RTracker: Recoverable Tracking via PN Tree Structured Memory (2403.19242v1)
Abstract: Existing tracking methods mainly focus on learning better target representation or developing more robust prediction models to improve tracking performance. While tracking performance has significantly improved, the target loss issue occurs frequently due to tracking failures, complete occlusion, or out-of-view situations. However, considerably less attention is paid to the self-recovery issue of tracking methods, which is crucial for practical applications. To this end, we propose a recoverable tracking framework, RTracker, that uses a tree-structured memory to dynamically associate a tracker and a detector to enable self-recovery ability. Specifically, we propose a Positive-Negative Tree-structured memory to chronologically store and maintain positive and negative target samples. Upon the PN tree memory, we develop corresponding walking rules for determining the state of the target and define a set of control flows to unite the tracker and the detector in different tracking scenarios. Our core idea is to use the support samples of positive and negative target categories to establish a relative distance-based criterion for a reliable assessment of target loss. The favorable performance in comparison against the state-of-the-art methods on numerous challenging benchmarks demonstrates the effectiveness of the proposed algorithm.
- Fully-convolutional siamese networks for object tracking. In ECCVW, 2016.
- Learning discriminative model prediction for tracking. In ICCV, 2019.
- Efficient visual tracking with exemplar transformers. In WACV, pages 1571–1581, 2023.
- Backbone is all your need: a simplified architecture for visual object tracking. In ECCV. Springer, 2022.
- A simple framework for contrastive learning of visual representations. In ICML, 2020.
- Transformer tracking. In CVPR, 2021.
- Seqtrack: Sequence to sequence learning for visual object tracking. In CVPR, 2023.
- Mixformer: End-to-end tracking with iterative mixed attention, 2023.
- Probabilistic regression for visual tracking. In CVPR, 2020.
- Lasot: A high-quality benchmark for large-scale single object tracking. In CVPR, 2019.
- Lasot: A high-quality large-scale single object tracking benchmark. IJCV, 2021.
- Dreamsim: Learning new dimensions of human visual similarity using synthetic data, 2023.
- Stmtrack: Template-free visual tracking with space-time memory networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13774–13783, 2021.
- Target-aware tracking with long-term context attention. arXiv preprint arXiv:2302.13840, 2023.
- Global instance tracking: Locating target more like humans. IEEE TPAMI, 2022.
- Got-10k: A large high-diversity benchmark for generic object tracking in the wild. IEEE TPAMI, 2019.
- Tracking-learning-detection. IEEE TPAMI, 2012.
- Tracking by sampling trackers. In ICCV, 2011.
- Siamrpn++: Evolution of siamese visual tracking with very deep networks. In CVPR, 2018a.
- High performance visual tracking with siamese region proposal network. In CVPR, 2018b.
- Target-aware deep tracking. In CVPR, 2019.
- Citetracker: Correlating image and text for visual tracking. In ICCV, 2023.
- Swintrack: A simple and strong baseline for transformer tracking. In NeurIPS, 2022.
- Robust visual tracking using local sparse appearance model and k-selection. In PAMI, 2012.
- Long-term correlation tracking. In ICCV, 2015.
- Learning target candidate association to keep track of what not to track. In ICCV, 2021.
- Clustering of static-adaptive correspondences for deformable object tracking. In CVPR, 2015.
- Crest: Convolutional residual learning for visual tracking. In ICCV, pages 2574–2583, 2017.
- Fast template matching and update for video object tracking and segmentation. In CVPR, 2020.
- Siam r-cnn: Visual tracking by re-detection. In CVPR, 2020.
- Transformer meets tracker: Exploiting temporal context for robust visual tracking. In CVPR, 2021a.
- Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark. In CVPR, 2021b.
- Autoregressive visual tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9697–9706, 2023.
- Dropmae: Masked autoencoders with spatial-attention dropout for tracking tasks. In CVPR, 2023.
- Online object tracking: A benchmark. In CVPR, 2013.
- Integrating boxes and masks: A multi-object framework for unified visual tracking and segmentation. arXiv preprint arXiv:2308.13266, 2023.
- ‘skimming-perusal’ tracking: A framework for real-time and robust long-term tracking. In IEEE International Conference on Computer Vision (ICCV), 2019.
- Learning spatio-temporal transformer for visual tracking. In ICCV, 2021.
- Universal instance perception as object discovery and retrieval. In CVPR, 2023.
- Learning dynamic memory networks for object tracking. In ECCV, 2018.
- Joint feature learning and relation modeling for tracking: A one-stream framework. In ECCV. Springer, 2022.
- Ocean: Object-aware anchor-free tracking. In ECCV, 2020.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.