AI Paper Atlas

Research map / Video / Video-language understanding

VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning

Zikang Wang, Boyu Chen, Zhengrong Yue, Yi Wang, Yu Qiao, Limin Wang, Yali Wang

AAAI 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 26 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 video glance pre-judging step (ablation)VideoChat-A1 (Qwen2.5-VL-7B) · MLVUaccuracy: 70.0 -> 71.9Improved
add shot partition only (ablation)VideoChat-A1 (Qwen2.5-VL-7B) · MLVUaccuracy: 66.2 -> 68.5Improved
add chain-of-shot only (ablation)VideoChat-A1 (Qwen2.5-VL-7B) · MLVUaccuracy: 66.2 -> 67.0Improved
add both shot partition and chain-of-shot (ablation)VideoChat-A1 (Qwen2.5-VL-7B) · MLVUaccuracy: 66.2 -> 71.9Improved
semantic shot partition vs cluster partition (ablation)VideoChat-A1 (Qwen2.5-VL-7B) · LongVideoBenchaccuracy: 58.4 -> 64.2Improved
semantic shot partition vs average partition (ablation)VideoChat-A1 (Qwen2.5-VL-7B) · LongVideoBenchaccuracy: 57.7 -> 64.2Improved
increase max reflection rounds from 1 to 3 (ablation)VideoChat-A1 (Qwen2.5-VL-7B) · MLVUaccuracy: 66.2 -> 71.9Improved
increase max rounds from 3 to 4 (ablation)VideoChat-A1 (Qwen2.5-VL-7B) · MLVUaccuracy: 71.9 -> 72.1No clear effect
6 initial shots vs 3 or 9 (ablation)VideoChat-A1 (Qwen2.5-VL-7B) · MLVUaccuracy: 70.8 / 71.9 / 71.8 (3/6/9)Mixed
wrap InternVL2.5-8B in chain-of-shot agentInternVL2.5-8B · Video-MME (w/ subs)accuracy: 66.9 -> 77.0Improved
agent with fewer frames vs GPT-4oVideoChat-A1 (InternVL2.5-8B) · frames and timeaverage frames: 384 -> 35.9Improved

Later papers that compared with this method

1 later accepted paper reports VideoChatA1 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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