AI Paper Atlas

Research map / Video / Video-language understanding

EatVid-Bench: A Multimodal Fine-Grained Eating Behavior Video Dataset

Xiangpeng Zheng, Zhenbo Xu, Gong Huang, Zhu Li, Qinghong Yang

ECCV 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add annotation-guided CoT supervision on top of plain LoRA (ablation)Qwen2.5-VL-7B · EatVid-QA Hard subset (4 FPS)Non-SA-WAcc (%): 22.3 -> 36.4Improved
add plain LoRA fine-tuning on EatVid data (ablation)Qwen2.5-VL-7B · EatVid-QA Hard subset (4 FPS)Non-SA-WAcc (%): 14.1 -> 22.3Improved
fine-tune with AGCoT-LoRAQwen2.5-VL-7B · EatVid-QA Hard subsetAcc: 0.2500 -> 0.4069Improved
fine-tune with AGCoT-LoRAQwen2.5-VL-7B · EatVid-QA Hard subsetNon-SA-WAcc: 0.1623 -> 0.3214Improved
fine-tune with AGCoT-LoRAQwen2.5-VL-7B · EatVid-QA Hard subsetWAcc: 0.5798 -> 0.6130Improved
use larger API model instead of 7B open modelQwen3.5-35B-A3B · EatVid-QA Hard subsetWAcc: 0.6130 -> 0.7359Improved
increase frame density from 32 to 64 frames or 1-4 FPSVideo-LLMs · EatVid-QAaccuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy