Pub Date : 2021-10-01DOI: 10.1109/ICCV48922.2021.01313
X. Nguyen
In this paper, we propose a novel method for representation and classification of two-person interactions from 3D skeleton sequences. The key idea of our approach is to use Gaussian distributions to capture statistics on ℝn and those on the space of symmetric positive definite (SPD) matrices. The main challenge is how to parametrize those distributions. Towards this end, we develop methods for embedding Gaussian distributions in matrix groups based on the theory of Lie groups and Riemannian symmetric spaces. Our method relies on the Riemannian geometry of the underlying manifolds and has the advantage of encoding high-order statistics from 3D joint positions. We show that the proposed method achieves competitive results in two-person interaction recognition on three benchmarks for 3D human activity understanding.
{"title":"GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition","authors":"X. Nguyen","doi":"10.1109/ICCV48922.2021.01313","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01313","url":null,"abstract":"In this paper, we propose a novel method for representation and classification of two-person interactions from 3D skeleton sequences. The key idea of our approach is to use Gaussian distributions to capture statistics on ℝn and those on the space of symmetric positive definite (SPD) matrices. The main challenge is how to parametrize those distributions. Towards this end, we develop methods for embedding Gaussian distributions in matrix groups based on the theory of Lie groups and Riemannian symmetric spaces. Our method relies on the Riemannian geometry of the underlying manifolds and has the advantage of encoding high-order statistics from 3D joint positions. We show that the proposed method achieves competitive results in two-person interaction recognition on three benchmarks for 3D human activity understanding.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"7 1","pages":"13359-13369"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89415472","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/ICCV48922.2021.00227
Bing Li, Chia-Wen Lin, Cheng Zheng, Sha Liu, Junsong Yuan, Bernard Ghanem, C. J. Kuo, King Abdullah
A high quality disparity remapping method that preserves 2D shapes and 3D structures, and adjusts disparities of important objects in stereo image pairs is proposed. It is formulated as a constrained optimization problem, whose solution is challenging, since we need to meet multiple requirements of disparity remapping simultaneously. The one-stage optimization process either degrades the quality of important objects or introduces serious distortions in background regions. To address this challenge, we propose a two-stage warping process to solve it. In the first stage, we develop a warping model that finds the optimal warping grids for important objects to fulfill multiple requirements of disparity remapping. In the second stage, we derive another warping model to refine warping results in less important regions by eliminating serious distortions in shape, disparity and 3D structure. The superior performance of the proposed method is demonstrated by experimental results.
{"title":"High Quality Disparity Remapping with Two-Stage Warping","authors":"Bing Li, Chia-Wen Lin, Cheng Zheng, Sha Liu, Junsong Yuan, Bernard Ghanem, C. J. Kuo, King Abdullah","doi":"10.1109/ICCV48922.2021.00227","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00227","url":null,"abstract":"A high quality disparity remapping method that preserves 2D shapes and 3D structures, and adjusts disparities of important objects in stereo image pairs is proposed. It is formulated as a constrained optimization problem, whose solution is challenging, since we need to meet multiple requirements of disparity remapping simultaneously. The one-stage optimization process either degrades the quality of important objects or introduces serious distortions in background regions. To address this challenge, we propose a two-stage warping process to solve it. In the first stage, we develop a warping model that finds the optimal warping grids for important objects to fulfill multiple requirements of disparity remapping. In the second stage, we derive another warping model to refine warping results in less important regions by eliminating serious distortions in shape, disparity and 3D structure. The superior performance of the proposed method is demonstrated by experimental results.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"43 1","pages":"2249-2258"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86511302","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/ICCV48922.2021.01093
N. Ghorbani, Michael J. Black
Marker-based optical motion capture (mocap) is the "gold standard" method for acquiring accurate 3D human motion in computer vision, medicine, and graphics. The raw output of these systems are noisy and incomplete 3D points or short tracklets of points. To be useful, one must associate these points with corresponding markers on the captured subject; i.e. "labelling". Given these labels, one can then "solve" for the 3D skeleton or body surface mesh. Commercial auto-labeling tools require a specific calibration procedure at capture time, which is not possible for archival data. Here we train a novel neural network called SOMA, which takes raw mocap point clouds with varying numbers of points, labels them at scale without any calibration data, independent of the capture technology, and requiring only minimal human intervention. Our key insight is that, while labeling point clouds is highly ambiguous, the 3D body provides strong constraints on the solution that can be exploited by a learning-based method. To enable learning, we generate massive training sets of simulated noisy and ground truth mocap markers animated by 3D bodies from AMASS. SOMA exploits an architecture with stacked self-attention elements to learn the spatial structure of the 3D body and an optimal transport layer to constrain the assignment (labeling) problem while rejecting outliers. We extensively evaluate SOMA both quantitatively and qualitatively. SOMA is more accurate and robust than existing state of the art research methods and can be applied where commercial systems cannot. We automatically label over 8 hours of archival mocap data across 4 different datasets captured using various technologies and output SMPL-X body models. The model and data is released for research purposes at https://soma.is.tue.mpg.de/.
