Egocentric Activity Recognition On Egtea 1
Metrics
Average Accuracy
Mean class accuracy
Results
Performance results of various models on this benchmark
Model Name | Average Accuracy | Mean class accuracy | Paper Title | Repository |
|---|---|---|---|---|
| LaViLa (Finetuned, TimeSformer-L) | 81.75 | 76 | Learning Video Representations from Large Language Models | |
| Min et al. | 69.58 | 62.84 | Integrating Human Gaze into Attention for Egocentric Activity Recognition | |
| GC-TSM | 65.1 | - | Group Contextualization for Video Recognition | |
| Ego-RNN | 60.8 | - | Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition | |
| SAP | 62.7 | - | Symbiotic Attention with Privileged Information for Egocentric Action Recognition | - |
| LSTA | 61.9 | - | LSTA: Long Short-Term Attention for Egocentric Action Recognition |
0 of 6 row(s) selected.