Pub Date : 2021-10-01DOI: 10.1109/ICCV48922.2021.00377
Robin Magnet, M. Ovsjanikov
We propose a novel pointwise descriptor, called DWKS, aimed at finding correspondences across two deformable shape collections. Unlike the majority of existing descriptors, rather than capturing local geometry, DWKS captures the deformation around a point within a collection in a multi-scale and informative manner. This, in turn, allows to compute inter-collection correspondences without using landmarks. To this end, we build upon the successful spectral WKS descriptors, but rather than using the Laplace-Beltrami operator, show that a similar construction can be performed on shape difference operators, that capture differences or distortion within a collection. By leveraging the collection information our descriptor facilitates difficult non-rigid shape matching tasks, even in the presence of strong partiality and significant deformations. We demonstrate the utility of our approach across a range of challenging matching problems on both meshes and point clouds. The code for this paper can be found at https://github.com/RobinMagnet/DWKS
{"title":"DWKS : A Local Descriptor of Deformations Between Meshes and Point Clouds","authors":"Robin Magnet, M. Ovsjanikov","doi":"10.1109/ICCV48922.2021.00377","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00377","url":null,"abstract":"We propose a novel pointwise descriptor, called DWKS, aimed at finding correspondences across two deformable shape collections. Unlike the majority of existing descriptors, rather than capturing local geometry, DWKS captures the deformation around a point within a collection in a multi-scale and informative manner. This, in turn, allows to compute inter-collection correspondences without using landmarks. To this end, we build upon the successful spectral WKS descriptors, but rather than using the Laplace-Beltrami operator, show that a similar construction can be performed on shape difference operators, that capture differences or distortion within a collection. By leveraging the collection information our descriptor facilitates difficult non-rigid shape matching tasks, even in the presence of strong partiality and significant deformations. We demonstrate the utility of our approach across a range of challenging matching problems on both meshes and point clouds. The code for this paper can be found at https://github.com/RobinMagnet/DWKS","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"104 1","pages":"3773-3782"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85654959","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.01609
Xin Hao, Sanyuan Zhao, Mang Ye, Jianbing Shen
Cross-modality person re-identification is a challenging task due to large cross-modality discrepancy and intramodality variations. Currently, most existing methods focus on learning modality-specific or modality-shareable features by using the identity supervision or modality label. Different from existing methods, this paper presents a novel Modality Confusion Learning Network (MCLNet). Its basic idea is to confuse two modalities, ensuring that the optimization is explicitly concentrated on the modality-irrelevant perspective. Specifically, MCLNet is designed to learn modality-invariant features by simultaneously minimizing inter-modality discrepancy while maximizing cross-modality similarity among instances in a single framework. Furthermore, an identity-aware marginal center aggregation strategy is introduced to extract the centralization features, while keeping diversity with a marginal constraint. Finally, we design a camera-aware learning scheme to enrich the discriminability. Extensive experiments on SYSU-MM01 and RegDB datasets show that MCLNet outperforms the state-of-the-art by a large margin. On the large-scale SYSU-MM01 dataset, our model can achieve 65.40 % and 61.98 % in terms of Rank-1 accuracy and mAP value.
