SOTAVerified|Agents Browse Leaderboard About

Video Understanding

A crucial task of Video Understanding is to recognise and localise (in space and time) different actions or events appearing in the video.

Source: Action Detection from a Robot-Car Perspective

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 451–460 of 1149 papers

Title	Date	Tasks	Status	Hype	Score
Video action detection by learning graph-based spatio-temporal interactions	Dec 9, 2019	Action DetectionAction Localization	CodeCode Available	0	5
SoccerNet 2024 Challenges Results	Sep 16, 2024	Action SpottingDense Video Captioning	CodeCode Available	0	5
4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding	Mar 22, 2025	BenchmarkingObject	CodeCode Available	0	5
Snippet-Aware Transformer With Multiple Action Elements for Skeleton-Based Action Segmentation	May 6, 2024	Action SegmentationSkeleton Based Action Segmentation	CodeCode Available	0	5
SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding	May 22, 2025	Action ClassificationAutomatic Speech Recognition	CodeCode Available	0	5
Tiny Video Networks	Oct 15, 2019	CPUGPU	CodeCode Available	0	5
SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding	Apr 30, 2025	Video Understanding	CodeCode Available	0	5
ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding	Oct 1, 2024	Contrastive LearningHallucination	CodeCode Available	0	5
Creative Flow+ Dataset	Jun 1, 2019	3D Character Animation From A Single PhotoDepth Estimation	CodeCode Available	0	5
Screencast Tutorial Video Understanding	Jun 1, 2020	object-detectionObject Detection	CodeCode Available	0	5

Show:10 25 50

← PrevPage 46 of 115Next →

No leaderboard results yet.