Papers › Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and...

Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation

25 Aug 2023ICCV 2023 1arXiv:2308.13266archive 2025-07-28

Yuanyou Xu, Zongxin Yang, Yi Yang

Tracking any given object(s) spatially and temporally is a common purpose in Visual Object Tracking (VOT) and Video Object Segmentation (VOS). Joint tracking and segmentation have been attempted in some studies but they often lack full compatibility of both box and mask in initialization and prediction, and mainly focus on single-object scenarios. To address these limitations, this paper proposes a Multi-object Mask-box Integrated framework for unified Tracking and Segmentation, dubbed MITS. Firstly, the unified identification module is proposed to support both box and mask reference for initialization, where detailed object information is inferred from boxes or directly retained from masks. Additionally, a novel pinpoint box predictor is proposed for accurate multi-object box prediction, facilitating target-oriented representation learning. All target objects are processed simultaneously from encoding to propagation and decoding, as a unified pipeline for VOT and VOS. Experimental results show MITS achieves state-of-the-art performance on both VOT and VOS benchmarks. Notably, MITS surpasses the best prior VOT competitor by around 6% on the GOT-10k test set, and significantly improves the performance of box initialization on VOS benchmarks. The code is available at https://github.com/yoxu515/MITS.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

yoxu515/mits officialmentioned in papermentioned on GitHubpytorchBSD-3-Clause 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

ObjectObject TrackingRepresentation LearningSegmentationSemantic SegmentationVideo Object SegmentationVideo Semantic SegmentationVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Object Tracking GOT-10k MITS Average Overlap 80.4 #4 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MITS Success Rate 0.5 89.8 #4 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k MITS Success Rate 0.75 75.8 #4 of 42 Archive leaderboard report
Visual Object Tracking LaSOT MITS AUC 72.0 #22 of 46 Archive leaderboard report
Visual Object Tracking LaSOT MITS Normalized Precision 80.1 #22 of 46 Archive leaderboard report
Visual Object Tracking LaSOT MITS Precision 78.5 #22 of 46 Archive leaderboard report
Visual Object Tracking TrackingNet MITS Accuracy 83.4 #22 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet MITS Normalized Precision 88.9 #22 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet MITS Precision 84.6 #22 of 40 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.

Methods

FocusVOS

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