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 601–650 of 1149 papers

TitleStatusHype
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision—0
Text-Conditioned Resampler For Long Form Video Understanding—0
Learning Object State Changes in Videos: An Open-World Perspective—0
Artificial intelligence optical hardware empowers high-resolution hyperspectral video understanding at 1.2 Tb/s—0
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot VideosCode1
SMILE: Multimodal Dataset for Understanding Laughter in Video with Language ModelsCode1
X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge TransferCode0
How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary InvestigationCode1
Audio-Visual LLM for Video Understanding—0
Grounded Question-Answering in Long Egocentric VideosCode1
Retrieval-based Video Language Model for Efficient Long Video Question Answering—0
MoVQA: A Benchmark of Versatile Question-Answering for Long-Form Movie Understanding—0
Action Scene Graphs for Long-Form Understanding of Egocentric VideosCode1
HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding—0
VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding—0
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video UnderstandingCode2
Zero-Shot Video Question Answering with Procedural Programs—0
DEVIAS: Learning Disentangled Video Representations of Action and SceneCode1
Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation—0
Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding—0
CAST: Cross-Attention in Space and Time for Video Action RecognitionCode1
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person PerspectivesCode2
Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional PropertiesCode1
Panoptic Video Scene Graph GenerationCode1
MVBench: A Comprehensive Multi-modal Video Understanding BenchmarkCode2
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer LearningCode1
GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation—0
Mug-STAN: Adapting Image-Language Pretrained Models for General Video UnderstandingCode1
PG-Video-LLaVA: Pixel Grounding Large Video-Language ModelsCode2
Vamos: Versatile Action Models for Video UnderstandingCode0
SPOT! Revisiting Video-Language Models for Event Understanding—0
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingCode2
ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab—0
Beyond still images: Temporal features and input variance resilience—0
ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection—0
MM-VID: Advancing Video Understanding with GPT-4V(ision)Code1
Videoprompter: an ensemble of foundational models for zero-shot video understanding—0
Query-aware Long Video Localization and Relation Discrimination for Deep Video Understanding—0
A Survey on Video Diffusion ModelsCode4
Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks—0
DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model—0
Telling Stories for Common Sense Zero-Shot Action RecognitionCode0
A Content-Driven Micro-Video Recommendation Dataset at ScaleCode2
BT-Adapter: Video Conversation is Feasible Without Video Instruction TuningCode1
End-to-End Streaming Video Temporal Action Segmentation with Reinforce LearningCode1
M^33D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding—0
Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges—0
Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding—0
Learning Dynamic MRI Reconstruction with Convolutional Network Assisted Reconstruction Swin Transformer—0
Language as the Medium: Multimodal Video Classification through text only—0
Show:102550
← PrevPage 13 of 23Next →

No leaderboard results yet.