AI Paper Atlas

Research map / Video / Video-language understanding

StimuVAR: Spatiotemporal Stimuli-Aware Video Affective Reasoning with Multimodal Large Language Models

Yuxiang Guo, Faizan Siddiqui, Yang Zhao, Rama Chellappa, Shao-Yuan Lo

IJCV 2025 · Video › Video-language understanding · approach: Long video understanding · 41 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 event-driven frame sampling (ablation)vanilla model · VCETop-1/Top-3 accuracy: 44.5 -> 46.0 Top-1; 68.4 -> 70.9 Top-3Improved
add VAR visual instruction tuning (ablation)model with event-driven sampling · VCETop-1/Top-3 accuracy: 46.0 -> 47.3 Top-1; 70.9 -> 72.5 Top-3Improved
add emotion-triggered tube selection (ablation)model with sampling and instruction tuning · VCETop-1/Top-3 accuracy: 47.3 -> 48.3 Top-1; 72.5 -> 73.5 Top-3Improved
tube selection instead of Valley V3 aggregation (ablation)StimuVAR · VCETop-3 accuracy: 72.9 -> 73.5Improved
tube selection instead of TS Selection (ablation)StimuVAR · VCETop-3 accuracy: 72.5 -> 73.5Improved
event-driven instead of uniform frame sampling (ablation)StimuVAR · VCE surprise subsetTop-3 accuracy: 67.6 -> 72.9Improved
event-driven instead of uniform frame sampling (ablation)StimuVAR · VCE entire test setTop-3 accuracy: 69.7 -> 73.5Improved
event-driven instead of AKS frame selection (ablation)StimuVAR · VCE entire test setTop-3 accuracy: 71.6 -> 73.5Improved
event-driven instead of uniform sampling (ablation)Chat-UniVi (fine-tuned) · VCE surprise subsetTop-3 accuracy: 57.9 -> 63.2Improved
increase sampled frames from N=3 to N=6 (ablation)StimuVAR · VCETop-3 accuracy: 69.9 -> 73.5Improved
select top K=4 tubes instead of K=1 (ablation)StimuVAR · VCETop-3 accuracy: 71.8 -> 73.5Improved
use Llama3-8b instead of Llama2-7b (ablation)StimuVAR · VCETop-3 accuracy: 73.5 -> 74.0Improved

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