Learning Target Candidate Association to Keep Track of What Not to Track

By Christoph Mayer, Martin Danelljan, Danda Pani Paudel, Luc Van Gool. IEEE International Conference on Computer Vision, 2021

373 citations recorded by the source corpus.

The presence of objects that are confusingly similar to the tracked target, poses a fundamental challenge in appearance-based visual tracking. Such distractor objects are easily misclassified as the target itself, leading to eventual tracking failure. While most methods strive to suppress distractors through more powerful appearance models, we take an alternative approach.We propose to keep track of distractor objects in order to continue tracking the target. To this end, we introduce a learned association network, allowing us to propagate the identities of all target candidates from frame-to-frame. To tackle the problem of lacking ground-truth correspondences between distractor objects in visual tracking, we propose a training strategy that combines partial annotations with self-supervision. We conduct comprehensive experimental validation and analysis of our approach on several challenging datasets. Our tracker sets a new state-of-the-art on six benchmarks, achieving an AUC score of 67.1% on LaSOT [21] and a +5.8% absolute gain on the OxUvA long-term dataset [41]. The code and trained models are available at https://github.com/visionml/pytracking

Subfields: Computer Vision and Pattern Recognition, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/fb058786bbcb2cead98a3ef55b33d2b73b2119fc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Xiaogang Wang
4. Dacheng Tao
5. Haibin Ling
6. Wanli Ouyang
7. Philip H. S. Torr
8. Yi Yang

In Global and Planetary Change

1. Chao Ma
2. Heng Fan
3. Haibin Ling
4. Wanli Ouyang
5. Zhipeng Zhang
6. Houwen Peng
7. Ming-Hsuan Yang

Citations in the corpus

• SwinTrack: A Simple and Strong Baseline for Transformer Tracking (2021, background): “SwinTrack suppresses the SOTA [44] [32] trackers on the challenging long-term dataset LaSOT by 3.”
• Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking (2022, background): “The compared trackers include SiamFC [2](ECCVW16), ATOM [11] (CVPR19), SiamRPN++ [42](CVPR19), DiMP [3](ICCV19), SiamFC++ [42] (AAAI20), Ocean [49](ECCV20), SiamBAN [9](CVPR20), SiamAtt [45] (CVPR 20), TransT [38](CVPR21), TrDiMP [39](CVPR21), KeepTrack [27](ICCV21), STARKS [43](ICCV21), AutoMatch [”
• AiATrack: Attention in Attention for Transformer Visual Tracking (2022, background): “However, in recent years, it has been noted that this benchmark has become highly saturated [53,58,41].”
• Autoregressive Visual Tracking (2023, background): “The present mainstream approaches [10,13,45,61,64] for visual object tracking typically view it as a per-frame template matching problem, neglecting the potential temporal dependencies among the video frames.”
• Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework (2022, neutral): “Previous SOTA tracker KeepTrack [35] designs a complex association network and runs at 18.3 FPS.”