📊 Showing 7 results | 📏 Metric: Accuracy (%)
| Rank | Model | Paper | Accuracy (%) | Date | Code |
|---|---|---|---|---|---|
| 1 | HERMES | HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics | 93.50 | 2024-08-30 | 📦 joslefaure/HERMES |
| 2 | MA-LMM | MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding | 93.20 | 2024-04-08 | 📦 boheumd/MA-LMM |
| 3 | S5 | Selective Structured State-Spaces for Long-Form Video Understanding | 90.80 | 2023-03-25 | - |
| 4 | D-Sprv. | Learning To Recognize Procedural Activities with Distant Supervision | 90.00 | 2022-01-26 | 📦 facebookresearch/video-distant-supervision |
| 5 | TranS4mer | Efficient Movie Scene Detection using State-Space Transformers | 89.30 | 2022-12-29 | 📦 md-mohaiminul/trans4mer |
| 6 | ViS4mer | Long Movie Clip Classification with State-Space Video Models | 88.40 | 2022-04-04 | 📦 md-mohaiminul/ViS4mer |
| 7 | TSN | Temporal Segment Networks for Action Recognition in Videos | 73.40 | 2017-05-08 | 📦 open-mmlab/mmaction2 📦 open-mmlab/mmaction 📦 PaddlePaddle/PaddleVideo |