📊 Showing 4 results | 📏 Metric: Top-1 Accuracy
| Rank | Model | Paper | Top-1 Accuracy | Date | Code |
|---|---|---|---|---|---|
| 1 | BIKE | Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models | 86.20 | 2022-12-31 | 📦 whwu95/Cap4Video 📦 whwu95/text4vis 📦 whwu95/GPT4Vis 📦 whwu95/BIKE 📦 whwu95/ATM |
| 2 | Text4Vis | Revisiting Classifier: Transferring Vision-Language Models for Video Recognition | 84.60 | 2022-07-04 | 📦 whwu95/Cap4Video 📦 whwu95/text4vis 📦 whwu95/GPT4Vis 📦 whwu95/BIKE 📦 whwu95/ATM |
| 3 | ResT | Cross-modal Representation Learning for Zero-shot Action Recognition | 32.50 | 2022-05-03 | - |
| 4 | E2E | Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications | 26.60 | 2020-03-03 | 📦 bbrattoli/ZeroShotVideoClassification |