FETrack: Feature-Enhanced Transformer Network for Visual Object Tracking
Source abstract
Abstract
Visual object tracking is a fundamental task in computer vision, with applications ranging from video surveillance to autonomous driving. Despite recent advances in transformer-based one-stream trackers, unrestricted feature interactions between the template and the search region often introduce background noise into the template, degrading the tracking performance. To address this issue, we propose FETrack, a feature-enhanced transformer-based network for visual object tracking. Specifically, we incorporate an independent template stream in the encoder of the one-stream tracker to acquire the high-quality template features while suppressing the harmful background noise effectively. Then, we employ a sequence-learning-based causal transformer in the decoder to generate the bounding box autoregressively, simplifying the prediction head network. Further, we present a dynamic threshold-based online template-updating strategy and a template-filtering approach to boost tracking robustness and reduce redundant computations. Extensive experiments demonstrate that our FETrack achieves a superior performance over state-of-the-art trackers. Specifically, the proposed FETrack achieves a 75.1% AO on GOT-10k, 81.2% AUC on LaSOT, and 89.3% Pnorm on TrackingNet.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Fire Detection and Safety Systems · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Engineering, Huaqiao University, Quanzhou 362021, China
Quanzhou Digital Institute, Quanzhou 362021, China
Funding
National Key R&D Program of China · National Natural Science Foundation of China · Fundamental Research Funds for the Central Universities · Collaborative Innovation Platform Project of Fujian Province · Natural Science Foundation of Fujian Province · Key Project of Quanzhou Science and Technology Plan · Key Science and Technology Project of Xiamen City
References (45)
Show source-provided references
1. Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook
2. Choubisa, M., Kumar, V., Kumar, M., and Khanna, S. (2023, January 7–8). Object Tracking in Intelligent Video Surveillance System Based on Artificial System. Proceedings of the 2023 International Conference on Computational Intelligence, Communication Technology and Networking (CICTN), Ghaziabad, India.10.1109/CICTN57981.2023.10140727 ↗
3. Barbu, T., Bejinariu, S.I., and Luca, R. (2024, January 27–28). Transfer Learning-Based Framework for Automatic Vehicle Detection, Recognition and Tracking. Proceedings of the 2024 International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Iasi, Romania.10.1109/ECAI61503.2024.10607565 ↗
4. Cao, X. (2023, January 29–31). Eye Tracking in Human-computer Interaction Recognition. Proceedings of the 2023 IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE), Jinzhou, China.10.1109/ICSECE58870.2023.10263468 ↗
5. The Use of Machine Learning in Eye Tracking Studies in Medical Imaging: A Review10.1109/JBHI.2024.3371893 ↗
6. Transformers in Single Object Tracking: An Experimental Survey10.1109/ACCESS.2023.3298440 ↗
7. Deng, A., Liu, J., Chen, Q., Wang, X., and Zuo, Y. (2022). Visual Tracking with FPN Based on Transformer and Response Map Enhancement. Appl. Sci., 12.10.3390/app12136551 ↗
8. Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. arXiv.10.3115/v1/D14-1179 ↗
9. Chen, B., Li, P., Bai, L., Qiao, L., Shen, Q., Li, B., Gan, W., Wu, W., and Ouyang, W. (2022, January 23–27). Backbone Is All Your Need: A Simplified Architecture for Visual Object Tracking. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-20047-2_22 ↗
10. Ye, B., Chang, H., Ma, B., Shan, S., and Chen, X. (2022, January 23–27). Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-20047-2_20 ↗
11. He, K., Zhang, C., Xie, S., Li, Z., and Wang, Z. (2023, January 7–14). Target-aware tracking with long-term context attention. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.
12. Xie, F., Chu, L., Li, J., Lu, Y., and Ma, C. (2023, January 18–22). VideoTrack: Learning to Track Objects via Video Transformer. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.02186 ↗
13. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16 × 16 words: Transformers for image recognition at scale. arXiv.
14. Gao, S., Zhou, C., and Zhang, J. (2023, January 18–22). Generalized relation modeling for transformer tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.01792 ↗
15. Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., and Torr, P.H. (15–16, January 8–10). Fully-convolutional siamese networks for object tracking. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.
