# \[DATASET\] WebUOT-1M: Advancing Deep Underwater Object Tracking

**URL:** <https://community.ultralytics.com/t/dataset-webuot-1m-advancing-deep-underwater-object-tracking/803>\
**Category:** Research\
**Tags:** discussion, publication, dataset\
**Created:** [February 27, 2025, 12:49pm UTC](https://community.ultralytics.com/t/dataset-webuot-1m-advancing-deep-underwater-object-tracking/803 "2025-02-27T12:49:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![BurhanQ](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/burhanq/32/7_2.png) [@BurhanQ](https://community.ultralytics.com/u/BurhanQ)\
**Post date:** [February 27, 2025, 12:49pm UTC](https://community.ultralytics.com/t/dataset-webuot-1m-advancing-deep-underwater-object-tracking/803/1 "2025-02-27T12:49:26Z")

</div>

> **[WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale...](https://arxiv.org/abs/2405.19818)**
>
> Underwater object tracking (UOT) is a foundational task for identifying and tracing submerged entities in underwater video sequences. However, current UOT datasets suffer from limitations in scale, diversity of target categories and scenarios...

If you want to check out a smaller sample of the dataset, check out this [toy dataset](https://huggingface.co/datasets/Voxel51/WebUOT-238-Test) put together by our friends at Voxel51!