{"title":"SOMA: Solving Optical Marker-Based MoCap Automatically","authors":"N. Ghorbani, Michael J. Black","doi":"10.1109/ICCV48922.2021.01093","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01093","url":null,"abstract":"Marker-based optical motion capture (mocap) is the \"gold standard\" method for acquiring accurate 3D human motion in computer vision, medicine, and graphics. The raw output of these systems are noisy and incomplete 3D points or short tracklets of points. To be useful, one must associate these points with corresponding markers on the captured subject; i.e. \"labelling\". Given these labels, one can then \"solve\" for the 3D skeleton or body surface mesh. Commercial auto-labeling tools require a specific calibration procedure at capture time, which is not possible for archival data. Here we train a novel neural network called SOMA, which takes raw mocap point clouds with varying numbers of points, labels them at scale without any calibration data, independent of the capture technology, and requiring only minimal human intervention. Our key insight is that, while labeling point clouds is highly ambiguous, the 3D body provides strong constraints on the solution that can be exploited by a learning-based method. To enable learning, we generate massive training sets of simulated noisy and ground truth mocap markers animated by 3D bodies from AMASS. SOMA exploits an architecture with stacked self-attention elements to learn the spatial structure of the 3D body and an optimal transport layer to constrain the assignment (labeling) problem while rejecting outliers. We extensively evaluate SOMA both quantitatively and qualitatively. SOMA is more accurate and robust than existing state of the art research methods and can be applied where commercial systems cannot. We automatically label over 8 hours of archival mocap data across 4 different datasets captured using various technologies and output SMPL-X body models. The model and data is released for research purposes at https://soma.is.tue.mpg.de/.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"11097-11106"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88179681","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/ICCV48922.2021.00172
Fei Liu, Jing Liu, Weining Wang, Hanqing Lu
Relational reasoning is at the heart of video question answering. However, existing approaches suffer from several common limitations: (1) they only focus on either object-level or frame-level relational reasoning, and fail to integrate the both; and (2) they neglect to leverage semantic knowledge for relational reasoning. In this work, we propose a Hierarchical VisuAl-Semantic RelatIonal Reasoning (HAIR) framework to address these limitations. Specifically, we present a novel graph memory mechanism to perform relational reasoning, and further develop two types of graph memory: a) visual graph memory that leverages visual information of video for relational reasoning; b) semantic graph memory that is specifically designed to explicitly leverage semantic knowledge contained in the classes and attributes of video objects, and perform relational reasoning in the semantic space. Taking advantage of both graph memory mechanisms, we build a hierarchical framework to enable visual-semantic relational reasoning from object level to frame level. Experiments on four challenging benchmark datasets show that the proposed framework leads to state-of-the-art performance, with fewer parameters and faster inference speed. Besides, our approach also shows superior performance on other video+language task.
{"title":"HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question Answering","authors":"Fei Liu, Jing Liu, Weining Wang, Hanqing Lu","doi":"10.1109/ICCV48922.2021.00172","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00172","url":null,"abstract":"Relational reasoning is at the heart of video question answering. However, existing approaches suffer from several common limitations: (1) they only focus on either object-level or frame-level relational reasoning, and fail to integrate the both; and (2) they neglect to leverage semantic knowledge for relational reasoning. In this work, we propose a Hierarchical VisuAl-Semantic RelatIonal Reasoning (HAIR) framework to address these limitations. Specifically, we present a novel graph memory mechanism to perform relational reasoning, and further develop two types of graph memory: a) visual graph memory that leverages visual information of video for relational reasoning; b) semantic graph memory that is specifically designed to explicitly leverage semantic knowledge contained in the classes and attributes of video objects, and perform relational reasoning in the semantic space. Taking advantage of both graph memory mechanisms, we build a hierarchical framework to enable visual-semantic relational reasoning from object level to frame level. Experiments on four challenging benchmark datasets show that the proposed framework leads to state-of-the-art performance, with fewer parameters and faster inference speed. Besides, our approach also shows superior performance on other video+language task.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"7 1","pages":"1678-1687"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75993509","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/ICCV48922.2021.00252
Nianyi Li, Simron Thapa, Cameron Whyte, Albert W. Reed, Suren Jayasuriya, Jinwei Ye
Many computer vision problems face difficulties when imaging through turbulent refractive media (e.g., air and water) due to the refraction and scattering of light. These effects cause geometric distortion that requires either handcrafted physical priors or supervised learning methods to remove. In this paper, we present a novel unsupervised network to recover the latent distortion-free image. The key idea is to model non-rigid distortions as deformable grids. Our network consists of a grid deformer that estimates the distortion field and an image generator that outputs the distortion-free image. By leveraging the positional encoding operator, we can simplify the network structure while maintaining fine spatial details in the recovered images. Our method doesn't need to be trained on labeled data and has good transferability across various turbulent image datasets with different types of distortions. Extensive experiments on both simulated and real-captured turbulent images demonstrate that our method can remove both air and water distortions without much customization.