{"title":"Cross-Modality Person Re-Identification via Modality Confusion and Center Aggregation","authors":"Xin Hao, Sanyuan Zhao, Mang Ye, Jianbing Shen","doi":"10.1109/ICCV48922.2021.01609","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01609","url":null,"abstract":"Cross-modality person re-identification is a challenging task due to large cross-modality discrepancy and intramodality variations. Currently, most existing methods focus on learning modality-specific or modality-shareable features by using the identity supervision or modality label. Different from existing methods, this paper presents a novel Modality Confusion Learning Network (MCLNet). Its basic idea is to confuse two modalities, ensuring that the optimization is explicitly concentrated on the modality-irrelevant perspective. Specifically, MCLNet is designed to learn modality-invariant features by simultaneously minimizing inter-modality discrepancy while maximizing cross-modality similarity among instances in a single framework. Furthermore, an identity-aware marginal center aggregation strategy is introduced to extract the centralization features, while keeping diversity with a marginal constraint. Finally, we design a camera-aware learning scheme to enrich the discriminability. Extensive experiments on SYSU-MM01 and RegDB datasets show that MCLNet outperforms the state-of-the-art by a large margin. On the large-scale SYSU-MM01 dataset, our model can achieve 65.40 % and 61.98 % in terms of Rank-1 accuracy and mAP value.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"35 1","pages":"16383-16392"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85746695","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 : 2021-10-01DOI: 10.1109/iccv48922.2021.01452
Zheng Zhu, Xianda Guo, Tian Yang, Junjie Huang, Jiankang Deng, Guan Huang, Dalong Du, Jiwen Lu, Jie Zhou
Gait benchmarks empower the research community to train and evaluate high-performance gait recognition systems. Even though growing efforts have been devoted to cross-view recognition, academia is restricted by current existing databases captured in the controlled environment. In this paper, we contribute a new benchmark for Gait REcognition in the Wild (GREW). The GREW dataset is constructed from natural videos, which contains hundreds of cameras and thousands of hours streams in open systems. With tremendous manual annotations, the GREW consists of 26K identities and 128K sequences with rich attributes for unconstrained gait recognition. Moreover, we add a distractor set of over 233K sequences, making it more suitable for real-world applications. Compared with prevailing predefined cross-view datasets, the GREW has diverse and practical view variations, as well as more natural challenging factors. To the best of our knowledge, this is the first large-scale dataset for gait recognition in the wild. Equipped with this benchmark, we dissect the unconstrained gait recognition problem. Representative appearance-based and model-based methods are explored, and comprehensive baselines are established. Experimental results show (1) The proposed GREW benchmark is necessary for training and evaluating gait recognizer in the wild. (2) For state-of-the-art gait recognition approaches, there is a lot of room for improvement. (3) The GREW benchmark can be used as effective pre-training for controlled gait recognition. Benchmark website is https://www.grew-benchmark.org/.
{"title":"Gait Recognition in the Wild: A Benchmark","authors":"Zheng Zhu, Xianda Guo, Tian Yang, Junjie Huang, Jiankang Deng, Guan Huang, Dalong Du, Jiwen Lu, Jie Zhou","doi":"10.1109/iccv48922.2021.01452","DOIUrl":"https://doi.org/10.1109/iccv48922.2021.01452","url":null,"abstract":"Gait benchmarks empower the research community to train and evaluate high-performance gait recognition systems. Even though growing efforts have been devoted to cross-view recognition, academia is restricted by current existing databases captured in the controlled environment. In this paper, we contribute a new benchmark for Gait REcognition in the Wild (GREW). The GREW dataset is constructed from natural videos, which contains hundreds of cameras and thousands of hours streams in open systems. With tremendous manual annotations, the GREW consists of 26K identities and 128K sequences with rich attributes for unconstrained gait recognition. Moreover, we add a distractor set of over 233K sequences, making it more suitable for real-world applications. Compared with prevailing predefined cross-view datasets, the GREW has diverse and practical view variations, as well as more natural challenging factors. To the best of our knowledge, this is the first large-scale dataset for gait recognition in the wild. Equipped with this benchmark, we dissect the unconstrained gait recognition problem. Representative appearance-based and model-based methods are explored, and comprehensive baselines are established. Experimental results show (1) The proposed GREW benchmark is necessary for training and evaluating gait recognizer in the wild. (2) For state-of-the-art gait recognition approaches, there is a lot of room for improvement. (3) The GREW benchmark can be used as effective pre-training for controlled gait recognition. Benchmark website is https://www.grew-benchmark.org/.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"108 1","pages":"14769-14779"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85797240","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}
Geometric constraints are shown to enforce scale consistency and remedy the scale ambiguity issue in self-supervised monocular depth estimation. Meanwhile, scale-invariant losses focus on learning relative depth, leading to accurate relative depth prediction. To combine the best of both worlds, we learn scale-consistent self-supervised depth in a scale-invariant manner. Towards this goal, we present a scale-aware geometric (SAG) loss, which enforces scale consistency through point cloud alignment. Compared to prior arts, SAG loss takes relative scale into consideration during relative motion estimation, enabling more precise alignment and explicit supervision for scale inference. In addition, a novel two-stream architecture for depth estimation is designed, which disentangles scale from depth estimation and allows depth to be learned in a scale-invariant manner. The integration of SAG loss and two-stream network enables more consistent scale inference and more accurate relative depth estimation. Our method achieves state-of-the-art performance under both scale-invariant and scale-dependent evaluation settings.
