DiDi dataset

NIAID Data Ecosystem2026-05-02 收录

视觉目标跟踪

干扰物感知

数据链接：

https://zenodo.org/record/14236143 数据链接链接失效反馈

官方服务：

资源简介：

The Distractor Distilled dataset (DiDi) presented in the paper: "A Distractor-Aware Memory for Visual Object Tracking with SAM2" https://arxiv.org/abs/2411.17576

创建时间：

2024-11-28

TNLLT

视觉目标跟踪

视频分析

TNLLT是一个大规模的长时视觉-语言跟踪基准数据集，包含200个视频序列，其中150个用于训练，50个用于测试。数据集由研究人员从视频网站收集，主要涉及电视、电影、游戏、娱乐、纪录片等。研究人员对裁剪的视频进行了细致的矩形框标注，并标注了对象的视觉外观、运动和其他线索的语言描述。这些视频涵盖了与视觉-语言跟踪相关的15个挑战因素。该数据集为视觉-语言跟踪任务的研究提供了一个坚实的基础。

arXiv2025-08-07 更新700

Comparison with state-of-the-art trackers on VOT2018 in terms of EAO, A and R.

视觉目标跟踪

探测器性能评估

Comparison with state-of-the-art trackers on VOT2018 in terms of EAO, A and R.

NIAID Data Ecosystem110

Generated RGBD Tracking Benchmarks (Got10K) 1501-2100

视觉目标跟踪

RGBD数据生成

We convert the existing RGB tracking benchmakrs, eg. Got10K, to RGB+pseudo-Depth tracking benchmarks using DenseDepth or HighResDepth monocular estimation methods. Please visit the Got10K page for the

Zenodo2021-12-22 更新60

DepthTrack Training Set 01 (ICCV2021)

RGB-D跟踪

视觉目标跟踪

DepthTrack training set 01, including 100 RGBD sequences and their groundtruth bounding boxes. If you use it, please cite: @InProceedings{yan2021det, author = {Yan, Song and Yang, Jinyu a

NIAID Data Ecosystem290

IIT dataset

昆虫启发视觉跟踪

视觉目标跟踪

Image sequences and the ground truth file used to compare insect-inspired tracker with the state-of-the-art engineering models.

NIAID Data Ecosystem90