AI Paper Atlas

Research map / Video / Video segmentation and tracking

V1-Inspired Dynamic Vision System: A Bio-Plausible Video Embedding Framework with Decoupled Shape–Color Pathways and Long-Range Spatiotemporal Perception

Beier Meng

NeurIPS 2026 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning

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 V1-DVS, a bio-plausible video embedding front end inspired by V1 with decoupled shape and color pathways and long-range spatiotemporal perception, trained end-to-end in video-text contrastive learning.

Problem

Video-text contrastive learning typically uses linear patch embeddings or evenly sliced tubelets as the ViT front end, which may be suboptimal for video understanding; the paper revisits this front end using principles of primary visual cortex (V1).

Approach

Replaces the standard linear patch/tubelet embedding with a V1-inspired front end that decouples shape and color pathways and models long-range spatiotemporal interactions, trained end-to-end with video-text contrastive objectives.

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