{"title":"Unsupervised Non-Rigid Image Distortion Removal via Grid Deformation","authors":"Nianyi Li, Simron Thapa, Cameron Whyte, Albert W. Reed, Suren Jayasuriya, Jinwei Ye","doi":"10.1109/ICCV48922.2021.00252","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00252","url":null,"abstract":"Many computer vision problems face difficulties when imaging through turbulent refractive media (e.g., air and water) due to the refraction and scattering of light. These effects cause geometric distortion that requires either handcrafted physical priors or supervised learning methods to remove. In this paper, we present a novel unsupervised network to recover the latent distortion-free image. The key idea is to model non-rigid distortions as deformable grids. Our network consists of a grid deformer that estimates the distortion field and an image generator that outputs the distortion-free image. By leveraging the positional encoding operator, we can simplify the network structure while maintaining fine spatial details in the recovered images. Our method doesn't need to be trained on labeled data and has good transferability across various turbulent image datasets with different types of distortions. Extensive experiments on both simulated and real-captured turbulent images demonstrate that our method can remove both air and water distortions without much customization.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"41 1","pages":"2502-2512"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79899446","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/ICCV48922.2021.00319
Zhiheng Ma, Xiaopeng Hong, Xing Wei, Yunfeng Qiu, Yihong Gong
This paper proposes to handle the practical problem of learning a universal model for crowd counting across scenes and datasets. We dissect that the crux of this problem is the catastrophic sensitivity of crowd counters to scale shift, which is very common in the real world and caused by factors such as different scene layouts and image resolutions. Therefore it is difficult to train a universal model that can be applied to various scenes. To address this problem, we propose scale alignment as a prime module for establishing a novel crowd counting framework. We derive a closed-form solution to get the optimal image rescaling factors for alignment by minimizing the distances between their scale distributions. A novel neural network together with a loss function based on an efficient sliced Wasserstein distance is also proposed for scale distribution estimation. Benefiting from the proposed method, we have learned a universal model that generally works well on several datasets where can even outperform state-of-the-art models that are particularly fine-tuned for each dataset significantly. Experiments also demonstrate the much better generalizability of our model to unseen scenes.
{"title":"Towards A Universal Model for Cross-Dataset Crowd Counting","authors":"Zhiheng Ma, Xiaopeng Hong, Xing Wei, Yunfeng Qiu, Yihong Gong","doi":"10.1109/ICCV48922.2021.00319","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00319","url":null,"abstract":"This paper proposes to handle the practical problem of learning a universal model for crowd counting across scenes and datasets. We dissect that the crux of this problem is the catastrophic sensitivity of crowd counters to scale shift, which is very common in the real world and caused by factors such as different scene layouts and image resolutions. Therefore it is difficult to train a universal model that can be applied to various scenes. To address this problem, we propose scale alignment as a prime module for establishing a novel crowd counting framework. We derive a closed-form solution to get the optimal image rescaling factors for alignment by minimizing the distances between their scale distributions. A novel neural network together with a loss function based on an efficient sliced Wasserstein distance is also proposed for scale distribution estimation. Benefiting from the proposed method, we have learned a universal model that generally works well on several datasets where can even outperform state-of-the-art models that are particularly fine-tuned for each dataset significantly. Experiments also demonstrate the much better generalizability of our model to unseen scenes.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"54 6 1","pages":"3185-3194"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77099630","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/ICCV48922.2021.00490
Pei Wang, N. Vasconcelos
We consider the scalable recognition problem in the fine-grained expert domain where large-scale data collection is easy whereas annotation is difficult. Existing solutions are typically based on semi-supervised or self-supervised learning. We propose an alternative new framework, MEMORABLE, based on machine teaching and online crowd-sourcing platforms. A small amount of data is first labeled by experts and then used to teach online annotators for the classes of interest, who finally label the entire dataset. Preliminary studies show that the accuracy of classifiers trained on the final dataset is a function of the accuracy of the student annotators. A new machine teaching algorithm, CMaxGrad, is then proposed to enhance this accuracy by introducing explanations in a state-of-the-art machine teaching algorithm. For this, CMaxGrad leverages counterfactual explanations, which take into account student predictions, thereby proving feedback that is student-specific, explicitly addresses the causes of student confusion, and adapts to the level of competence of the student. Experiments show that both MEMORABLE and CMaxGrad outperform existing solutions to their respective problems.
