检索结果-内蒙古大学图书馆

Learning to Reconnect Interrupted Trajectories for Weakly Supervised Multi-Object Tracking 48

学校读者我要写书评

暂无评论

Learning to Reconnect Interrupted Trajectories for Weakly Su...

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Li, Yu-Lei Lu, Yang Li, Jie Wang, Hanzi Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics China Xidian University Video and Image Processing System Laboratory School of Electronic Engineering China

ISBN: (纸本)9781728163277

Recently, some weakly supervised multi-object tracking (MOT) methods learn identity embedding features with pseudo identity labels rather than the high-cost manual ones. However, these pseudo identity labels may contain many false or missing identities, which adversely affect the optimization of tracking networks, resulting in interrupted trajectories of occluded targets. To effectively reconnect the interrupted trajectories caused by noisy pseudo labels, we propose a novel weakly supervised MOT method based on a Trajectory-Reconnecting Transformer (TRTMOT). TRT-MOT performs feature decoupling to extract discriminative embedding features for reconnecting trajectories of occluded targets. Experimental results show that TRTMOT outperforms previous weakly supervised MOT methods by at least +3.6 and +5.6 on MOTA for the MOT17 and MOT20 datasets, respectively. © 2023 IEEE.

关键词： Feature Decoupling Pseudo Identity Labels Trajectory-Reconnecting Transformer Weakly Supervised Multi-Object Tracking

Learning to Reconnect Interrupted Trajectories for Weakly Supervised Multi-Object Tracking

学校读者我要写书评

暂无评论

Learning to Reconnect Interrupted Trajectories for Weakly Su...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yu-Lei Li Yang Lu Jie Li Hanzi Wang Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University China

关键词： Technological innovation Target tracking Manuals Signal processing Feature extraction Transformers Trajectory

A Unified Framework for Domain Adaptive Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kim, Donghyun Wang, Kaihong Saenko, Kate Betke, Margrit Sclaroff, Stan Image and Video Computing Department of Computer Science Boston University United States MIT-IBM Watson AI Lab United States

While pose estimation is an important computer vision task, it requires expensive annotation and suffers from domain shift. In this paper, we investigate the problem of domain adaptive 2D pose estimation that transfers knowledge learned on a synthetic source domain to a target domain without supervision. While several domain adaptive pose estimation models have been proposed recently, they are not generic but only focus on either human pose or animal pose estimation, and thus their effectiveness is somewhat limited to specific scenarios. In this work, we propose a unified framework that generalizes well on various domain adaptive pose estimation problems. We propose to align representations using both input-level and output-level cues (pixels and pose labels, respectively), which facilitates the knowledge transfer from the source domain to the unlabeled target domain. Our experiments show that our method achieves state-of-the-art performance under various domain shifts. Our method outperforms existing baselines on human pose estimation by up to 4.5 percent points (pp), hand pose estimation by up to 7.4 pp, and animal pose estimation by up to 4.8 pp for dogs and 3.3 pp for sheep. These results suggest that our method is able to mitigate domain shift on diverse tasks and even unseen domains and objects (e.g., trained on horse and tested on dog). Our code will be publicly available at: https://***/VisionLearningGroup/UDA_PoseEstimation. Copyright © 2022, The Authors. All rights reserved.

关键词： Animals

MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Yukang Yan, Yan Li, Jie Wang, Hanzi Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi’an China Shanghai Artificial Intelligence Laboratory Shanghai China