{"title":"Can Scale-Consistent Monocular Depth Be Learned in a Self-Supervised Scale-Invariant Manner?","authors":"Lijun Wang, Yifan Wang, Linzhao Wang, Yu-Wei Zhan, Ying Wang, Huchuan Lu","doi":"10.1109/ICCV48922.2021.01249","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01249","url":null,"abstract":"Geometric constraints are shown to enforce scale consistency and remedy the scale ambiguity issue in self-supervised monocular depth estimation. Meanwhile, scale-invariant losses focus on learning relative depth, leading to accurate relative depth prediction. To combine the best of both worlds, we learn scale-consistent self-supervised depth in a scale-invariant manner. Towards this goal, we present a scale-aware geometric (SAG) loss, which enforces scale consistency through point cloud alignment. Compared to prior arts, SAG loss takes relative scale into consideration during relative motion estimation, enabling more precise alignment and explicit supervision for scale inference. In addition, a novel two-stream architecture for depth estimation is designed, which disentangles scale from depth estimation and allows depth to be learned in a scale-invariant manner. The integration of SAG loss and two-stream network enables more consistent scale inference and more accurate relative depth estimation. Our method achieves state-of-the-art performance under both scale-invariant and scale-dependent evaluation settings.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"6 1","pages":"12707-12716"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86279441","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}
Physical-world adversarial attacks based on universal adversarial patches have been proved to be able to mislead deep convolutional neural networks (CNNs), exposing the vulnerability of real-world visual classification systems based on CNNs. In this paper, we empirically reveal and mathematically explain that the universal adversarial patches usually lead to deep feature vectors with very large norms in popular CNNs. Inspired by this, we propose a simple yet effective defending approach using a new feature norm clipping (FNC) layer which is a differentiable module that can be flexibly inserted in different CNNs to adaptively suppress the generation of large norm deep feature vectors. FNC introduces no trainable parameter and only very low computational overhead. However, experiments on multiple datasets validate that it can effectively improve the robustness of different CNNs towards white-box universal patch attacks while maintaining a satisfactory recognition accuracy for clean samples.
{"title":"Defending against Universal Adversarial Patches by Clipping Feature Norms","authors":"Cheng Yu, Jiansheng Chen, Youze Xue, Yuyang Liu, Weitao Wan, Jiayu Bao, Huimin Ma","doi":"10.1109/ICCV48922.2021.01612","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01612","url":null,"abstract":"Physical-world adversarial attacks based on universal adversarial patches have been proved to be able to mislead deep convolutional neural networks (CNNs), exposing the vulnerability of real-world visual classification systems based on CNNs. In this paper, we empirically reveal and mathematically explain that the universal adversarial patches usually lead to deep feature vectors with very large norms in popular CNNs. Inspired by this, we propose a simple yet effective defending approach using a new feature norm clipping (FNC) layer which is a differentiable module that can be flexibly inserted in different CNNs to adaptively suppress the generation of large norm deep feature vectors. FNC introduces no trainable parameter and only very low computational overhead. However, experiments on multiple datasets validate that it can effectively improve the robustness of different CNNs towards white-box universal patch attacks while maintaining a satisfactory recognition accuracy for clean samples.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"16414-16422"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87395430","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.01506
Jingwei Huang, Yanfeng Zhang, Mingwei Sun
We present PrimitiveNet, a novel approach for high-resolution primitive instance segmentation from point clouds on a large scale. Our key idea is to transform the global segmentation problem into easier local tasks. We train a high-resolution primitive embedding network to predict explicit geometry features and implicit latent features for each point. The embedding is jointly trained with an adversarial network as a primitive discriminator to decide whether points are from the same primitive instance in local neighborhoods. Such local supervision encourages the learned embedding and discriminator to describe local surface properties and robustly distinguish different instances. At inference time, network predictions are followed by a region growing method to finalize the segmentation. Experiments show that our method outperforms existing state-of-the-arts based on mean average precision by a significant margin (46.3%) on ABC dataset [31]. We can process extremely large real scenes covering more than 0.1km2. Ablation studies highlight the contribution of our core designs. Finally, our method can improve geometry processing algorithms to abstract scans as lightweight models. Code and data will be available based on Pytorch1 and Mindspore2.
