OpenCodePapers

video-classification-on-coin

Action RecognitionVideo Classification
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracy (%)ModelNameReleaseDate
MoTE: Mixture of Task Experts for Multi-Task Video Understanding94.4VideoLLM-MoTE-1B+5E2026-08-25
HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics✓ Link93.5HERMES2024-08-30
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding✓ Link93.2MA-LMM2024-04-08
VETO: Video Efficient Token Optimization for Vision Language Models92.7VETO2026-10-01
Cross-Modal Dual-Causal Learning for Long-Term Action Recognition✓ Link92.28CMDCL (extra data)2025-07-09
Selective Structured State-Spaces for Long-Form Video Understanding90.8S52023-03-25
Learning To Recognize Procedural Activities with Distant Supervision✓ Link90.0D-Sprv.2022-01-26
Efficient Movie Scene Detection using State-Space Transformers✓ Link89.3TranS4mer2022-12-29
Long Movie Clip Classification with State-Space Video Models✓ Link88.4ViS4mer2022-04-04
Temporal Segment Networks for Action Recognition in Videos✓ Link73.4TSN2017-05-08