Pedestrian detection is a canonical instance of object detection in computer vision. In practice, scale variation is one of the key challenges, resulting in unbalanced performance across different scales. Recently, the High-Resolution Network (HRNet) has become popular because high-resolution feature representations are more friendly to small objects. However, when we apply HRNet for pedestrian detection, we observe that it improves for small pedestrians on one hand, but hurts the performance for larger ones on the other hand. To overcome this problem, we propose a learnable Dynamic HRNet (DHRNet) aiming to generate different network paths adaptive to different scales. Specifically, we construct a parallel multi-branch architecture and add a soft conditional gate module allowing for dynamic feature fusion. Both branches share all the same parameters except the soft gate module. Experimental results on CityPersons and Caltech benchmarks indicate that our proposed dynamic HRNet is more capable of dealing with pedestrians of various scales, and thus improves the performance across different scales consistently.

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

Théo Voillemin, Hazem Wannous, Jean-Philippe Vandeborre

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

Abstract 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.

SFPN: Semantic Feature Pyramid Network for Object Detection

Yi Gan, Wei Xu, Jianbo Su

Auto-TLDR; SFPN: Semantic Feature Pyramid Network to Address Information Dilution Issue in FPN

Abstract Slides Poster Similar

Feature Pyramid Network(FPN) employs a top-down path to enhance low level feature by utilizing high level feature.However, further improvement of detector is greatly hindered by the inner defect of FPN. The dilution issue in FPN is analyzed in this paper, and a new architecture named Semantic Feature Pyramid Network(SFPN) is introduced to address the information imbalance problem caused by information dilution. The proposed method consists of two simple and effective components: Semantic Pyramid Module(SPM) and Semantic Feature Fusion Module(SFFM). To compensate for the weaknesses of FPN, the semantic segmentation result is utilized as an extra information source in our architecture.By constructing a semantic pyramid based on the segmentation result and fusing it with FPN, feature maps at each level can obtain the necessary information without suffering from the dilution issue. The proposed architecture could be applied on many detectors, and non-negligible improvement could be achieved. Although this method is designed for object detection, other tasks such as instance segmentation can also largely benefit from it. The proposed method brings Faster R-CNN and Mask R-CNN with ResNet-50 as backbone both 1.8 AP improvements respectively. Furthermore, SFPN improves Cascade R-CNN with backbone ResNet-101 from 42.4 AP to 43.5 AP.

Dynamic Guided Network for Monocular Depth Estimation

Xiaoxia Xing, Yinghao Cai, Yiping Yang, Dayong Wen

Auto-TLDR; DGNet: Dynamic Guidance Upsampling for Self-attention-Decoding for Monocular Depth Estimation

Abstract Slides Poster Similar

Self-attention or encoder-decoder structure has been widely used in deep neural networks for monocular depth estimation tasks. The former mechanism are capable to capture long-range information by computing the representation of each position by a weighted sum of the features at all positions, while the latter networks can capture structural details information by gradually recovering the spatial information. In this work, we combine the advantages of both methods. Specifically, our proposed model, DGNet, extends EMANet Network by adding an effective decoder module to refine the depth results. In the decoder stage, we further design dynamic guidance upsampling which uses local neighboring information of low-level features guide coarser depth to upsample. In this way, dynamic guidance upsampling generates content-dependent and spatially-variant kernels for depth upsampling which makes full use of spatial details information from low-level features. Experimental results demonstrate that our method obtains higher accuracy and generates the desired depth map.

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

Chong Zheng, Ping Wei, Nanning Zheng

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

Abstract 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.

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

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

Abstract 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.

MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recognition

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

Auto-TLDR; Mixed Temporal Convolution for Action Recognition

Abstract Slides Poster Similar

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.

Enhancing Semantic Segmentation of Aerial Images with Inhibitory Neurons

Ihsan Ullah, Sean Reilly, Michael Madden

Auto-TLDR; Lateral Inhibition in Deep Neural Networks for Object Recognition and Semantic Segmentation

Abstract Slides Poster Similar

In a Convolutional Neural Network, each neuron in the output feature map takes input from the neurons in its receptive field. This receptive field concept plays a vital role in today's deep neural networks. However, inspired by neuro-biological research, it has been proposed to add inhibitory neurons outside the receptive field, which may enhance the performance of neural network models. In this paper, we begin with deep network architectures such as VGG and ResNet, and propose an approach to add lateral inhibition in each output neuron to reduce its impact on its neighbours, both in fine-tuning pre-trained models and training from scratch. Our experiments show that notable improvements upon prior baseline deep models can be achieved. A key feature of our approach is that it is easy to add to baseline models; it can be adopted in any model containing convolution layers, and we demonstrate its value in applications including object recognition and semantic segmentation of aerial images, where we show state-of-the-art result on the Aeroscape dataset. On semantic segmentation tasks, our enhancement shows 17.43% higher mIoU than a single baseline model on a single source (the Aeroscape dataset), 13.43% higher performance than an ensemble model on the same single source, and 7.03% higher than an ensemble model on multiple sources (segmentation datasets). Our experiments illustrate the potential impact of using inhibitory neurons in deep learning models, and they also show better results than the baseline models that have standard convolutional layer.