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 851–875 of 1149 papers

TitleStatusHype
STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition—0
EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding—0
PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval—0
Self-Supervised Object Detection from Egocentric Videos—0
Relational Space-Time Query in Long-Form Videos—0
Few-Shot Referring Relationships in VideosCode0
UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding—0
Inverse Compositional Learning for Weakly-supervised Relation Grounding—0
Multimodal High-order Relation Transformer for Scene Boundary Detection—0
Joint Engagement Classification using Video Augmentation Techniques for Multi-person Human-robot Interaction—0
Inductive Attention for Video Action Anticipation—0
Egocentric Video Task Translation—0
Contextual Explainable Video Representation: Human Perception-based UnderstandingCode0
PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data—0
Transition Is a Process: Pair-to-Video Change Detection Networks for Very High Resolution Remote Sensing Images—0
Spatio-Temporal Crop Aggregation for Video Representation Learning—0
Dynamic Appearance: A Video Representation for Action Recognition with Joint Training—0
A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset—0
Masked Autoencoders for Egocentric Video Understanding @ Ego4D Challenge 2022Code0
Exploring State Change Capture of Heterogeneous Backbones @ Ego4D Hands and Objects Challenge 2022—0
Grounded Video Situation Recognition—0
How Would The Viewer Feel? Estimating Wellbeing From Video ScenariosCode0
Self-supervised video pretraining yields robust and more human-aligned visual representations—0
Students taught by multimodal teachers are superior action recognizers—0
Compressed Vision for Efficient Video Understanding—0
Show:102550
← PrevPage 35 of 46Next →

No leaderboard results yet.