Visible-infrared person re-identification (VI-ReID), which aims to search identities across different spectra, is a challenging task due to large cross-modality discrepancy between visible and infrared images. The key to reduce the discrepancy is to filter out identity-irrelevant interference and effectively learn modality-invariant person representations. In this paper, we propose a novel Modality Restitution and Compensation Network (MRCN) to narrow the gap between the two modalities. Specifically, we first reduce the modality discrepancy by using two Instance Normalization (IN) layers. Next, to reduce the influence of IN layers on removing discriminative information and to reduce modality differences, we propose a Modality Restitution Module (MRM) and a Modality Compensation Module (MCM) to respectively distill modality-irrelevant and modality-relevant features from the removed information. Then, the modality-irrelevant features are used to restitute to the normalized visible and infrared features, while the modality-relevant features are used to compensate for the features of the other modality. Furthermore, to better disentangle the modality-relevant features and the modality-irrelevant features, we propose a novel Center-Quadruplet Causal (CQC) loss to encourage the network to effectively learn the modality-relevant features and the modality-irrelevant features. Extensive experiments are conducted to validate the superiority of our method on the challenging SYSU-MM01 and RegDB datasets. More remarkably, our method achieves 95.1% in terms of Rank-1 and 89.2% in terms of mAP on the RegDB dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Infrared imaging

学校读者我要写书评

暂无评论

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jianghao Xiong Jianhuang Lai School of Computer Science and Engineering Sun Yat-Sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Key Laboratory of Video and Image Intelligent Analysis and Applicaiton Technology Ministry of Public Security China

Group re-identification (G-ReID) aims to re-identify a group of people that is observed from non-overlapping camera systems. The existing literature has mainly addressed RGB-based problems, but RGB-infrared (RGB-IR) cross-modality matching problem has not been studied yet. In this paper, we propose a metric learning method Closest Permutation Matching (CPM) for RGB-IR G-ReID. We model each group as a set of single-person features which are extracted by MPANet, then we propose the metric Closest Permutation Distance (CPD) to measure the similarity between two sets of features. CPD is invariant with order changes of group members so that it solves the layout change problem in G-ReID. Furthermore, we introduce the problem of G-ReID without person labels. In the weak-supervised case, we design the Relation-aware Module (RAM) that exploits visual context and relations among group members to produce a modality-invariant order of features in each group, with which group member features within a set can be sorted to form a robust group representation against modality change. To support the study on RGB-IR G-ReID, we construct a new large-scale RGB-IR G-ReID dataset CM-Group. The dataset contains 15,440 RGB images and 15,506 infrared images of 427 groups and 1,013 identi-ties. Extensive experiments on the new dataset demonstrate the effectiveness of the proposed models and the complexity of CM-Group. The code and dataset are available at: https://***/WhollyOat/CM-Group.

关键词：

Temporal Relevance Analysis for video Action Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fan, Quanfu Kim, Donghyun Chen, Chun-Fu Sclaroff, Stan Saenko, Kate Bargal, Sarah Adel Image and Video Computing Dept. of Computer Science Boston University United States MIT-IBM Watson AI Lab United States Future Lab for Applied Research and Engineering JPMorgan Chase Bank N.A United States

In this paper, we provide a deep analysis of temporal modeling for action recognition, an important but underexplored problem in the literature. We first propose a new approach to quantify the temporal relationships between frames captured by CNN-based action models based on layer-wise relevance propagation. We then conduct comprehensive experiments and in-depth analysis to provide a better understanding of how temporal modeling is affected by various factors such as dataset, network architecture, and input frames. With this, we further study some important questions for action recognition that lead to interesting findings. Our analysis shows that there is no strong correlation between temporal relevance and model performance;and action models tend to capture local temporal information, but less long-range dependencies. Our codes and models will be publicly available. Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

A bi-level formulation for label noise learning with spectral cluster discovery 29

学校读者我要写书评

暂无评论

A bi-level formulation for label noise learning with spectra...

