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 251–275 of 1149 papers

TitleStatusHype
HFGCN:Hypergraph Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition—0
AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual SegmentationCode1
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks—0
Facial Dynamics in Video: Instruction Tuning for Improved Facial Expression Perception and Contextual AwarenessCode1
Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video UnderstandingCode4
MECD+: Unlocking Event-Level Causal Graph Discovery for Video ReasoningCode1
Video Quality Assessment for Online Processing: From Spatial to Temporal Sampling—0
VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video CaptioningCode1
X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding—0
Zero-shot Shark Tracking and Biometrics from Aerial Imagery—0
From My View to Yours: Ego-Augmented Learning in Large Vision Language Models for Understanding Exocentric Daily Living ActivitiesCode1
Valley2: Exploring Multimodal Models with Scalable Vision-Language DesignCode3
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?Code2
LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding—0
LongViTU: Instruction Tuning for Long-Form Video Understanding—0
Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs—0
H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving—0
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models—0
HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video UnderstandingCode0
Unifying Specialized Visual Encoders for Video Language ModelsCode1
Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space ModelsCode1
Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs—0
HuMoCon: Concept Discovery for Human Motion Understanding—0
Video Language Model Pretraining with Spatio-temporal Masking—0
HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding—0
Show:102550
← PrevPage 11 of 46Next →

No leaderboard results yet.