AI RESEARCH
REMAP: Regularized Matching and Partial Alignment of Video Embeddings
arXiv CS.CV
•
ArXi:2509.24382v2 Announce Type: replace Real-world instructional videos are long, noisy, and often contain extended background segments, repeated actions, and execution variability that do not correspond to meaningful procedural steps. We propose **REMAP**, an unsupervised framework for procedure learning based on *Regularized Fused Partial Gromo-Wasserstein Optimal Transport*. REMAP relaxes balanced transport constraints, allowing non-informative or redundant frames to remain unmatched through partial transport.