Lee, Sanghoon Oh, Youngmin Baek, Donghyeon Lee, Junghyup Ham, Bumsub 2024-02-07T05:16:01Z 2024-02-07T05:16:01Z 2023-01-30 2022-10 0302-9743 https://pubs.kist.re.kr/handle/201004/148561 We address the task of person search, that is, localizing and re-identifying query persons from a set of raw scene images. Recent approaches are typically built upon OIMNet, a pioneer work on person search, that learns joint person representations for performing both detection and person re-identification (reID) tasks. To obtain the representations, they extract features from pedestrian proposals, and then project them on a unit hypersphere with L2 normalization. These methods also incorporate all positive proposals, that sufficiently overlap with the ground truth, equally to learn person representations for reID. We have found that 1) the L2 normalization without considering feature distributions degenerates the discriminative power of person representations, and 2) positive proposals often also depict background clutter and person overlaps, which could encode noisy features to person representations. In this paper, we introduce OIMNet++ that addresses the aforementioned limitations. To this end, we introduce a novel normalization layer, dubbed ProtoNorm, that calibrates features from pedestrian proposals, while considering a long-tail distribution of person IDs, enabling L2 normalized person representations to be discriminative. We also propose a localization-aware feature learning scheme that encourages better-aligned proposals to contribute more in learning discriminative representations. Experimental results and analysis on standard person search benchmarks demonstrate the effectiveness of OIMNet++. English SPRINGER INTERNATIONAL PUBLISHING AG OIMNet plus plus: Prototypical Normalization and Localization-Aware Learning for Person Search Conference 10.1007/978-3-031-20080-9_36 1 17th European Conference on Computer Vision (ECCV), pp.621 - 637 17th European Conference on Computer Vision (ECCV) 621 637 SZ Tel Aviv, ISRAEL 2022-10-23 COMPUTER VISION, ECCV 2022, PT X 000897089200036 2-s2.0-85144543335