AI Paper Atlas

Research map / Video / Video-language understanding

VideoSetDiff: Identifying and Reasoning Similarities and Differences in Similar Videos

Yue Qiu, Yanjun Sun, Takuma Yagi, Shusaku Egami, Natsuki Miyata, Ken Fukuda, Kensho Hara, Ryusuke Sagawa

ICCV 2025 · 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
fine-tune with multi-video training set and cross-video modelling (VidSetReasoner vs InternVideo2.5)InternVideo2.5 · VideoSetDiff evaluation setoverall accuracy: 66.8 -> 68.6Improved
fine-tune with multi-video training set (reasoning questions)InternVideo2.5 · VideoSetDiff evaluation setreasoning question accuracy: 64.8 -> 66.5Improved
fine-tune with multi-video training set (recognition questions)InternVideo2.5 · VideoSetDiff evaluation setrecognition question accuracy: 68.7 -> 70.6Improved
add captions + GPT-4 instead of blind GPT-4Blind GPT-4 · VideoSetDiff evaluation setoverall accuracy: 51.7 -> 56.7Improved
use direct multi-video QA instead of caption + GPT-4VideoChat2 · VideoSetDiff evaluation setoverall accuracy: 56.7 -> 52.4No clear effect
use direct multi-video QA instead of caption + GPT-4InternVideo2.5 · VideoSetDiff evaluation setoverall accuracy: 56.9 -> 66.8Improved
use direct multi-video QA instead of caption + GPT-4TimeChat · VideoSetDiff evaluation setoverall accuracy: 57.1 -> 32.7Hurt
use multiple-choice instead of binary questionsVidSetReasoner · VideoSetDiff evaluation setaccuracy: 74.2 -> 62.7Hurt
use caption + GPT-4 pipeline instead of direct for recognitionInternVideo2 · VideoSetDiff evaluation setrecognition question accuracy: 59.3 -> 53.7Hurt
use caption + GPT-4 instead of direct QA for reasoningInternVideo2 · VideoSetDiff evaluation setreasoning question accuracy: 45.6 -> 60.9Improved
increase number of input frames (ablation)VideoLLaMA2 and GPT4o · VideoSetDiff evaluation setaccuracyNo clear effect
increase number of input frames (ablation)InternVideo2.5 · VideoSetDiff evaluation setaccuracyMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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