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Luo, Yijing Han, Bo Gong, Chen PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China Jiangsu Key Lab of Image Video Understanding for Social Security China Department of Computer Science Hong Kong Baptist University Hong Kong Department of Computing Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9780999241165

Practically, we often face the dilemma that some of the examples for training a classifier are incorrectly labeled due to various subjective and objective factors. Although intensive efforts have been put to design classifiers that are robust to label noise, most of the previous methods have not fully utilized data distribution information. To address this issue, this paper introduces a bi-level learning paradigm termed "Spectral Cluster Discovery" (SCD) for combating with noisy labels. Namely, we simultaneously learn a robust classifier (Learning stage) by discovering the low-rank approximation to the ground-truth label matrix and learn an ideal affinity graph (Clustering stage). Specifically, we use the learned classifier to assign the examples with similar label to a mutual cluster. Based on the cluster membership, we use the learned affinity graph to explore the noisy examples based on the cluster membership. Both stages will reinforce each other iteratively. Experimental results on typical benchmark and real-world datasets verify the superiority of SCD to other label noise learning methods. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Iterative methods

Dual Interactive Graph Convolutional Networks for Hyperspectral image Classification

学校读者我要写书评

暂无评论

IEEE Transactions on Geoscience and Remote Sensing 2022年 60卷

作者： Wan, Sheng Pan, Shirui Zhong, Ping Chang, Xiaojun Yang, Jian Gong, Chen Pca Laboratory Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Faculty of Information Technology Monash University ClaytonVIC3800 Australia National Key Laboratory of Science and Technology on Atr National University of Defense Technology Changsha410073 China Pca Laboratory Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing210094 China Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong

Recently, graph convolutional network (GCN) has progressed significantly and gained increasing attention in hyperspectral image (HSI) classification due to its impressive representation power. However, existing GCN-based methods do not give full consideration to the multiscale spatial information, since the convolution operations are governed by fixed neighborhood. As a result, their performances can be limited, particularly in the regions with diverse land cover appearances. In this article, we develop a new dual interactive GCN (DIGCN) which introduces the dual GCN branches to capture spatial information at different scales. More significantly, the dual interactive module is embedded across the GCN branches, so that the correlation of multiscale spatial information can be leveraged to refine the graph information. To be concrete, the edge information contained in one GCN branch can be refined by incorporating the feature representations from the other branch. Analogously, improved feature representations can be generated in one GCN branch by fusing the edge information from the other branch. As such, the refined graph information can help enhance the representation power of the model. Furthermore, to avoid the negative effects of the manually constructed graph, our proposed model adaptively learns a discriminative region-induced graph, which also accelerates the convolution operation. We comprehensively evaluate the proposed method on four commonly used HSI benchmark data sets, and the state-of-the-art results can be achieved when compared with several typical HSI classification methods. © 1980-2012 IEEE.

关键词： Convolution

Exploring Separable Attention for Multi-Contrast MR image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Feng, Chun-Mei Yan, Yunlu Yu, Kai Xu, Yong Yang, Jian Shao, Ling Fu, Huazhu The Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen518055 China The Institute of High Performance Computing A*STAR Singapore138632 Singapore The PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing210094 China The Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Terminus Group China

Super-resolving the Magnetic Resonance (MR) image of a target contrast under the guidance of the corresponding auxiliary contrast, which provides additional anatomical information, is a new and effective solution for fast MR imaging. However, current multi-contrast super-resolution (SR) methods tend to concatenate different contrasts directly, ignoring their relationships in different clues, e.g., in the high-intensity and low-intensity regions. In this study, we propose a separable attention network (comprising high-intensity priority attention and low-intensity separation attention), named SANet. Our SANet could explore the areas of high-intensity and low-intensity regions in the "forward" and "reverse" directions with the help of the auxiliary contrast, while learning clearer anatomical structure and edge information for the SR of a target-contrast MR image. SANet provides three appealing benefits: (1) It is the first model to explore a separable attention mechanism that uses the auxiliary contrast to predict the high-intensity and low-intensity regions regions, diverting more attention to refining any uncertain details between these regions and correcting the fine areas in the reconstructed results. (2) A multi-stage integration module is proposed to learn the response of multi-contrast fusion at multiple stages, get the dependency between the fused representations, and boost their representation ability. (3) Extensive experiments with various state-of-the-art multi-contrast SR methods on fastMRI and clinical in vivo datasets demonstrate the superiority of our model. © 2021, CC BY.

关键词： Magnetic resonance imaging