Graph Convolutional Tracking

Gao, Junyu; Zhang, Tianzhu; Xu, Changsheng

doi:10.1109/cvpr.2019.00478

Cited by 284 publications

(114 citation statements)

References 68 publications

Supporting

Mentioning

114

Contrasting

Order By: Relevance

“…State-of-the-art competitors: We compare our CRCDCF with 21 state-of-the-art trackers including SAMF [15], SRDCF [31], Staple [20], BACF [22], STAPLE-CA [21], CSRDCF [52] , ECO-HC [9], STRCF [54], CREST [55], CFWCR [56], SiamFC [57], CFNet [58], MCPF [59], C-COT [60] and ECO [9], SRDCF-deep [17], TRACA [61], MCCT [48], GCT [62], TADT [63], and GradNet [64]. For a fair comparison, all the results of these trackers were obtained by re-running these algorithms on the datasets using the source codes published by the original authors with the provided parameter settings.…”

Section: B Experimental Setup Datasetsmentioning

confidence: 99%

Complementary Discriminative Correlation Filters Based on Collaborative Representation for Visual Object Tracking

Zhu

et al. 2021

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Section: B Experimental Setup Datasetsmentioning

confidence: 99%

Complementary Discriminative Correlation Filters Based on Collaborative Representation for Visual Object Tracking

Zhu

et al. 2021

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

“…Veličković et al [35] proposed graph attention network (GAT), a new convolution-style neural network that operates on graph-structured data, leveraging masked self-attentional layers. It has been adopted successfully in many multimedia tasks, such as image classification [26], visual question answering [29], graph classification [13,47], object tracking [5], point clouds processing [37], action recognition [36] and person search [44] etc.…”

Section: Related Workmentioning

confidence: 99%

A Structured Graph Attention Network for Vehicle Re-Identification

Zhu

Zha

Zhang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Vehicle re-identification aims to identify the same vehicle across different surveillance cameras and plays an important role in public security. Existing approaches mainly focus on exploring informative regions or learning an appropriate distance metric. However, they not only neglect the inherent structured relationship between discriminative regions within an image, but also ignore the extrinsic structured relationship among images. The inherent and extrinsic structured relationships are crucial to learning effective vehicle representation. In this paper, we propose a Structured Graph ATtention network (SGAT) to fully exploit these relationships and allow the message propagation to update the features of graph nodes. SGAT creates two graphs for one probe image. One is an inherent structured graph based on the geometric relationship between the landmarks that can use features of their neighbors to enhance themselves. The other is an extrinsic structured graph guided by the attribute similarity to update image representations. Experimental results on two public vehicle re-identification datasets including VeRi-776 and VehicleID have shown that our proposed method achieves significant improvements over the state-of-the-art methods. CCS CONCEPTS • Information systems → Top-k retrieval in databases; • Computing methodologies → Visual content-based indexing and retrieval.

show abstract

“…GNN has been used in many tasks involving relation inference, such as human-object interaction (HOI) [7,29], scene understanding [19,24], human action localization [48] and human gaze communication [22]. GNN was also used to model the different parts of a human or other objects for action recognition [45] and object tracking [8]. More recently, several works [39,47] were proposed to solve the deep graph matching problem, with verified the effectiveness in both theory and applications.…”

Section: Graph Neural Networkmentioning

confidence: 99%

“…The GConv and CrossConv in GMN and the functions of Eqs. (5,6,8,9) in GIN are implemented by neural networks, whose parameters are learnable. The proposed GMN and GIN are trained in an end-to-end way.…”

Section: Detailed Network Architecturementioning

confidence: 99%

Human Identification and Interaction Detection in Cross-View Multi-Person Videos with Wearable Cameras

Zhao

Han

Gan

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Compared to a single fixed camera, multiple moving cameras, e.g., those worn by people, can better capture the human interactive and group activities in a scene, by providing multiple, flexible and possibly complementary views of the involved people. In this setting the actual promotion of activity detection is highly dependent on the effective correlation and collaborative analysis of multiple videos taken by different wearable cameras, which is highly challenging given the time-varying view differences across different cameras and mutual occlusion of people in each video. By focusing on two wearable cameras and the interactive activities that involve only two people, in this paper we develop a new approach that can simultaneously: (i) identify the same persons across the two videos, (ii) detect the interactive activities of interest, including their occurrence intervals and involved people, and (iii) recognize the category of each interactive activity. Specifically, we represent each video by a graph, with detected persons as nodes, and propose a unified Graph Neural Network (GNN) based framework to jointly solve the above three problems. A graph matching network is developed for identifying the same persons across the two videos and a graph inference network is then used for detecting the human interactions. We also build a new video dataset, which provides a benchmark for this study, and conduct extensive experiments to validate the effectiveness and superiority of the proposed method.

show abstract

Graph Convolutional Tracking

Cited by 284 publications

References 68 publications

Complementary Discriminative Correlation Filters Based on Collaborative Representation for Visual Object Tracking

Complementary Discriminative Correlation Filters Based on Collaborative Representation for Visual Object Tracking

A Structured Graph Attention Network for Vehicle Re-Identification

Human Identification and Interaction Detection in Cross-View Multi-Person Videos with Wearable Cameras

Contact Info

Product

Resources

About