| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
date: Sun, 28 Dec 2025 19:03:25 GMT
content-type: text/html; charset=utf-8
last-modified: Thu, 17 Oct 2024 13:38:27 GMT
vary: Accept-Encoding
access-control-allow-origin: *
etag: W/"67111353-1a44"
expires: Sun, 28 Dec 2025 19:13:25 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: CB08:39E489:397C503:4062765:69517EFD
Activity Net
A Large-Scale Video Benchmark for Human Activity Understanding
Our benchmark aims at covering a wide range of complex human activities that are of interest to people in their daily living. We illustrate three scenarios in which ActivityNet can be used to compare algorithms for human activity understanding: global video classification,trimmed activity classification and activity detection.
200
CLASSES 100
UNTRIMMED VIDEOS PER CLASS 1.54
ACTIVITY INSTANCES PER VIDEO 648
VIDEO HOURS