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 401–450 of 1149 papers

TitleStatusHype
From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video UnderstandingCode1
EAGLE: Egocentric AGgregated Language-video Engine—0
LLM4Brain: Training a Large Language Model for Brain Video Understanding—0
E.T. Bench: Towards Open-Ended Event-Level Video-Language UnderstandingCode2
Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP—0
Video-XL: Extra-Long Vision Language Model for Hour-Scale Video UnderstandingCode4
Towards Child-Inclusive Clinical Video Understanding for Autism Spectrum Disorder—0
First Place Solution to the Multiple-choice Video QA Track of The Second Perception Test Challenge—0
Interpretable Action Recognition on Hard to Classify Actions—0
AMEGO: Active Memory from long EGOcentric videos—0
SoccerNet 2024 Challenges ResultsCode0
HAVANA: Hierarchical stochastic neighbor embedding for Accelerated Video ANnotAtions—0
Enhancing Long Video Understanding via Hierarchical Event-Based Memory—0
VidLPRO: A Video-Language Pre-training Framework for Robotic and Laparoscopic Surgery—0
TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations—0
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid ArchitectureCode3
VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges—0
StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models—0
Streamlining Forest Wildfire Surveillance: AI-Enhanced UAVs Utilizing the FLAME Aerial Video Dataset for Lightweight and Efficient Monitoring—0
DLM-VMTL:A Double Layer Mapper for heterogeneous data video Multi-task prompt learning—0
CogVLM2: Visual Language Models for Image and Video UnderstandingCode9
Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input—0
Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long VideosCode2
Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification—0
LMM-VQA: Advancing Video Quality Assessment with Large Multimodal ModelsCode0
LongVILA: Scaling Long-Context Visual Language Models for Long Videos—0
Flatten: Video Action Recognition is an Image Classification task—0
Disentangle and denoise: Tackling context misalignment for video moment retrieval—0
HAT: History-Augmented Anchor Transformer for Online Temporal Action LocalizationCode1
Spherical World-Locking for Audio-Visual Localization in Egocentric Videos—0
VideoQA in the Era of LLMs: An Empirical StudyCode0
LLaVA-OneVision: Easy Visual Task TransferCode0
FE-Adapter: Adapting Image-based Emotion Classifiers to Videos—0
COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language BenchmarkCode1
Multimodal Fusion and Coherence Modeling for Video Topic Segmentation—0
Segment Anything for Videos: A Systematic SurveyCode5
Learning Video Context as Interleaved Multimodal SequencesCode1
Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter—0
Ego-VPA: Egocentric Video Understanding with Parameter-efficient Adaptation—0
Wolf: Captioning Everything with a World Summarization Framework—0
Harnessing Temporal Causality for Advanced Temporal Action DetectionCode3
EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video RetrievalCode1
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language UnderstandingCode2
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language ModelsCode3
Audio-visual training for improved grounding in video-text LLMs—0
Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data—0
Goldfish: Vision-Language Understanding of Arbitrarily Long VideosCode4
Open Vocabulary Multi-Label Video Classification—0
Hypergraph Multi-modal Large Language Model: Exploiting EEG and Eye-tracking Modalities to Evaluate Heterogeneous Responses for Video UnderstandingCode1
VideoMamba: Spatio-Temporal Selective State Space ModelCode1
Show:102550
← PrevPage 9 of 23Next →

No leaderboard results yet.