Learning Context-Aware Embedding for Person Search
This work addresses the problem of improving person search accuracy for applications like surveillance by incorporating contextual information, representing an incremental advancement over existing one-step methods.
The paper tackles the challenge of distinguishing confusing persons in person search due to factors like illumination, pose variance, and occlusion by introducing a novel contextual feature head called Attention Context-Aware Embedding (ACAE) that enhances contextual information, achieving state-of-the-art results on one-step methods.
Person Search is a relevant task that aims to jointly solve Person Detection and Person Re-identification(re-ID). Though most previous methods focus on learning robust individual features for retrieval, it's still hard to distinguish confusing persons because of illumination, large pose variance, and occlusion. Contextual information is practically available in person search task which benefits searching in terms of reducing confusion. To this end, we present a novel contextual feature head named Attention Context-Aware Embedding(ACAE) which enhances contextual information. ACAE repeatedly reviews the person features within and across images to find similar pedestrian patterns, allowing it to implicitly learn to find possible co-travelers and efficiently model contextual relevant instances' relations. Moreover, we propose Image Memory Bank to improve the training efficiency. Experimentally, ACAE shows extensive promotion when built on different one-step methods. Our overall methods achieve state-of-the-art results compared with previous one-step methods.