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 551–600 of 1149 papers

TitleStatusHype
A Unified Framework for Human-centric Point Cloud Video Understanding—0
Towards Multimodal Video Paragraph Captioning Models Robust to Missing ModalityCode0
OmniVid: A Generative Framework for Universal Video UnderstandingCode2
Understanding Long Videos with Multimodal Language ModelsCode2
Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding—0
InternVideo2: Scaling Foundation Models for Multimodal Video UnderstandingCode7
VURF: A General-purpose Reasoning and Self-refinement Framework for Video UnderstandingCode0
Language Repository for Long Video UnderstandingCode1
Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object SegmentationCode1
VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding—0
Towards Neuro-Symbolic Video UnderstandingCode1
VideoAgent: Long-form Video Understanding with Large Language Model as AgentCode2
Video Mamba Suite: State Space Model as a Versatile Alternative for Video UnderstandingCode3
Don't Judge by the Look: Towards Motion Coherent Video RepresentationCode0
Action Reimagined: Text-to-Pose Video Editing for Dynamic Human Actions—0
VideoMamba: State Space Model for Efficient Video UnderstandingCode5
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language ModelsCode4
Beyond MOT: Semantic Multi-Object TrackingCode2
A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives—0
MovieLLM: Enhancing Long Video Understanding with AI-Generated Movies—0
Abductive Ego-View Accident Video Understanding for Safe Driving Perception—0
TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning—0
LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs—0
Slot-VLM: SlowFast Slots for Video-Language Modeling—0
Video ReCap: Recursive Captioning of Hour-Long VideosCode3
VideoPrism: A Foundational Visual Encoder for Video Understanding—0
Dynamics Based Neural Encoding with Inter-Intra Region Connectivity—0
Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly VideosCode0
World Model on Million-Length Video And Language With Blockwise RingAttentionCode9
Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learningCode2
Memory Consolidation Enables Long-Context Video Understanding—0
Spatio-temporal Prompting Network for Robust Video Feature ExtractionCode1
BehAVE: Behaviour Alignment of Video Game EncodingsCode1
A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming—0
Multi-granularity Correspondence Learning from Long-term Noisy VideosCode2
Cutup and Detect: Human Fall Detection on Cutup Untrimmed Videos Using a Large Foundational Video Understanding Model—0
Exploring Missing Modality in Multimodal Egocentric Datasets—0
Learning to Visually Connect Actions and their Effects—0
CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding—0
Multi-scale 2D Temporal Map Diffusion Models for Natural Language Video Localization—0
Dr^2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient FinetuningCode0
Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action—0
Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning—0
Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning—0
Compositional Video Understanding with Spatiotemporal Structure-based TransformersCode1
VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding—0
Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding—0
Video Understanding with Large Language Models: A SurveyCode4
A Simple LLM Framework for Long-Range Video Question-AnsweringCode1
Open-Vocabulary Video Relation ExtractionCode1
Show:102550
← PrevPage 12 of 23Next →

No leaderboard results yet.