Papers › Ocean: Object-aware Anchor-free Tracking
Ocean: Object-aware Anchor-free Tracking
Zhipeng Zhang, Houwen Peng, Jianlong Fu, Bing Li, Weiming Hu
Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based methods is only trained on the positive anchor boxes (i.e., IoU ≥0.6). This mechanism makes it difficult to refine the anchors whose overlap with the target objects are small. In this paper, we propose a novel object-aware anchor-free network to address this issue. First, instead of refining the reference anchor boxes, we directly predict the position and scale of target objects in an anchor-free fashion. Since each pixel in groundtruth boxes is well trained, the tracker is capable of rectifying inexact predictions of target objects during inference. Second, we introduce a feature alignment module to learn an object-aware feature from predicted bounding boxes. The object-aware feature can further contribute to the classification of target objects and background. Moreover, we present a novel tracking framework based on the anchor-free model. The experiments show that our anchor-free tracker achieves state-of-the-art performance on five benchmarks, including VOT-2018, VOT-2019, OTB-100, GOT-10k and LaSOT. The source code is available at https://github.com/researchmm/TracKit.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video Object Tracking | NT-VOT211 | Ocean | AUC | 32.86 | #26 of 43 | Archive leaderboard | report |
| Video Object Tracking | NT-VOT211 | Ocean | Precision | 46.72 | #26 of 43 | Archive leaderboard | report |
| Visual Object Tracking | GOT-10k | Ocean | Average Overlap | 61.1 | #39 of 42 | Archive leaderboard | report |
| Visual Object Tracking | GOT-10k | Ocean | Success Rate 0.5 | 72.1 | #39 of 42 | Archive leaderboard | report |
| Visual Object Tracking | VOT2018 | Ocean | Expected Average Overlap (EAO) | 0.467 | #2 of 2 | Archive leaderboard | report |
| Visual Object Tracking | VOT2019 | Ocean | Expected Average Overlap (EAO) | 0.327 | #2 of 3 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections