Papers › HIPTrack: Visual Tracking with Historical Prompts

HIPTrack: Visual Tracking with Historical Prompts

3 Nov 2023CVPR 2024 1arXiv:2311.02072archive 2025-07-28

Wenrui Cai, Qingjie Liu, Yunhong Wang

Trackers that follow Siamese paradigm utilize similarity matching between template and search region features for tracking. Many methods have been explored to enhance tracking performance by incorporating tracking history to better handle scenarios involving target appearance variations such as deformation and occlusion. However, the utilization of historical information in existing methods is insufficient and incomprehensive, which typically requires repetitive training and introduces a large amount of computation. In this paper, we show that by providing a tracker that follows Siamese paradigm with precise and updated historical information, a significant performance improvement can be achieved with completely unchanged parameters. Based on this, we propose a historical prompt network that uses refined historical foreground masks and historical visual features of the target to provide comprehensive and precise prompts for the tracker. We build a novel tracker called HIPTrack based on the historical prompt network, which achieves considerable performance improvements without the need to retrain the entire model. We conduct experiments on seven datasets and experimental results demonstrate that our method surpasses the current state-of-the-art trackers on LaSOT, LaSOText, GOT-10k and NfS. Furthermore, the historical prompt network can seamlessly integrate as a plug-and-play module into existing trackers, providing performance enhancements. The source code is available at https://github.com/WenRuiCai/HIPTrack.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

wenruicai/hiptrack officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

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

Visual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Object Tracking GOT-10k HIPTrack Average Overlap 77.4 #14 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k HIPTrack Success Rate 0.5 88.0 #14 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k HIPTrack Success Rate 0.75 74.5 #14 of 42 Archive leaderboard report
Visual Object Tracking LaSOT HIPTrack AUC 72.7 #17 of 46 Archive leaderboard report
Visual Object Tracking LaSOT HIPTrack Normalized Precision 82.9 #17 of 46 Archive leaderboard report
Visual Object Tracking LaSOT HIPTrack Precision 79.5 #17 of 46 Archive leaderboard report
Visual Object Tracking LaSOT-ext HIPTrack AUC 53.0 #11 of 18 Archive leaderboard report
Visual Object Tracking LaSOT-ext HIPTrack Normalized Precision 64.3 #11 of 18 Archive leaderboard report
Visual Object Tracking LaSOT-ext HIPTrack Precision 60.6 #11 of 18 Archive leaderboard report
Visual Object Tracking NeedForSpeed HIPTrack AUC 0.681 #4 of 10 Archive leaderboard report
Visual Object Tracking OTB-2015 HIPTrack AUC 0.71 #7 of 18 Archive leaderboard report
Visual Object Tracking TrackingNet HIPTrack Accuracy 84.5 #17 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet HIPTrack Normalized Precision 89.1 #17 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet HIPTrack Precision 83.8 #17 of 40 Archive leaderboard report
Visual Object Tracking UAV123 HIPTrack AUC 0.705 #9 of 16 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