Pub Date : 2020-06-01DOI: 10.1109/CVPR42600.2020.01233
Scott Workman, Nathan Jacobs
Our goal is to use overhead imagery to understand patterns in traffic flow, for instance answering questions such as how fast could you traverse Times Square at 3am on a Sunday. A traditional approach for solving this problem would be to model the speed of each road segment as a function of time. However, this strategy is limited in that a significant amount of data must first be collected before a model can be used and it fails to generalize to new areas. Instead, we propose an automatic approach for generating dynamic maps of traffic speeds using convolutional neural networks. Our method operates on overhead imagery, is conditioned on location and time, and outputs a local motion model that captures likely directions of travel and corresponding travel speeds. To train our model, we take advantage of historical traffic data collected from New York City. Experimental results demonstrate that our method can be applied to generate accurate city-scale traffic models.
{"title":"Dynamic Traffic Modeling From Overhead Imagery","authors":"Scott Workman, Nathan Jacobs","doi":"10.1109/CVPR42600.2020.01233","DOIUrl":"https://doi.org/10.1109/CVPR42600.2020.01233","url":null,"abstract":"Our goal is to use overhead imagery to understand patterns in traffic flow, for instance answering questions such as how fast could you traverse Times Square at 3am on a Sunday. A traditional approach for solving this problem would be to model the speed of each road segment as a function of time. However, this strategy is limited in that a significant amount of data must first be collected before a model can be used and it fails to generalize to new areas. Instead, we propose an automatic approach for generating dynamic maps of traffic speeds using convolutional neural networks. Our method operates on overhead imagery, is conditioned on location and time, and outputs a local motion model that captures likely directions of travel and corresponding travel speeds. To train our model, we take advantage of historical traffic data collected from New York City. Experimental results demonstrate that our method can be applied to generate accurate city-scale traffic models.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"36 1","pages":"12312-12321"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91293776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/CVPR42600.2020.01084
Yunbo Wang, Jiajun Wu, Mingsheng Long, J. Tenenbaum
We study a new research problem of probabilistic future frames prediction from a sequence of noisy inputs, which is useful because it is difficult to guarantee the quality of input frames in practical spatiotemporal prediction applications. It is also challenging because it involves two levels of uncertainty: the perceptual uncertainty from noisy observations and the dynamics uncertainty in forward modeling. In this paper, we propose to tackle this problem with an end-to-end trainable model named Bayesian Predictive Network (BP-Net). Unlike previous work in stochastic video prediction that assumes spatiotemporal coherence and therefore fails to deal with perceptual uncertainty, BP-Net models both levels of uncertainty in an integrated framework. Furthermore, unlike previous work that can only provide unsorted estimations of future frames, BP-Net leverages a differentiable sequential importance sampling (SIS) approach to make future predictions based on the inference of underlying physical states, thereby providing sorted prediction candidates in accordance with the SIS importance weights, i.e., the confidences. Our experiment results demonstrate that BP-Net remarkably outperforms existing approaches on predicting future frames from noisy data.
{"title":"Probabilistic Video Prediction From Noisy Data With a Posterior Confidence","authors":"Yunbo Wang, Jiajun Wu, Mingsheng Long, J. Tenenbaum","doi":"10.1109/CVPR42600.2020.01084","DOIUrl":"https://doi.org/10.1109/CVPR42600.2020.01084","url":null,"abstract":"We study a new research problem of probabilistic future frames prediction from a sequence of noisy inputs, which is useful because it is difficult to guarantee the quality of input frames in practical spatiotemporal prediction applications. It is also challenging because it involves two levels of uncertainty: the perceptual uncertainty from noisy observations and the dynamics uncertainty in forward modeling. In this paper, we propose to tackle this problem with an end-to-end trainable model named Bayesian Predictive Network (BP-Net). Unlike previous work in stochastic video prediction that assumes spatiotemporal coherence and therefore fails to deal with perceptual uncertainty, BP-Net models both levels of uncertainty in an integrated framework. Furthermore, unlike previous work that can only provide unsorted estimations of future frames, BP-Net leverages a differentiable sequential importance sampling (SIS) approach to make future predictions based on the inference of underlying physical states, thereby providing sorted prediction candidates in accordance with the SIS importance weights, i.e., the confidences. Our experiment results demonstrate that BP-Net remarkably outperforms existing approaches on predicting future frames from noisy data.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"22 1","pages":"10827-10836"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87670384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/cvpr42600.2020.00309
Qian Zheng, Jinnan Chen, Zhangchi Lu, Boxin Shi, Xudong Jiang, Kim-Hui Yap, Ling-yu Duan, A. Kot
This paper aims to calibrate the orientation of glass and the field of view of the camera from a single reflection-contaminated image. We show how a reflective amplitude coefficient map can be used as a calibration cue. Different from existing methods, the proposed solution is free from image contents. To reduce the impact of a noisy calibration cue estimated from a reflection-contaminated image, we propose two strategies: an optimization-based method that imposes part of though reliable entries on the map and a learning-based method that fully exploits all entries. We collect a dataset containing 320 samples as well as their camera parameters for evaluation. We demonstrate that our method not only facilitates a general single image camera calibration method that leverages image contents but also contributes to improving the performance of single image reflection removal. Furthermore, we show our byproduct output helps alleviate the ill-posed problem of estimating the panorama from a single image.
