Video Question Answering on CausalChaos!QA
67.65AccuracyOurs
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OursCategory=VLMs/Multimodal foundation approaches2025.08 | 67.65 | 69.26 | 71.22 | |
| VILA 1.5-3BCategory=VLMs/Multimodal foundation approaches2025.08 | 62.8 | 65.05 | 67.2 | |
| GPT4oCategory=VLMs/Multimodal foundation approaches2025.08 | 48.17 | 56.72 | 58 | |
| MISTCategory=Semi-traditional approaches2025.08 | 44.88 | 57.36 | 64.04 | |
| QwenVL 2.5-7BCategory=VLMs/Multimodal foundation approaches2025.08 | 31.54 | 59.5 | 70.73 | |
| BLIP-2Category=VLMs/Multimodal foundation approaches2025.08 | 23.32 | 43.44 | 53 | |
| DeepSeek-VL2Category=VLMs/Multimodal foundation approaches2025.08 | 17.12 | 41.92 | 51.95 | |
| HCRNCategory=Traditional VideoQA approaches2025.08 | 17 | 41.86 | 52.93 | |
| HGACategory=Traditional VideoQA approaches2025.08 | 15.36 | 42 | 53.88 | |
| VideoChat2Category=VLMs/Multimodal foundation approaches2025.08 | 15.36 | 40.45 | 48.5 | |
| HMECategory=Traditional VideoQA approaches2025.08 | 14.02 | 40.66 | 52.43 | |
| CoMemCategory=Traditional VideoQA approaches2025.08 | 13.88 | 40.94 | 53.05 | |
| EVQACategory=Traditional VideoQA approaches2025.08 | 13.48 | 38.91 | 50.62 | |
| BlindQACategory=Traditional VideoQA approaches2025.08 | 13.07 | 33.64 | 44.87 | |
| VideoLLaMACategory=VLMs/Multimodal foundation approaches2025.08 | 11.73 | 28.24 | 33.31 |