AI Paper Atlas

Research map / Video / Video-language understanding

VideoAds for Fast-Paced Video Understanding

Zheyuan Zhang, Wanying Dou, Linkai Peng, Hongyi Pan, Ulas Bagci, Boqing Gong

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 3 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 speech audio transcript (Whisper) to frame input (ablation)LongVA · VideoAdsoverall accuracy (%): 42.33 -> 48.18Improved
add speech audio transcript to frame input (ablation)LLaVA-Video-72B · VideoAdsoverall accuracy (%): 66.58 -> 71.73Improved
add speech audio transcript to frame input (ablation)Qwen2.5-VL-72B · VideoAdsoverall accuracy (%): 64.33 -> 67.48Improved
add speech audio transcript to frame input (ablation)GPT-4o · VideoAdsoverall accuracy (%): 65.86 -> 66.47Mixed
increase sampled frames from 32 to 128 (ablation)Qwen2.5-VL-72B · VideoAdsoverall accuracy (%): 64.33 -> 73.35Improved
increase sampled frames from 32 to 128 (ablation)LLaVA-Video-72B · VideoAdsoverall accuracy (%): 66.58 -> 68.45Mixed
increase sampled frames from 32 to 128 (ablation)GPT-4o · VideoAdsoverall accuracy (%): 65.57 -> 66.82Mixed
add guided chain-of-thought intermediate questions (ablation)GPT-4o · VideoAds reasoningreasoning accuracy (%): 61 -> 70Improved
add guided chain-of-thought intermediate questions (ablation)LongVA-7B, LLaVA-NeXT-32B, LLaVA-Video-72B · VideoAds reasoningreasoning accuracyHurt
add guided chain-of-thought intermediate questions (ablation)Qwen2.5-VL · VideoAds reasoningreasoning accuracyImproved
remove visual input (text-only GPT-4o) (ablation)GPT-4o · VideoAdsoverall accuracy (%): 66.82 -> 21.27Hurt

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