{"title":"What Does Plate Glass Reveal About Camera Calibration?","authors":"Qian Zheng, Jinnan Chen, Zhangchi Lu, Boxin Shi, Xudong Jiang, Kim-Hui Yap, Ling-yu Duan, A. Kot","doi":"10.1109/cvpr42600.2020.00309","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.00309","url":null,"abstract":"This paper aims to calibrate the orientation of glass and the field of view of the camera from a single reflection-contaminated image. We show how a reflective amplitude coefficient map can be used as a calibration cue. Different from existing methods, the proposed solution is free from image contents. To reduce the impact of a noisy calibration cue estimated from a reflection-contaminated image, we propose two strategies: an optimization-based method that imposes part of though reliable entries on the map and a learning-based method that fully exploits all entries. We collect a dataset containing 320 samples as well as their camera parameters for evaluation. We demonstrate that our method not only facilitates a general single image camera calibration method that leverages image contents but also contributes to improving the performance of single image reflection removal. Furthermore, we show our byproduct output helps alleviate the ill-posed problem of estimating the panorama from a single image.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"254 1","pages":"3019-3029"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87033267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/CVPR42600.2020.00908
Yongri Piao, Zhengkun Rong, Miao Zhang, Weisong Ren, Huchuan Lu
Existing state-of-the-art RGB-D salient object detection methods explore RGB-D data relying on a two-stream architecture, in which an independent subnetwork is required to process depth data. This inevitably incurs extra computational costs and memory consumption, and using depth data during testing may hinder the practical applications of RGB-D saliency detection. To tackle these two dilemmas, we propose a depth distiller (A2dele) to explore the way of using network prediction and attention as two bridges to transfer the depth knowledge from the depth stream to the RGB stream. First, by adaptively minimizing the differences between predictions generated from the depth stream and RGB stream, we realize the desired control of pixel-wise depth knowledge transferred to the RGB stream. Second, to transfer the localization knowledge to RGB features, we encourage consistencies between the dilated prediction of the depth stream and the attention map from the RGB stream. As a result, we achieve a lightweight architecture without use of depth data at test time by embedding our A2dele. Our extensive experimental evaluation on five benchmarks demonstrate that our RGB stream achieves state-of-the-art performance, which tremendously minimizes the model size by 76% and runs 12 times faster, compared with the best performing method. Furthermore, our A2dele can be applied to existing RGB-D networks to significantly improve their efficiency while maintaining performance (boosts FPS by nearly twice for DMRA and 3 times for CPFP).
