AI RESEARCH
Look Beyond Saliency: Low-Attention Guided Dual Encoding for Video Semantic Search
arXiv CS.CV
•
ArXi:2605.06229v1 Announce Type: new Video semantic search in densely crowded scenes remains a challenging task due to visual encoders tendency to prioritize salient foreground regions while neglecting contextually important, background areas. We propose an Inverse Attention Embedding mechanism that explicitly captures and highlights these overlooked regions. By combining inverse attention embeddings with traditional visual embeddings, our method significantly enhances semantic retrieval performance without additional.