[2005.10356] TAO: A Large-Scale Benchmark for Tracking Any Objectopen searchopen navigation menucontact arXivarXiv Twitter

For many years, multi-object tracking benchmarks have focused on a handful of categories. Motivated primarily by surveillance and self-driving applications, these datasets provide tracks for people, vehicles, and animals, ignoring the vast majority of objects in the world. By contrast, in the related field of object detection, the introduction of large-scale, diverse datasets (e.g., COCO) have fostered significant progress in developing highly robust solutions. To bridge this gap, we introduce a similarly diverse dataset for Tracking Any Object (TAO). It consists of 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average. Importantly, we adopt a bottom-up approach for discovering a large vocabulary of 833 categories, an order of magnitude more than prior tracking benchmarks. To this end, we ask annotators to label objects that move at any point in the video, and give names to them post factum. Our vocabulary is both significantly larger a

1 mentions: @ak92501
Date: 2020/05/23 05:21

Referring Tweets

@ak92501 TAO: A Large-Scale Benchmark for Tracking Any Object pdf: t.co/qBMJ23iYor abs: t.co/RCrZHRhC5y project page: t.co/i8OkGiXUAh t.co/O2D5SP4p6q

Related Entries

Read more [2002.02112] Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Var...
0 users, 1 mentions 2020/02/10 12:54
Read more Abstract | GFLA-web
0 users, 1 mentions 2020/03/03 06:51
Read more [2004.04972] Generating Multilingual Voices Using Speaker Space Translation Based on Bilingual Speak...
0 users, 1 mentions 2020/04/13 15:51
Read more [2004.11714] Residual Energy-Based Models for Text Generationopen searchopen navigation menucontact ...
0 users, 1 mentions 2020/04/27 15:51
Read more GitHub - vyvydkf628/ShadeSketch: Implementation of "Learning to Shadow Hand-drawn Sketches" CVPR 202...
0 users, 1 mentions 2020/05/20 17:21