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

Showing 551560 of 1149 papers

TitleStatusHype
Learning Dynamic MRI Reconstruction with Convolutional Network Assisted Reconstruction Swin Transformer0
Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval0
Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering0
Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding0
Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection0
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition0
Dynamic Appearance: A Video Representation for Action Recognition with Joint Training0
Beyond the Camera: Neural Networks in World Coordinates0
LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision0
Large-Scale YouTube-8M Video Understanding with Deep Neural Networks0
Show:102550
← PrevPage 56 of 115Next →

No leaderboard results yet.