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

Read full text Summarise with VIRAT
Authors: Sherif Abdelwahab
Cited by: 0
References: 19

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

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. A single-pass streaming filter outperforms offline alternatives (k-means, farthest-point, uniform, random) across eight vision-language models (8M-632M) on two egocentric datasets (AEA, EPIC-KITCHENS). Combined, the architecture reaches 45.6% Hit@5 on held-out data using an 8M on-device encoder at an estimated 2.7 mW.

Fields of Study & Subjects

Multimodal Machine Learning Applications Advanced Image and Video Retrieval Techniques Image Retrieval and Classification Techniques

Publication details

Journal / source
arXiv (Cornell University)
Publication date
31 March 2026
Language
EN
Document type
Preprint