Storing Less, Finding More: How Novelty Filtering Improves Cross-Modal Retrieval on Edge Cameras

ArXi:2603.29631v1 Announce Type: new Always-on edge cameras generate continuous video streams where redundant frames degrade cross-modal retrieval by crowding correct results out of top-k search. This paper presents a streaming retrieval architecture: an on-device epsilon-net filter retains only semantically novel frames, building a denoised embedding index; a cross-modal adapter and cloud re-ranker compensate for the compact encoder's weak alignment.