AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

MotionBind: Multi-Modal Human Motion Alignment for Retrieval, Recognition, and Generation

Kaleab A Kinfu, Rene Vidal

NeurIPS 2025 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MotionBind, a multi-modal embedding framework that aligns human motion sequences with text, video, and other modalities for retrieval, recognition, and generation.

Problem

Human motion sequences are largely absent from unified multi-modal embedding spaces, which limits semantic understanding of dynamic human activities that requires grounding in text and visual modalities.

Approach

Aligns a human motion encoder into a shared multi-modal embedding space with images, text, audio, and vision, grounding motion semantics through multiple modalities; the abstract is truncated so the specific mechanism is not stated.

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