📊 Showing 6 results | 📏 Metric: Accuracy
| Rank | Model | Paper | Accuracy | Date | Code |
|---|---|---|---|---|---|
| 1 | LLaMA-VQA | Large Language Models are Temporal and Causal Reasoners for Video Question Answering | 82.20 | 2023-10-24 | 📦 mlvlab/Flipped-VQA |
| 2 | FrozenBiLM 📚 | Zero-Shot Video Question Answering via Frozen Bidirectional Language Models | 82.00 | 2022-06-16 | 📦 antoyang/FrozenBiLM 📦 klauscc/dam 📦 sts-vlcc/sts-vlcc |
| 3 | VindLU 📚 | VindLU: A Recipe for Effective Video-and-Language Pretraining | 79.00 | 2022-12-09 | 📦 klauscc/vindlu |
| 4 | iPerceive (Chadha et al., 2020) | iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering | 76.96 | 2020-11-16 | - |
| 5 | Hero w/ pre-training | HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training | 74.24 | 2020-05-01 | 📦 linjieli222/HERO 📦 linjieli222/hero_video_feature_extractor 📦 grounded-sport-convai/goal-baselines |
| 6 | STAGE (Lei et al., 2019) | TVQA+: Spatio-Temporal Grounding for Video Question Answering | 70.50 | 2019-04-25 | 📦 jayleicn/TVQAplus 📦 jayleicn/TVQA-PLUS 📦 h19920918/quiz_for_day06 |