{"title":"PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric","authors":"Jingwei Huang, Yanfeng Zhang, Mingwei Sun","doi":"10.1109/ICCV48922.2021.01506","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01506","url":null,"abstract":"We present PrimitiveNet, a novel approach for high-resolution primitive instance segmentation from point clouds on a large scale. Our key idea is to transform the global segmentation problem into easier local tasks. We train a high-resolution primitive embedding network to predict explicit geometry features and implicit latent features for each point. The embedding is jointly trained with an adversarial network as a primitive discriminator to decide whether points are from the same primitive instance in local neighborhoods. Such local supervision encourages the learned embedding and discriminator to describe local surface properties and robustly distinguish different instances. At inference time, network predictions are followed by a region growing method to finalize the segmentation. Experiments show that our method outperforms existing state-of-the-arts based on mean average precision by a significant margin (46.3%) on ABC dataset [31]. We can process extremely large real scenes covering more than 0.1km2. Ablation studies highlight the contribution of our core designs. Finally, our method can improve geometry processing algorithms to abstract scans as lightweight models. Code and data will be available based on Pytorch1 and Mindspore2.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"40 1","pages":"15323-15333"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82250295","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.01027
Daniel Zoran, Rishabh Kabra, Alexander Lerchner, Danilo Jimenez Rezende
From an early age, humans perceive the visual world as composed of coherent objects with distinctive properties such as shape, size, and color. There is great interest in building models that are able to learn similar structure, ideally in an unsupervised manner. Learning such structure from complex 3D scenes that include clutter, occlusions, interactions, and camera motion is still an open challenge. We present a model that is able to segment visual scenes from complex 3D environments into distinct objects, learn disentangled representations of individual objects, and form consistent and coherent predictions of future frames, in a fully unsupervised manner. Our model (named PARTS) builds on recent approaches that utilize iterative amortized inference and transition dynamics for deep generative models. We achieve dramatic improvements in performance by introducing several novel contributions. We introduce a recurrent slot-attention like encoder which allows for top-down influence during inference. We argue that when inferring scene structure from image sequences it is better to use a fixed prior which is shared across the sequence rather than an auto-regressive prior as often used in prior work. We demonstrate our model’s success on three different video datasets (the popular benchmark CLEVRER; a simulated 3D Playroom environment; and a real-world Robotics Arm dataset). Finally, we analyze the contributions of the various model components and the representations learned by the model.