{"title":"A Machine Teaching Framework for Scalable Recognition","authors":"Pei Wang, N. Vasconcelos","doi":"10.1109/ICCV48922.2021.00490","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00490","url":null,"abstract":"We consider the scalable recognition problem in the fine-grained expert domain where large-scale data collection is easy whereas annotation is difficult. Existing solutions are typically based on semi-supervised or self-supervised learning. We propose an alternative new framework, MEMORABLE, based on machine teaching and online crowd-sourcing platforms. A small amount of data is first labeled by experts and then used to teach online annotators for the classes of interest, who finally label the entire dataset. Preliminary studies show that the accuracy of classifiers trained on the final dataset is a function of the accuracy of the student annotators. A new machine teaching algorithm, CMaxGrad, is then proposed to enhance this accuracy by introducing explanations in a state-of-the-art machine teaching algorithm. For this, CMaxGrad leverages counterfactual explanations, which take into account student predictions, thereby proving feedback that is student-specific, explicitly addresses the causes of student confusion, and adapts to the level of competence of the student. Experiments show that both MEMORABLE and CMaxGrad outperform existing solutions to their respective problems.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"48 1","pages":"4925-4934"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76913312","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/ICCV48922.2021.00451
Jérôme Revaud, M. Humenberger
Even though CCTV cameras are widely deployed for traffic surveillance and have therefore the potential of becoming cheap automated sensors for traffic speed analysis, their large-scale usage toward this goal has not been reported yet. A key difficulty lies in fact in the camera calibration phase. Existing state-of-the-art methods perform the calibration using image processing or keypoint detection techniques that require high-quality video streams, yet typical CCTV footage is low-resolution and noisy. As a result, these methods largely fail in real-world conditions. In contrast, we propose two novel calibration techniques whose only inputs come from an off-the-shelf object detector. Both methods consider multiple detections jointly, leveraging the fact that cars have similar and well-known 3D shapes with normalized dimensions. The first one is based on minimizing an energy function corresponding to a 3D reprojection error, the second one instead learns from synthetic training data to predict the scene geometry directly. Noticing the lack of speed estimation benchmarks faithfully reflecting the actual quality of surveillance cameras, we introduce a novel dataset collected from public CCTV streams. Experimental results conducted on three diverse benchmarks demonstrate excellent speed estimation accuracy that could enable the wide use of CCTV cameras for traffic analysis, even in challenging conditions where state-of-the-art methods completely fail. Additional information can be found on our project web page: https://rebrand.ly/nle-cctv
{"title":"Robust Automatic Monocular Vehicle Speed Estimation for Traffic Surveillance","authors":"Jérôme Revaud, M. Humenberger","doi":"10.1109/ICCV48922.2021.00451","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00451","url":null,"abstract":"Even though CCTV cameras are widely deployed for traffic surveillance and have therefore the potential of becoming cheap automated sensors for traffic speed analysis, their large-scale usage toward this goal has not been reported yet. A key difficulty lies in fact in the camera calibration phase. Existing state-of-the-art methods perform the calibration using image processing or keypoint detection techniques that require high-quality video streams, yet typical CCTV footage is low-resolution and noisy. As a result, these methods largely fail in real-world conditions. In contrast, we propose two novel calibration techniques whose only inputs come from an off-the-shelf object detector. Both methods consider multiple detections jointly, leveraging the fact that cars have similar and well-known 3D shapes with normalized dimensions. The first one is based on minimizing an energy function corresponding to a 3D reprojection error, the second one instead learns from synthetic training data to predict the scene geometry directly. Noticing the lack of speed estimation benchmarks faithfully reflecting the actual quality of surveillance cameras, we introduce a novel dataset collected from public CCTV streams. Experimental results conducted on three diverse benchmarks demonstrate excellent speed estimation accuracy that could enable the wide use of CCTV cameras for traffic analysis, even in challenging conditions where state-of-the-art methods completely fail. Additional information can be found on our project web page: https://rebrand.ly/nle-cctv","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"222 1","pages":"4531-4541"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76421028","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 present a unified and flexible framework to address the generalized problem of 3D motion synthesis that covers the tasks of motion prediction, completion, interpolation, and spatial-temporal recovery. Since these tasks have different input constraints and various fidelity and diversity requirements, most existing approaches only cater to a specific task or use different architectures to address various tasks. Here we propose a unified framework based on Conditional Variational Auto-Encoder (CVAE), where we treat any arbitrary input as a masked motion series. Notably, by considering this problem as a conditional generation process, we estimate a parametric distribution of the missing regions based on the input conditions, from which to sample and synthesize the full motion series. To further allow the flexibility of manipulating the motion style of the generated series, we design an Action-Adaptive Modulation (AAM) to propagate the given semantic guidance through the whole sequence. We also introduce a cross-attention mechanism to exploit distant relations among decoder and encoder features for better realism and global consistency. We conducted extensive experiments on Human 3.6M and CMU-Mocap. The results show that our method produces coherent and realistic results for various motion synthesis tasks, with the synthesized motions distinctly adapted by the given action labels.
