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 11311140 of 1149 papers

TitleStatusHype
TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation0
TIME: Temporal-sensitive Multi-dimensional Instruction Tuning and Benchmarking for Video-LLMs0
Toward a Human-Level Video Understanding Intelligence0
Towards Child-Inclusive Clinical Video Understanding for Autism Spectrum Disorder0
Towards Efficient and Robust Moment Retrieval System: A Unified Framework for Multi-Granularity Models and Temporal Reranking0
Towards Fine-Grained Video Question Answering0
Towards Holistic Language-video Representation: the language model-enhanced MSR-Video to Text Dataset0
Towards Long Video Understanding via Fine-detailed Video Story Generation0
Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition0
Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition0
Show:102550
← PrevPage 114 of 115Next →

No leaderboard results yet.