EgoCaptioner model released
The story so far
qwen has released the EgoCaptioner model, which achieves comprehensive and fine-grained first-person video description by combining scene, participant, and wearer overall activity video-level overviews with adaptive narration at key time steps. It outperforms all evaluated open-source models in five first-person benchmarks in terms of description quality, description conditional question answering, and temporal alignment, surpassing Gemini 3.1 Pro on PhysCapBench and all proprietary baselines on Minerva-Ego.
AI-written from the reports · Updated 1 hour ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersEgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning
EgoCaptioner achieves comprehensive and fine-grained first-person video description by combining video-level overviews of scenes, participants, and the overall activities of wearers with key time steps of adaptive narration. It outperforms all evaluated open-source models in description quality, description conditional question answering, and time alignment across five first-person benchmarks, surpassing Gemini 3.1 Pro on PhysCapBench and all proprietary baselines on Minerva-Ego.
Heat over time
Not enough data yet to draw a trend.