{"title":"PARTS: Unsupervised segmentation with slots, attention and independence maximization","authors":"Daniel Zoran, Rishabh Kabra, Alexander Lerchner, Danilo Jimenez Rezende","doi":"10.1109/ICCV48922.2021.01027","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01027","url":null,"abstract":"From an early age, humans perceive the visual world as composed of coherent objects with distinctive properties such as shape, size, and color. There is great interest in building models that are able to learn similar structure, ideally in an unsupervised manner. Learning such structure from complex 3D scenes that include clutter, occlusions, interactions, and camera motion is still an open challenge. We present a model that is able to segment visual scenes from complex 3D environments into distinct objects, learn disentangled representations of individual objects, and form consistent and coherent predictions of future frames, in a fully unsupervised manner. Our model (named PARTS) builds on recent approaches that utilize iterative amortized inference and transition dynamics for deep generative models. We achieve dramatic improvements in performance by introducing several novel contributions. We introduce a recurrent slot-attention like encoder which allows for top-down influence during inference. We argue that when inferring scene structure from image sequences it is better to use a fixed prior which is shared across the sequence rather than an auto-regressive prior as often used in prior work. We demonstrate our model’s success on three different video datasets (the popular benchmark CLEVRER; a simulated 3D Playroom environment; and a real-world Robotics Arm dataset). Finally, we analyze the contributions of the various model components and the representations learned by the model.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"16 1","pages":"10419-10427"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82547817","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.00639
Andrea Porfiri Dal Cin, L. Magri, F. Arrigoni, Andrea Fusiello, G. Boracchi
Synchronization refers to the problem of inferring the unknown values attached to vertices of a graph where edges are labelled with the ratio of the incident vertices, and labels belong to a group. This paper addresses the synchronization problem on multi-graphs, that are graphs with more than one edge connecting the same pair of nodes. The problem naturally arises when multiple measures are available to model the relationship between two vertices. This happens when different sensors measure the same quantity, or when the original graph is partitioned into sub-graphs that are solved independently. In this case, the relationships among sub-graphs give rise to multi-edges and the problem can be traced back to a multi-graph synchronization. The baseline solution reduces multi-graphs to simple ones by averaging their multi-edges, however this approach falls short because: i) averaging is well defined only for some groups and ii) the resulting estimator is less precise and accurate, as we prove empirically. Specifically, we present MULTISYNC, a synchronization algorithm for multi-graphs that is based on a principled constrained eigenvalue optimization. MULTISYNC is a general solution that can cope with any linear group and we show to be profitably usable both on synthetic and real problems.
{"title":"Synchronization of Group-labelled Multi-graphs","authors":"Andrea Porfiri Dal Cin, L. Magri, F. Arrigoni, Andrea Fusiello, G. Boracchi","doi":"10.1109/ICCV48922.2021.00639","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00639","url":null,"abstract":"Synchronization refers to the problem of inferring the unknown values attached to vertices of a graph where edges are labelled with the ratio of the incident vertices, and labels belong to a group. This paper addresses the synchronization problem on multi-graphs, that are graphs with more than one edge connecting the same pair of nodes. The problem naturally arises when multiple measures are available to model the relationship between two vertices. This happens when different sensors measure the same quantity, or when the original graph is partitioned into sub-graphs that are solved independently. In this case, the relationships among sub-graphs give rise to multi-edges and the problem can be traced back to a multi-graph synchronization. The baseline solution reduces multi-graphs to simple ones by averaging their multi-edges, however this approach falls short because: i) averaging is well defined only for some groups and ii) the resulting estimator is less precise and accurate, as we prove empirically. Specifically, we present MULTISYNC, a synchronization algorithm for multi-graphs that is based on a principled constrained eigenvalue optimization. MULTISYNC is a general solution that can cope with any linear group and we show to be profitably usable both on synthetic and real problems.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"34 1","pages":"6433-6443"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81289292","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.00701
Chi-Chong Wong, C. Vong
Fine-grained 3D segmentation is an important task in 3D object understanding, especially in applications such as intelligent manufacturing or parts analysis for 3D objects. However, many challenges involved in such problem are yet to be solved, such as i) interpreting the complex structures located in different regions for 3D objects; ii) capturing fine-grained structures with sufficient topology correctness. Current deep learning and graph machine learning methods fail to tackle such challenges and thus provide inferior performance in fine-grained 3D analysis. In this work, methods in topological data analysis are incorporated with geometric deep learning model for the task of fine-grained segmentation for 3D objects. We propose a novel neural network model called Persistent Homology based Graph Convolution Network (PHGCN), which i) integrates persistent homology into graph convolution network to capture multi-scale structural information that can accurately represent complex structures for 3D objects; ii) applies a novel Persistence Diagram Loss (ℒPD) that provides sufficient topology correctness for segmentation over the fine-grained structures. Extensive experiments on fine-grained 3D segmentation validate the effectiveness of the proposed PHGCN model and show significant improvements over current state-of-the-art methods.
