Prototype-Guided Saliency Feature Learning for Person Search
Existing person search methods integrate person detection and re-identification (re-ID) module into a unified system. Though promising results have been achieved, the misalignment problem, which commonly occurs in person search, limits the discriminative feature representation for re-ID. To overcome this limitation, we introduce a novel framework to learn the discriminative representation by utilizing prototype in OIM loss. Unlike conventional methods using prototype as a representation of person identity, we utilize it as guidance to allow the attention network to consistently highlight multiple instances across different poses. Moreover, we propose a new prototype update scheme with adaptive momentum to increase the discriminative ability across different instances. Extensive ablation experiments demonstrate that our method can significantly enhance the feature discriminative power, outperforming the state-of-the-art results on two person search benchmarks including CUHK-SYSU and PRW.
Code (0)
등록된 구현이 없습니다.
Tasks
Human DetectionPerson SearchSimilar Papers 제목 키워드 기반
Guided Saliency Feature Learning for Person Re-identification in Crowded Scenes
Person Re-identification (Re-ID) in crowed scenes is a challenging problem, where people are frequently partially occluded by objects and other people. However, few studies have provided flexible solutions to re-identify…
Person Re-IdentificationPrototype-Guided Text-based Person Search based on Rich Chinese Descriptions
Text-based person search aims to simultaneously localize and identify the target person based on query text from uncropped scene images, which can be regarded as the unified task of person detection and text-based person…
Human DetectionPerson RetrievalPerson SearchRetrieval+3Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation with only image-level labels aims to reduce annotation costs for the segmentation task. Existing approaches generally leverage class activation maps (CAMs) to locate the object reg…
ObjectPseudo LabelRelationSegmentation+3Saliency-guided Emotion Modeling: Predicting Viewer Reactions from Video Stimuli
Understanding the emotional impact of videos is crucial for applications in content creation, advertising, and Human-Computer Interaction (HCI). Traditional affective computing methods rely on self-reported emotions, fac…
DPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification
Although person re-identification has made impressive progress, occlusion caused by obstacles remains an unsettled issue in real applications. The difficulty lies in the mismatch between incomplete occluded samples and h…
Person Re-IdentificationData AugmentationMetric Learning