{"title":"A2dele: Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object Detection","authors":"Yongri Piao, Zhengkun Rong, Miao Zhang, Weisong Ren, Huchuan Lu","doi":"10.1109/CVPR42600.2020.00908","DOIUrl":"https://doi.org/10.1109/CVPR42600.2020.00908","url":null,"abstract":"Existing state-of-the-art RGB-D salient object detection methods explore RGB-D data relying on a two-stream architecture, in which an independent subnetwork is required to process depth data. This inevitably incurs extra computational costs and memory consumption, and using depth data during testing may hinder the practical applications of RGB-D saliency detection. To tackle these two dilemmas, we propose a depth distiller (A2dele) to explore the way of using network prediction and attention as two bridges to transfer the depth knowledge from the depth stream to the RGB stream. First, by adaptively minimizing the differences between predictions generated from the depth stream and RGB stream, we realize the desired control of pixel-wise depth knowledge transferred to the RGB stream. Second, to transfer the localization knowledge to RGB features, we encourage consistencies between the dilated prediction of the depth stream and the attention map from the RGB stream. As a result, we achieve a lightweight architecture without use of depth data at test time by embedding our A2dele. Our extensive experimental evaluation on five benchmarks demonstrate that our RGB stream achieves state-of-the-art performance, which tremendously minimizes the model size by 76% and runs 12 times faster, compared with the best performing method. Furthermore, our A2dele can be applied to existing RGB-D networks to significantly improve their efficiency while maintaining performance (boosts FPS by nearly twice for DMRA and 3 times for CPFP).","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"64 1","pages":"9057-9066"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90428016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/cvpr42600.2020.00247
Renjie Wan, Boxin Shi, Haoliang Li, Ling-yu Duan, A. Kot
For images taken through glass, existing methods focus on the restoration of the background scene by regarding the reflection components as noise. However, the scene reflected by glass surface also contains important information to be recovered, especially for the surveillance or criminal investigations. In this paper, instead of removing reflection components from the mixture image, we aim at recovering reflection scenes from the mixture image. We first propose a strategy to obtain such ground truth and its corresponding input images. Then, we propose a two-stage framework to obtain the visible reflection scene from the mixture image. Specifically, we train the network with a shift-invariant loss which is robust to misalignment between the input and output images. The experimental results show that our proposed method achieves promising results.
{"title":"Reflection Scene Separation From a Single Image","authors":"Renjie Wan, Boxin Shi, Haoliang Li, Ling-yu Duan, A. Kot","doi":"10.1109/cvpr42600.2020.00247","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.00247","url":null,"abstract":"For images taken through glass, existing methods focus on the restoration of the background scene by regarding the reflection components as noise. However, the scene reflected by glass surface also contains important information to be recovered, especially for the surveillance or criminal investigations. In this paper, instead of removing reflection components from the mixture image, we aim at recovering reflection scenes from the mixture image. We first propose a strategy to obtain such ground truth and its corresponding input images. Then, we propose a two-stage framework to obtain the visible reflection scene from the mixture image. Specifically, we train the network with a shift-invariant loss which is robust to misalignment between the input and output images. The experimental results show that our proposed method achieves promising results.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"30 1","pages":"2395-2403"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85549926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/CVPR42600.2020.00818
Ji-yang Yu, R. Ramamoorthi
We propose a novel neural network that infers the per-pixel warp fields for video stabilization from the optical flow fields of the input video. While previous learning based video stabilization methods attempt to implicitly learn frame motions from color videos, our method resorts to optical flow for motion analysis and directly learns the stabilization using the optical flow. We also propose a pipeline that uses optical flow principal components for motion inpainting and warp field smoothing, making our method robust to moving objects, occlusion and optical flow inaccuracy, which is challenging for other video stabilization methods. Our method achieves quantitatively and visually better results than the state-of-the-art optimization based and deep learning based video stabilization methods. Our method also gives a ~3x speed improvement compared to the optimization based methods.
{"title":"Learning Video Stabilization Using Optical Flow","authors":"Ji-yang Yu, R. Ramamoorthi","doi":"10.1109/CVPR42600.2020.00818","DOIUrl":"https://doi.org/10.1109/CVPR42600.2020.00818","url":null,"abstract":"We propose a novel neural network that infers the per-pixel warp fields for video stabilization from the optical flow fields of the input video. While previous learning based video stabilization methods attempt to implicitly learn frame motions from color videos, our method resorts to optical flow for motion analysis and directly learns the stabilization using the optical flow. We also propose a pipeline that uses optical flow principal components for motion inpainting and warp field smoothing, making our method robust to moving objects, occlusion and optical flow inaccuracy, which is challenging for other video stabilization methods. Our method achieves quantitatively and visually better results than the state-of-the-art optimization based and deep learning based video stabilization methods. Our method also gives a ~3x speed improvement compared to the optimization based methods.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"8156-8164"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88774007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/cvpr42600.2020.00166
Keyang Luo, T. Guan, L. Ju, Yuesong Wang, Zhu Chen, Yawei Luo
Multi-view stereo is a crucial task in computer vision, that requires accurate and robust photo-consistency among input images for depth estimation. Recent studies have shown that learning-based feature matching and confidence regularization can play a vital role in this task. Nevertheless, how to design good matching confidence volumes as well as effective regularizers for them are still under in-depth study. In this paper, we propose an attention-aware deep neural network “AttMVS” for learning multi-view stereo. In particular, we propose a novel attention-enhanced matching confidence volume, that combines the raw pixel-wise matching confidence from the extracted perceptual features with the contextual information of local scenes, to improve the matching robustness. Furthermore, we develop an attention-guided regularization module, which consists of multilevel ray fusion modules, to hierarchically aggregate and regularize the matching confidence volume into a latent depth probability volume.Experimental results show that our approach achieves the best overall performance on the DTU dataset and the intermediate sequences of Tanks & Temples benchmark over many state-of-the-art MVS algorithms.
