Relying on a large amount of data, recent object trackers achieve superior performance. However Siamese-like trackers expose considerable shortcomings in the case of brief occlusion. To address these shortages, the paper proposes a novel pre-frame auxiliary and fusion tracking framework. Within this framework, a retained variable is first introduced to avoid some additional twin branches while retaining the previously obtained deep features of the search frames. Based on such a variable, a pre-frame auxiliary module is constructed to establish the relationship between encoding features and the retained pre-frame information and a decoding fusion module is designed to fuse the generated similarity relationship. Moreover, the Efficient IoU (EIoU) loss is employed to increase the precision of predicted bounding boxes by adding three penalty terms for the differences in the center point, length, and width of the two bounding boxes. Finally, the superiority over state-of-the-art methods is verified by numerous tests on visual tracking benchmarks.
|Title of host publication
|2023 IEEE 10th International Conference on Data Science and Advanced Analytics, DSAA 2023 - Proceedings
|Yannis Manolopoulos, Zhi-Hua Zhou
|Institute of Electrical and Electronics Engineers Inc.
|Number of pages
|Published - 6 Nov 2023
|10th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2023 - Thessaloniki, Greece
Duration: 9 Oct 2023 → 12 Oct 2023
|10th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2023
|9/10/23 → 12/10/23
- Feature Fusion
- Pre-Frame Auxiliary
- Siamese Network
- Similarity Relationship
- Visual Tracking