Video Question Answering on MSRVTT-MC
97.7AccuracyUMT-L
Evaluation Results
| Method | Links | |
|---|---|---|
| UMT-L#Pairs=17M2023.03 | 97.7 | |
| VIOLETV2# Pretrain videos/images=5M2022.09 | 97.6 | |
| UMT-L#Pairs=25M2023.03 | 97.3 | |
| VINDLU#Pairs=25M2023.03 | 97.1 | |
| UMT-L#Pairs=5M2023.03 | 96.8 | |
| UMT-B#Pairs=17M2023.03 | 96.3 | |
| UMT-B#Pairs=25M2023.03 | 96.3 | |
| UMT-B#Pairs=5M2023.03 | 95.9 | |
| VINDLU#PT=25M2022.12 | 95.5 | |
| VINDLU#PT=5M2022.12 | 95.4 | |
| Tem-adapter2023.08 | 94.3 | |
| Tem-adapter2023.08 | 94.3 | |
| VINDLU#PT=17M2022.12 | 93.8 | |
| Singularity#PT=17M2022.12 | 93.7 | |
| Singularity#Pairs=17M2023.03 | 93.7 | |
| SimVTP2022.12 | 93.6 | |
| ATPNumber of sampled frames (n)=16, embeddings chosen=12022.06 | 93.2 | |
| ATPYear=20222023.08 | 93.2 | |
| ATPYear=20222023.08 | 93.2 | |
| ATPNumber of sampled frames (n)=8, embeddings chosen=12022.06 | 92.5 | |
| All-in-one# Pretrain videos/images=283M2022.09 | 92.3 | |
| VideoCLIP#PT=136M, #Train Frame=9602022.06 | 92.1 | |
| SINGULARITY#PT=17M, #Train Frame=12022.06 | 92.1 | |
| VideoCLIP2022.06 | 92.1 | |
| VideoCLIP#PT=136M2022.12 | 92.1 | |
| VideoCLIPYear=20192023.08 | 92.1 | |
| VideoCLIPYear=20192023.08 | 92.1 | |
| VideoCLIP#Pairs=136M2023.03 | 92.1 | |
| All-in-one#PT=138M, #Train Frame=92022.06 | 92 | |
| SINGULARITY#PT=5M, #Train Frame=12022.06 | 92 | |
| All-in-one#PT=138M2022.12 | 92 | |
| All-in-one#Pairs=138M2023.03 | 92 | |
| VIOLET2022.12 | 91.9 | |
| VIOLET#PT=138M2022.12 | 91.9 | |
| VIOLET# Pretrain videos/images=186M2022.09 | 91.9 | |
| VIOLET#Pairs=138M2023.03 | 91.9 | |
| ATPNumber of sampled frames (n)=4, embeddings chosen=12022.06 | 91.4 | |
| MERLOT#PT=180M, #Train Frame=52022.06 | 90.9 | |
| MERLOT2022.06 | 90.9 | |
| MERLOT2022.12 | 90.9 | |
| MERLOT#PT=180M2022.12 | 90.9 | |
| MERLOT# Pretrain videos/images=180M2022.09 | 90.9 | |
| MERLOTYear=20212023.08 | 90.9 | |
| MERLOTYear=20212023.08 | 90.9 | |
| MERLOT#Pairs=180M2023.03 | 90.9 | |
| ClipBERT#PT=0.2M, #Train Frame=162022.06 | 88.2 | |
| ClipBERT2022.06 | 88.2 | |
| ClipBert2022.12 | 88.2 | |
| ClipBERT#PT=0.2M2022.12 | 88.2 | |
| ClipBERT# Pretrain videos/images=0.2M2022.09 | 88.2 | |
| ClipBERTYear=20212023.08 | 88.2 | |
| ClipBERTYear=20212023.08 | 88.2 | |
| ClipBERT#Pairs=0.2M2023.03 | 88.2 | |
| ActBERT2022.06 | 85.7 | |
| ActBERTYear=20202023.08 | 85.7 | |
| ActBERTYear=20202023.08 | 85.7 | |
| CLIPmode=single-frame2022.06 | 84.8 | |
| JSFusion2022.12 | 83.4 | |
| CLIPYear=20212023.08 | 74.1 | |
| CLIPYear=20212023.08 | 74.1 | |
| HTGS2022.12 | 33 |