ML Research Wiki / Benchmarks / Video Question Answering / How2QA

How2QA

Video Question Answering Benchmark

Performance Over Time

📊 Showing 7 results | 📏 Metric: Accuracy

Top Performing Models

Rank Model Paper Accuracy Date Code
1 Text + Text (no Multimodal Pretext Training) Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval 93.20 2022-06-05 📦 xudonglinthu/upgradable-multimodal-intelligence
2 FrozenBiLM 📚 Zero-Shot Video Question Answering via Frozen Bidirectional Language Models 86.70 2022-06-16 📦 antoyang/FrozenBiLM 📦 klauscc/dam 📦 sts-vlcc/sts-vlcc
3 Just Ask 📚 Just Ask: Learning to Answer Questions from Millions of Narrated Videos 84.40 2020-12-01 📦 antoyang/just-ask
4 Hero w/ pre-training HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training 77.75 2020-05-01 📦 linjieli222/HERO 📦 linjieli222/hero_video_feature_extractor 📦 grounded-sport-convai/goal-baselines
5 ATP Revisiting the "Video" in Video-Language Understanding 65.10 2022-06-03 📦 stanfordvl/atp-video-language
6 FrozenBiLM (0-shot) Zero-Shot Video Question Answering via Frozen Bidirectional Language Models 58.40 2022-06-16 📦 antoyang/FrozenBiLM 📦 klauscc/dam 📦 sts-vlcc/sts-vlcc
7 Just Ask (0-shot) Just Ask: Learning to Answer Questions from Millions of Narrated Videos 51.10 2020-12-01 📦 antoyang/just-ask

All Papers (7)

xudonglinthu/upgradable-multimodal-intelligence
antoyang/FrozenBiLM klauscc/dam sts-vlcc/sts-vlcc
antoyang/just-ask
linjieli222/HERO linjieli222/hero_video_feature_extractor grounded-sport-convai/goal-baselines
stanfordvl/atp-video-language
antoyang/FrozenBiLM klauscc/dam sts-vlcc/sts-vlcc
antoyang/just-ask