Video Question Answering on Next-QA v1 (test)
73.8Overall AccSeViLA
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SeViLAzero-shot=false, video-level training=true, parameters=4B2024.03 | 73.8 | 74.2 | 69.4 | 81.3 | |
| VideoTreezero-shot=true, video-level training=false, parameters=1.7T2024.03 | 73.5 | 75.2 | 67 | 81.3 | |
| LVNet + MVUzero-shot=true, video-level training=false, parameters=1.8T2024.03 | 73.3 | 75.2 | 66.8 | 81.3 | |
| LVNetzero-shot=true, video-level training=false, parameters=1.8T2024.03 | 72.9 | 75 | 65.5 | 81.5 | |
| Vamoszero-shot=false, video-level training=true, parameters=7B2024.03 | 72.5 | 72.6 | 69.6 | 78 | |
| LLama-VQA-7Bzero-shot=false, video-level training=true, parameters=7B2024.03 | 72 | 72.7 | 69.2 | 75.8 | |
| VideoAgentzero-shot=true, video-level training=false, parameters=1.7T2024.03 | 71.3 | 72.7 | 64.5 | 81.1 | |
| BLIP-2zero-shot=false, video-level training=true, parameters=4B2024.03 | 70.1 | 70.1 | 65.2 | 80.1 | |
| MoreVQAzero-shot=true, video-level training=false, parameters=1.7T2024.03 | 69.2 | 70.2 | 64.6 | — | |
| LLoVi (GPT-4)zero-shot=true, video-level training=false, parameters=1.8T2024.03 | 67.7 | 69.5 | 61 | 75.6 | |
| MC-ViT-Lzero-shot=false, video-level training=true, parameters=424M2024.03 | 65 | — | — | — | |
| SeViLAzero-shot=true, video-level training=false, parameters=4B2024.03 | 63.6 | 61.3 | 61.5 | 75.6 | |
| InternVideozero-shot=false, video-level training=true, parameters=478M2024.03 | 63.2 | 62.5 | 58.5 | 75.8 | |
| HiTeAzero-shot=false, video-level training=true, parameters=297M2024.03 | 63.1 | 62.4 | 58.3 | 75.6 | |
| SeViTzero-shot=false, video-level training=true, parameters=215M2024.03 | 60.6 | — | — | — | |
| CoVGTzero-shot=false, video-level training=true, parameters=149M2024.03 | 60 | 58.8 | 57.4 | 69.3 | |
| ViperGPTzero-shot=true, video-level training=false, parameters=175B2024.03 | 60 | — | — | — | |
| SF-VLM + MVUzero-shot=true, video-level training=false, parameters=13B2024.03 | 55.4 | 55.7 | 48.2 | 64.2 | |
| LLoVizero-shot=true, video-level training=false, parameters=13B2024.03 | 54.3 | 55.6 | 47.9 | 63.2 | |
| VFCzero-shot=true, video-level training=false, parameters=164M2024.03 | 51.5 | 45.4 | 51.6 | 64.1 | |
| InternVideozero-shot=true, video-level training=false, parameters=478M2024.03 | 49.1 | 43.4 | 48 | 65.1 | |
| Just-Askzero-shot=true, video-level training=false, parameters=66M2024.03 | 38.4 | 31.8 | 30.4 | 36 | |
| CaKE-LMzero-shot=true, video-level training=false, parameters=2.7B2024.03 | 34.9 | 35.7 | 35.3 | 36.8 | |
| Random Selection2024.03 | 20 | 20 | 20 | 20 |