{"title":"Persistent Homology based Graph Convolution Network for Fine-grained 3D Shape Segmentation","authors":"Chi-Chong Wong, C. Vong","doi":"10.1109/ICCV48922.2021.00701","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00701","url":null,"abstract":"Fine-grained 3D segmentation is an important task in 3D object understanding, especially in applications such as intelligent manufacturing or parts analysis for 3D objects. However, many challenges involved in such problem are yet to be solved, such as i) interpreting the complex structures located in different regions for 3D objects; ii) capturing fine-grained structures with sufficient topology correctness. Current deep learning and graph machine learning methods fail to tackle such challenges and thus provide inferior performance in fine-grained 3D analysis. In this work, methods in topological data analysis are incorporated with geometric deep learning model for the task of fine-grained segmentation for 3D objects. We propose a novel neural network model called Persistent Homology based Graph Convolution Network (PHGCN), which i) integrates persistent homology into graph convolution network to capture multi-scale structural information that can accurately represent complex structures for 3D objects; ii) applies a novel Persistence Diagram Loss (ℒPD) that provides sufficient topology correctness for segmentation over the fine-grained structures. Extensive experiments on fine-grained 3D segmentation validate the effectiveness of the proposed PHGCN model and show significant improvements over current state-of-the-art methods.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"7078-7087"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84367691","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 : 2021-10-01DOI: 10.1109/ICCV48922.2021.01346
Hanul Kim, Mihir Jain, Jun-Tae Lee, Sungrack Yun, F. Porikli
Efficient action recognition has become crucial to extend the success of action recognition to many real-world applications. Contrary to most existing methods, which mainly focus on selecting salient frames to reduce the computation cost, we focus more on making the most of the selected frames. To this end, we employ two networks of different capabilities that operate in tandem to efficiently recognize actions. Given a video, the lighter network processes more frames while the heavier one only processes a few. In order to enable the effective interaction between the two, we propose dynamic knowledge propagation based on a cross-attention mechanism. This is the main component of our framework that is essentially a student-teacher architecture, but as the teacher model continues to interact with the student model during inference, we call it a dynamic student-teacher framework. Through extensive experiments, we demonstrate the effectiveness of each component of our framework. Our method outperforms competing state-of-the-art methods on two video datasets: ActivityNet-v1.3 and Mini-Kinetics.
{"title":"Efficient Action Recognition via Dynamic Knowledge Propagation","authors":"Hanul Kim, Mihir Jain, Jun-Tae Lee, Sungrack Yun, F. Porikli","doi":"10.1109/ICCV48922.2021.01346","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01346","url":null,"abstract":"Efficient action recognition has become crucial to extend the success of action recognition to many real-world applications. Contrary to most existing methods, which mainly focus on selecting salient frames to reduce the computation cost, we focus more on making the most of the selected frames. To this end, we employ two networks of different capabilities that operate in tandem to efficiently recognize actions. Given a video, the lighter network processes more frames while the heavier one only processes a few. In order to enable the effective interaction between the two, we propose dynamic knowledge propagation based on a cross-attention mechanism. This is the main component of our framework that is essentially a student-teacher architecture, but as the teacher model continues to interact with the student model during inference, we call it a dynamic student-teacher framework. Through extensive experiments, we demonstrate the effectiveness of each component of our framework. Our method outperforms competing state-of-the-art methods on two video datasets: ActivityNet-v1.3 and Mini-Kinetics.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"42 2 1","pages":"13699-13708"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82859374","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：