AI Paper Atlas

Research map / Video / Video generation

HERO: Human Reaction Generation from Videos

Chengjun Yu, Wei Zhai, Yuhang Yang, Yang Cao, Zheng-Jun Zha

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 10 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 Interaction Intention Extraction (global-local cross-attention) (ablation)HERO · ViMo test setFID: 0.535 -> 0.427Improved
add Interaction Intention Extraction (ablation)HERO · ViMo test setMModality: 1.626 -> 1.614No clear effect
add Dynamic Information Exploitation (motion-frame cross-attention) (ablation)HERO · ViMo test setFID: 0.521 -> 0.427Improved
add Dynamic Information Exploitation (ablation)HERO · ViMo test setMModality: 1.443 -> 1.614Improved
use 6 Transformer decoder units instead of 4 (ablation)HERO · ViMo test setFID: 0.659 -> 0.427Improved
use 6 Transformer decoder units instead of 8 (ablation)HERO · ViMo test setFID: 0.683 -> 0.427Improved
use 6 Transformer decoder units instead of 7 (ablation)HERO · ViMo test setMModality: 1.614 -> 1.649No clear effect
increase training pairs from 2800 to 8400 (ablation)HERO · ViMo test setFID: 0.427 -> 0.376Improved
increase training pairs from 2800 to 8400 (ablation)HERO · ViMo test setMModality: 1.614 -> 1.422Hurt
replace MoMask with HERO on unseen categoriesHERO vs MoMask · ViMo Unseen setFID: 2.477 -> 2.156Improved
replace MoMask with HEROHERO vs MoMask · ViMo test setFID: 0.856 -> 0.427Improved
replace MoMask with HEROHERO vs MoMask · ViMo test setMModality: 1.567 -> 1.614Hurt

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