SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 276–300 of 1149 papers

TitleStatusHype
HuMoCon: Concept Discovery for Human Motion Understanding—0
Adapting Pre-trained 3D Models for Point Cloud Video Understanding via Cross-frame Spatio-temporal Perception—0
AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction—0
Efficient Motion-Aware Video MLLM—0
Language-Guided Audio-Visual Learning for Long-Term Sports AssessmentCode1
VEU-Bench: Towards Comprehensive Understanding of Video Editing—0
Flexible Frame Selection for Efficient Video Reasoning—0
Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models—0
OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models—0
Online Video Understanding: OVBench and VideoChat-OnlineCode2
CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval—0
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLMCode3
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding—0
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language ModelsCode2
Detection-Fusion for Knowledge Graph Extraction from VideosCode0
ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video UnderstandingCode1
MVTamperBench: Evaluating Robustness of Vision-Language Models—0
Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries—0
HumanVBench: Exploring Human-Centric Video Understanding Capabilities of MLLMs with Synthetic Benchmark Data—0
Video Domain Incremental Learning for Human Action Recognition in Home Environments—0
FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story VideosCode0
PruneVid: Visual Token Pruning for Efficient Video Large Language ModelsCode2
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal GroundingCode1
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language ModelsCode2
Do Language Models Understand Time?Code1
Show:102550
← PrevPage 12 of 46Next →

No leaderboard results yet.