{"title":"Attention-Aware Multi-View Stereo","authors":"Keyang Luo, T. Guan, L. Ju, Yuesong Wang, Zhu Chen, Yawei Luo","doi":"10.1109/cvpr42600.2020.00166","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.00166","url":null,"abstract":"Multi-view stereo is a crucial task in computer vision, that requires accurate and robust photo-consistency among input images for depth estimation. Recent studies have shown that learning-based feature matching and confidence regularization can play a vital role in this task. Nevertheless, how to design good matching confidence volumes as well as effective regularizers for them are still under in-depth study. In this paper, we propose an attention-aware deep neural network “AttMVS” for learning multi-view stereo. In particular, we propose a novel attention-enhanced matching confidence volume, that combines the raw pixel-wise matching confidence from the extracted perceptual features with the contextual information of local scenes, to improve the matching robustness. Furthermore, we develop an attention-guided regularization module, which consists of multilevel ray fusion modules, to hierarchically aggregate and regularize the matching confidence volume into a latent depth probability volume.Experimental results show that our approach achieves the best overall performance on the DTU dataset and the intermediate sequences of Tanks & Temples benchmark over many state-of-the-art MVS algorithms.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"95 1","pages":"1587-1596"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88966625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose a boundary-aware multi-task deep-learning-based framework for fast 3D building modeling from a single overhead image. Unlike most existing techniques which rely on multiple images for 3D scene modeling, we seek to model the buildings in the scene from a single overhead image by jointly learning a modified signed distance function (SDF) from the building boundaries, a dense heightmap of the scene, and scene semantics. To jointly train for these tasks, we leverage pixel-wise semantic segmentation and normalized digital surface maps (nDSM) as supervision, in addition to labeled building outlines. At test time, buildings in the scene are automatically modeled in 3D using only an input overhead image. We demonstrate an increase in building modeling performance using a multi-feature network architecture that improves building outline detection by considering network features learned for the other jointly learned tasks. We also introduce a novel mechanism for robustly refining instance-specific building outlines using the learned modified SDF. We verify the effectiveness of our method on multiple large-scale satellite and aerial imagery datasets, where we obtain state-of-the-art performance in the 3D building reconstruction task.
{"title":"Boundary-Aware 3D Building Reconstruction From a Single Overhead Image","authors":"Jisan Mahmud, True Price, Akash Bapat, Jan-Michael Frahm","doi":"10.1109/cvpr42600.2020.00052","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.00052","url":null,"abstract":"We propose a boundary-aware multi-task deep-learning-based framework for fast 3D building modeling from a single overhead image. Unlike most existing techniques which rely on multiple images for 3D scene modeling, we seek to model the buildings in the scene from a single overhead image by jointly learning a modified signed distance function (SDF) from the building boundaries, a dense heightmap of the scene, and scene semantics. To jointly train for these tasks, we leverage pixel-wise semantic segmentation and normalized digital surface maps (nDSM) as supervision, in addition to labeled building outlines. At test time, buildings in the scene are automatically modeled in 3D using only an input overhead image. We demonstrate an increase in building modeling performance using a multi-feature network architecture that improves building outline detection by considering network features learned for the other jointly learned tasks. We also introduce a novel mechanism for robustly refining instance-specific building outlines using the learned modified SDF. We verify the effectiveness of our method on multiple large-scale satellite and aerial imagery datasets, where we obtain state-of-the-art performance in the 3D building reconstruction task.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"22 1","pages":"438-448"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81471331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/cvpr42600.2020.00916
Huajun Zhou, Xiaohua Xie, J. Lai, Zixuan Chen, Lingxiao Yang
Recently, contour information largely improves the performance of saliency detection. However, the discussion on the correlation between saliency and contour remains scarce. In this paper, we first analyze such correlation and then propose an interactive two-stream decoder to explore multiple cues, including saliency, contour and their correlation. Specifically, our decoder consists of two branches, a saliency branch and a contour branch. Each branch is assigned to learn distinctive features for predicting the corresponding map. Meanwhile, the intermediate connections are forced to learn the correlation by interactively transmitting the features from each branch to the other one. In addition, we develop an adaptive contour loss to automatically discriminate hard examples during learning process. Extensive experiments on six benchmarks well demonstrate that our network achieves competitive performance with a fast speed around 50 FPS. Moreover, our VGG-based model only contains 17.08 million parameters, which is significantly smaller than other VGG-based approaches. Code has been made available at: https://github.com/moothes/ITSD-pytorch.
