Jie Wu
Research Subjects
Jie Wu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Hongming Zhang
College of Information Engineering, Northwest A&F University, Yangling 712100, China
2 shared publications Mingyu Cai
College of Information Engineering, Northwest AF University, Xianyang, China
2 shared publications- Bin Li
Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China
1 shared publication - Cheng Sun
School of Civil Engineering and Architecture, Guangxi Minzu University, Nanning 530006, China
1 shared publication - Guang Chen
Bureau of Academic Divisions, Chinese Academy of Sciences, Beijing 100190, China
1 shared publication Hanchen Wang
1 shared publication
Latest Publications
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (3) , 2556-2569
Visual Object Tracking With Multi-Frame Distractor Suppression
With the rapid development of CNN or Transformer, the present mainstream approaches regard an image patch as the reference of the target to perform tracking, which is known as template matching-based trackers. However, most existing template matching-based trackers only consider the per-frame localization accuracy, neglecting the potential distractor (similar object) dependencies among multiple video frames, which poses a fundamental challenge in template matching-based tracking. In this work, we propose a novel comprehensive framework with multi-frame distractor suppression for visual object tracking (MFDSTrack), which explicitly models the temporal history of both the target object and potential distractors. Specifically, we utilize a universal target candidate generation module to detect target candidates (both target and distractors), providing a holistic view of the scene. In addition, a temporal and distractor-aware association module is designed to suppress multi-frame distractors by adopting a simple encoder-decoder Transformer architecture. The encoder accepts inputs of target candidates’ history, while the decoder takes current target candidate queries and the output of the encoder as inputs to associate current target candidate queries with historical trajectories. We extensively evaluate our trackers, MFDSTrack-SD, MFDSTrack-OS, MFDSTrack-GRM, and MFDSTrack-LT on the LaSOT, LaSOText, TrackingNet, GOT-10k, UAV123, NFS, and OTB100 benchmark. Extensive experiments show that our methods outperform previous state-of-the-art trackers on seven tracking benchmarks.
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (3) , 2556-2569
Visual Object Tracking With Multi-Frame Distractor Suppression
With the rapid development of CNN or Transformer, the present mainstream approaches regard an image patch as the reference of the target to perform tracking, which is known as template matching-based trackers. However, most existing template matching-based trackers only consider the per-frame localization accuracy, neglecting the potential distractor (similar object) dependencies among multiple video frames, which poses a fundamental challenge in template matching-based tracking. In this work, we propose a novel comprehensive framework with multi-frame distractor suppression for visual object tracking (MFDSTrack), which explicitly models the temporal history of both the target object and potential distractors. Specifically, we utilize a universal target candidate generation module to detect target candidates (both target and distractors), providing a holistic view of the scene. In addition, a temporal and distractor-aware association module is designed to suppress multi-frame distractors by adopting a simple encoder-decoder Transformer architecture. The encoder accepts inputs of target candidates’ history, while the decoder takes current target candidate queries and the output of the encoder as inputs to associate current target candidate queries with historical trajectories. We extensively evaluate our trackers, MFDSTrack-SD, MFDSTrack-OS, MFDSTrack-GRM, and MFDSTrack-LT on the LaSOT, LaSOText, TrackingNet, GOT-10k, UAV123, NFS, and OTB100 benchmark. Extensive experiments show that our methods outperform previous state-of-the-art trackers on seven tracking benchmarks.
- 29 March 2024
- Published by Elsevier in Biosystems Engineering
- Vol. 241, 28-42
Beef cattle abnormal behaviour recognition based on dual-branch frequency channel temporal excitation and aggregation
- 29 March 2024
- Published by Elsevier in Biosystems Engineering
- Vol. 241, 28-42
Beef cattle abnormal behaviour recognition based on dual-branch frequency channel temporal excitation and aggregation
- 1 January 2023
- Published by Inderscience Publishers in International Journal of Technology Management
- Vol. 93 (1/2) , 105-132
Cooperation alliance, technical value, and standards dynamics
- 1 January 2023
- Published by Inderscience Publishers in International Journal of Technology Management
- Vol. 93 (1/2) , 105-132
Cooperation alliance, technical value, and standards dynamics