VastTrack：海量类别视觉目标跟踪
VastTrack: Vast Category Visual Object Tracking
AI总结：
本文提出包含2115类、50610个序列的大规模视觉跟踪基准VastTrack，含边界框与语言标注，评估25个跟踪器发现通用跟踪性能仍待提升，数据集将开源。
摘要：
本文提出了一个名为VastTrack的新型基准数据集，旨在通过涵盖丰富的类别和视频，推动更通用的视觉跟踪技术发展。VastTrack具备多项突出特性：（1）海量目标类别。具体而言，它覆盖了2115个类别的目标对象，大幅超越了现有主流基准的目标类别数量（例如GOT-10k有563个类别，LaSOT有70个类别）。凭借如此海量的目标类别，我们有望学习到更通用的目标跟踪能力。（2）更大规模。与现有基准相比，VastTrack提供了50610个序列，共420万帧，是目前视频数量最多的基准数据集，因此能够在深度学习时代助力训练性能更强的视觉跟踪器。（3）丰富标注。除了常规的边界框标注外，VastTrack还为视频提供了语言描述。VastTrack的丰富标注可支撑纯视觉跟踪与视觉-语言跟踪两类方向的研究。为确保标注精准，所有视频均经过人工多轮仔细检查与优化标注。为了解现有跟踪器的性能，并为未来的对比研究提供基线，我们对25个具有代表性的跟踪器进行了全面评估。结果不出所料，由于现有跟踪器缺乏海量类别与多样场景视频的训练支撑，其在VastTrack上的性能较在当前数据集上的表现出现显著下降，提升通用跟踪能力仍需更多研究投入。我们的VastTrack数据集及所有评估结果将公开发布于https://github.com/HengLan/VastTrack。
英文摘要：
In this paper, we introduce a novel benchmark, dubbed VastTrack, towards facilitating the development of more general visual tracking via encompassing abundant classes and videos. VastTrack possesses several attractive properties: (1) Vast Object Category. In particular, it covers target objects from 2,115 classes, largely surpassing object categories of existing popular benchmarks (e.g., GOT-10k with 563 classes and LaSOT with 70 categories). With such vast object classes, we expect to learn more general object tracking. (2) Larger scale. Compared with current benchmarks, VastTrack offers 50,610 sequences with 4.2 million frames, which makes it to date the largest benchmark regarding the number of videos, and thus could benefit training even more powerful visual trackers in the deep learning era. (3) Rich Annotation. Besides conventional bounding box annotations, VastTrack also provides linguistic descriptions for the videos. The rich annotations of VastTrack enables development of both the vision-only and the vision-language tracking. To ensure precise annotation, all videos are manually labeled with multiple rounds of careful inspection and refinement. To understand performance of existing trackers and to provide baselines for future comparison, we extensively assess 25 representative trackers. The results, not surprisingly, show significant drops compared to those on current datasets due to lack of abundant categories and videos from diverse scenarios for training, and more efforts are required to improve general tracking. Our VastTrack and all the evaluation results will be made publicly available https://github.com/HengLan/VastTrack.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
