Towards effective person search with deep learning: A survey from systematic perspective

P Zhang, X Yu, C Wang, J Zheng, X Ning, X Bai - Pattern Recognition, 2024 - Elsevier
Person search detects and retrieves simultaneously a query person across uncropped
scene images captured by multiple non-overlap** cameras. In light of the deep learning …

Cascade transformers for end-to-end person search

R Yu, D Du, R LaLonde, D Davila… - Proceedings of the …, 2022 - openaccess.thecvf.com
The goal of person search is to localize a target person from a gallery set of scene images,
which is extremely challenging due to large scale variations, pose/viewpoint changes, and …

Pstr: End-to-end one-step person search with transformers

J Cao, Y Pang, RM Anwer… - Proceedings of the …, 2022 - openaccess.thecvf.com
We propose a novel one-step transformer-based person search framework, PSTR, that
jointly performs person detection and re-identification (re-id) in a single architecture. PSTR …

OIMNet++: Prototypical Normalization and Localization-Aware Learning for Person Search

S Lee, Y Oh, D Baek, J Lee, B Ham - European Conference on Computer …, 2022 - Springer
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 …

DCMNet: Discriminant and cross-modality network for RGB-D salient object detection

F Wang, R Wang, F Sun - Expert Systems with Applications, 2023 - Elsevier
It is well-acknowledged that depth maps contain affluent spatial information which is crucial
to explicitly distinguish the foreground and background in Salient Object Detection (SOD) …

Query-guided networks for few-shot fine-grained classification and person search

B Munjal, A Flaborea, S Amin, F Tombari, F Galasso - Pattern Recognition, 2023 - Elsevier
Few-shot fine-grained classification and person search appear as distinct tasks and
literature has treated them separately. But a closer look unveils important similarities: both …

Hierarchical visual primitive experts for compositional zero-shot learning

H Kim, J Lee, S Park, K Sohn - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior
knowledge of known primitives (attribute and object). Previous works for CZSL often suffer …

Deep intra-image contrastive learning for weakly supervised one-step person search

J Wang, Y Pang, J Cao, H Sun, Z Shao, X Li - Pattern Recognition, 2024 - Elsevier
Weakly supervised person search aims to perform joint pedestrian detection and re-
identification (re-id) with only bounding-box annotations. Recently, the idea of contrastive …

Self-similarity driven scale-invariant learning for weakly supervised person search

B Wang, Y Yang, J Wu, G Qi… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Weakly supervised person search aims to jointly detect and match persons with only
bounding box annotations. Existing approaches typically focus on improving the features by …

DMRNet++: Learning discriminative features with decoupled networks and enriched pairs for one-step person search

C Han, Z Zheng, K Su, D Yu, Z Yuan… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
Person search aims at localizing and recognizing query persons from raw video frames,
which is a combination of two sub-tasks, ie, pedestrian detection and person re …