AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A

Chen Li, Chinthani Sugandhika, Yeo Keat Ee, Eric Peh, Hao Zhang, Hong Yang, Deepu Rajan, Basura Fernando

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning

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 program-guided feature selection over multi-level ViT features (ablation)IMoRe · Babel-QAOverall accuracy: 0.607 -> 0.640Improved
condition reasoning on program functions instead of MAC soft attention over question words (ablation)IMoRe · Babel-QAOverall accuracy: 0.582 -> 0.607Improved
use implicit MAC reasoning instead of explicit NSPose reasoning, same ViT encoder (ablation)motion Q&A · Babel-QAOverall accuracy: 0.440 -> 0.582Improved
replace NSPose motion encoder with ViT (ablation)NSPose · Babel-QAOverall accuracy: 0.578 -> 0.440Hurt
use predicted programs instead of ground-truth programs (ablation)IMoRe · Babel-QAOverall accuracy: 0.640 -> 0.615 (IMoRe II); NSPose 0.578 -> 0.472Hurt
use program rather than question for text-aware motion feature (ablation)IMoRe I · Babel-QAOverall accuracy: 0.609 -> 0.598Hurt
add question type information in fusion (ablation)IMoRe I · Babel-QAOverall accuracy: 0.603 -> 0.609Improved
sample 224 random frames with five test runs (IMoRe II) instead of processing the full sequence in segments (IMoRe I)IMoRe · Babel-QAOverall accuracy: 0.609 -> 0.640Improved
use IMoRe instead of fine-tuned video-language modelsIMoRe I · Babel-QAOverall accuracy: 0.425 (Qwen-2.5-VL-3B) -> 0.609Improved
use IMoRe on HuMMan-QA body-part queries versus MotionCLIP-MLPIMoRe · HuMMan-QAQuery body part accuracy: MotionCLIP-MLP 0.692 vs IMoRe I 0.665Mixed

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