{"title":"A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder∗","authors":"Yujun Cai, Yiwei Wang, Yiheng Zhu, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Chuanxia Zheng, Sijie Yan, Henghui Ding, Xiaohui Shen, Ding Liu, N. Thalmann","doi":"10.1109/ICCV48922.2021.01144","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01144","url":null,"abstract":"We present a unified and flexible framework to address the generalized problem of 3D motion synthesis that covers the tasks of motion prediction, completion, interpolation, and spatial-temporal recovery. Since these tasks have different input constraints and various fidelity and diversity requirements, most existing approaches only cater to a specific task or use different architectures to address various tasks. Here we propose a unified framework based on Conditional Variational Auto-Encoder (CVAE), where we treat any arbitrary input as a masked motion series. Notably, by considering this problem as a conditional generation process, we estimate a parametric distribution of the missing regions based on the input conditions, from which to sample and synthesize the full motion series. To further allow the flexibility of manipulating the motion style of the generated series, we design an Action-Adaptive Modulation (AAM) to propagate the given semantic guidance through the whole sequence. We also introduce a cross-attention mechanism to exploit distant relations among decoder and encoder features for better realism and global consistency. We conducted extensive experiments on Human 3.6M and CMU-Mocap. The results show that our method produces coherent and realistic results for various motion synthesis tasks, with the synthesized motions distinctly adapted by the given action labels.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"33 1","pages":"11625-11635"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81203301","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/ICCV48922.2021.00325
G. Han, Yicheng He, Shiyuan Huang, Jiawei Ma, Shih-Fu Chang
Few-shot object detection (FSOD) aims to detect never-seen objects using few examples. This field sees recent improvement owing to the meta-learning techniques by learning how to match between the query image and few-shot class examples, such that the learned model can generalize to few-shot novel classes. However, currently, most of the meta-learning-based methods perform parwise matching between query image regions (usually proposals) and novel classes separately, therefore failing to take into account multiple relationships among them. In this paper, we propose a novel FSOD model using heterogeneous graph convolutional networks. Through efficient message passing among all the proposal and class nodes with three different types of edges, we could obtain context-aware proposal features and query-adaptive, multiclass-enhanced prototype representations for each class, which could help promote the pairwise matching and improve final FSOD accuracy. Extensive experimental results show that our proposed model, denoted as QA-FewDet, outperforms the current state-of-the-art approaches on the PASCAL VOC and MSCOCO FSOD benchmarks under different shots and evaluation metrics.
{"title":"Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks","authors":"G. Han, Yicheng He, Shiyuan Huang, Jiawei Ma, Shih-Fu Chang","doi":"10.1109/ICCV48922.2021.00325","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00325","url":null,"abstract":"Few-shot object detection (FSOD) aims to detect never-seen objects using few examples. This field sees recent improvement owing to the meta-learning techniques by learning how to match between the query image and few-shot class examples, such that the learned model can generalize to few-shot novel classes. However, currently, most of the meta-learning-based methods perform parwise matching between query image regions (usually proposals) and novel classes separately, therefore failing to take into account multiple relationships among them. In this paper, we propose a novel FSOD model using heterogeneous graph convolutional networks. Through efficient message passing among all the proposal and class nodes with three different types of edges, we could obtain context-aware proposal features and query-adaptive, multiclass-enhanced prototype representations for each class, which could help promote the pairwise matching and improve final FSOD accuracy. Extensive experimental results show that our proposed model, denoted as QA-FewDet, outperforms the current state-of-the-art approaches on the PASCAL VOC and MSCOCO FSOD benchmarks under different shots and evaluation metrics.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"14 1","pages":"3243-3252"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83539527","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：