{"title":"Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection","authors":"Huajun Zhou, Xiaohua Xie, J. Lai, Zixuan Chen, Lingxiao Yang","doi":"10.1109/cvpr42600.2020.00916","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.00916","url":null,"abstract":"Recently, contour information largely improves the performance of saliency detection. However, the discussion on the correlation between saliency and contour remains scarce. In this paper, we first analyze such correlation and then propose an interactive two-stream decoder to explore multiple cues, including saliency, contour and their correlation. Specifically, our decoder consists of two branches, a saliency branch and a contour branch. Each branch is assigned to learn distinctive features for predicting the corresponding map. Meanwhile, the intermediate connections are forced to learn the correlation by interactively transmitting the features from each branch to the other one. In addition, we develop an adaptive contour loss to automatically discriminate hard examples during learning process. Extensive experiments on six benchmarks well demonstrate that our network achieves competitive performance with a fast speed around 50 FPS. Moreover, our VGG-based model only contains 17.08 million parameters, which is significantly smaller than other VGG-based approaches. Code has been made available at: https://github.com/moothes/ITSD-pytorch.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"9138-9147"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84673840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/cvpr42600.2020.01434
Xikun Zhang, Chang Xu, D. Tao
Graph convolutional models have gained impressive successes on skeleton based human action recognition task. As graph convolution is a local operation, it cannot fully investigate non-local joints that could be vital to recognizing the action. For example, actions like typing and clapping request the cooperation of two hands, which are distant from each other in a human skeleton graph. Multiple graph convolutional layers thus tend to be stacked together to increase receptive field, which brings in computational inefficiency and optimization difficulty. But there is still no guarantee that distant joints (e.g. two hands) can be well integrated. In this paper, we propose a context aware graph convolutional network (CA-GCN). Besides the computation of localized graph convolution, CA-GCN considers a context term for each vertex by integrating information of all other vertices. Long range dependencies among joints are thus naturally integrated in context information, which then eliminates the need of stacking multiple layers to enlarge receptive field and greatly simplifies the network. Moreover, we further propose an advanced CA-GCN, in which asymmetric relevance measurement and higher level representation are utilized to compute context information for more flexibility and better performance. Besides the joint features, our CA-GCN could also be extended to handle graphs with edge (limb) features. Extensive experiments on two real-world datasets demonstrate the importance of context information and the effectiveness of the proposed CA-GCN in skeleton based action recognition.
{"title":"Context Aware Graph Convolution for Skeleton-Based Action Recognition","authors":"Xikun Zhang, Chang Xu, D. Tao","doi":"10.1109/cvpr42600.2020.01434","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.01434","url":null,"abstract":"Graph convolutional models have gained impressive successes on skeleton based human action recognition task. As graph convolution is a local operation, it cannot fully investigate non-local joints that could be vital to recognizing the action. For example, actions like typing and clapping request the cooperation of two hands, which are distant from each other in a human skeleton graph. Multiple graph convolutional layers thus tend to be stacked together to increase receptive field, which brings in computational inefficiency and optimization difficulty. But there is still no guarantee that distant joints (e.g. two hands) can be well integrated. In this paper, we propose a context aware graph convolutional network (CA-GCN). Besides the computation of localized graph convolution, CA-GCN considers a context term for each vertex by integrating information of all other vertices. Long range dependencies among joints are thus naturally integrated in context information, which then eliminates the need of stacking multiple layers to enlarge receptive field and greatly simplifies the network. Moreover, we further propose an advanced CA-GCN, in which asymmetric relevance measurement and higher level representation are utilized to compute context information for more flexibility and better performance. Besides the joint features, our CA-GCN could also be extended to handle graphs with edge (limb) features. Extensive experiments on two real-world datasets demonstrate the importance of context information and the effectiveness of the proposed CA-GCN in skeleton based action recognition.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"6 1","pages":"14321-14330"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84712882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：