16. Choi, J. (2023). Target-Aware Feature Bottleneck for Real-Time Visual Tracking. Appl. Sci., 13.10.3390/app131810198 ↗
17. GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild10.1109/TPAMI.2019.2957464 ↗
18. Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., and Ling, H. (2019, January 15–20). LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00552 ↗
19. Muller, M., Bibi, A., Giancola, S., Alsubaihi, S., and Ghanem, B. (2018, January 8–14). Trackingnet: A Large-Scale Dataset and Benchmark for Object Tracking in the wild. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01246-5_19 ↗
20. LaSOT: A High-quality Large-scale Single Object Tracking Benchmark10.1007/s11263-020-01387-y ↗
21. Object Tracking Benchmark10.1109/TPAMI.2014.2388226 ↗
22. Kiani Galoogahi, H., Fagg, A., Huang, C., Ramanan, D., and Lucey, S. (2017, January 22–29). Need for Speed: A Benchmark for Higher Frame Rate Object Tracking. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.128 ↗
23. Zhang, Z., Peng, H., Fu, J., Li, B., and Hu, W. (2020, January 23–28). Ocean: Object-aware anchor-free tracking. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58589-1_46 ↗
24. Xu, Z., Huang, D., Huang, X., Song, J., and Liu, H. (2024). DLUT: Decoupled Learning-Based Unsupervised Tracker. Sensors, 24.10.3390/s24010083 ↗
25. Attention is all you need
26. Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., and Lu, H. (2021, January 19–25). Transformer Tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual.10.1109/CVPR46437.2021.00803 ↗
27. Cui, Y., Jiang, C., Wang, L., and Wu, G. (2022, January 19–24). MixFormer: End-to-End Tracking with Iterative Mixed Attention. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Orleans, LA, USA.10.1109/CVPR52688.2022.01324 ↗
28. Gao, S., Zhou, C., Ma, C., Wang, X., and Yuan, J. (2022, January 23–27). AiATrack: Attention in Attention for Transformer Visual Tracking. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-20047-2_9 ↗
29. Ma, Z. (2024, January 22–24). Hybrid Transformer-CNN Feature Enhancement Network for Visual Object Tracking. Proceedings of the 2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT), Nanjing, China.10.1109/AINIT61980.2024.10581634 ↗
30. Xie, F., Wang, C., Wang, G., Yang, W., and Zeng, W. (2021, January 11–17). Learning Tracking Representations via Dual-Branch Fully Transformer Networks. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, BC, Canada.10.1109/ICCVW54120.2021.00303 ↗
31. Lan, J.P., Cheng, Z.Q., He, J.Y., Li, C., Luo, B., Bao, X., Xiang, W., Geng, Y., and Xie, X. (2023, January 4–10). Procontext: Exploring Progressive Context Transformer for Tracking. Proceedings of the ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece.10.1109/ICASSP49357.2023.10094971 ↗
32. Kugarajeevan, J., Kokul, T., Ramanan, A., and Fernando, S. (2024). Optimized Information Flow for Transformer Tracking. arXiv.10.1016/j.eswa.2024.125381 ↗
33. Robust Tracking via Fully Exploring Background Prior Knowledge10.1109/TCSVT.2023.3323702 ↗
34. Xie, F., Yang, W., Wang, C., Chu, L., Cao, Y., Ma, C., and Zeng, W. (2024). Correlation-Embedded Transformer Tracking: A Single-Branch Framework. arXiv.10.1109/TPAMI.2024.3448254 ↗
35. Chen, X., Peng, H., Wang, D., Lu, H., and Hu, H. (2023, January 18–22). SeqTrack: Sequence to Sequence Learning for Visual Object Tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.01400 ↗
36. Wei, X., Bai, Y., Zheng, Y., Shi, D., and Gong, Y. (2023, January 18–22). Autoregressive Visual Tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00935 ↗
37. Sequence to Sequence Learning with Neural Networks
38. Chen, T., Saxena, S., Li, L., Fleet, D.J., and Hinton, G. (2021). Pix2seq: A Language Modeling Framework for Object Detection. arXiv.
39. A Unified Sequence Interface for Vision Tasks
40. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C.L. (2014, January 6–12). Microsoft coco: Common objects in context. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10602-1_48 ↗
41. Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Kämäräinen, J.K., Danelljan, M., Zajc, L.Č., Lukežič, A., and Drbohlav, O. (2020, January 23–28). The Eighth Visual Object Tracking VOT2020 Challenge Results. Proceedings of the European Conference on Computer Vision, Glasgow, UK.
42. Yan, B., Peng, H., Fu, J., Wang, D., and Lu, H. (2021, January 11–17). Learning Spatio-Temporal Transformer for Visual Tracking. Proceedings of the IEEE/CVF International Conference on Computer Vision, Virtual.10.1109/ICCV48922.2021.01028 ↗
43. Cai, Y., Liu, J., Tang, J., and Wu, G. (2023, January 18–22). Robust Object Modeling for Visual Tracking. Proceedings of the IEEE/CVF International Conference on Computer Vision, Vancouver, BC, Canada.10.1109/ICCV51070.2023.00879 ↗
44. Zhu, J., Chen, X., Diao, H., Li, S., He, J.Y., Li, C., Luo, B., Wang, D., and Lu, H. (2024). Exploring Dynamic Transformer for Efficient Object Tracking. arXiv.
45. Wang, N., Zhou, W., Wang, J., and Li, H. (2021, January 19–25). Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual.10.1109/CVPR46437.2021.00162 ↗