Person search detects and retrieves simultaneously a query person across uncropped
scene images captured by multiple non-overlapping cameras. In light of the deep learning …

A neural network trained on a classification dataset often exhibits a higher vector norm of
hidden layer features for in-distribution (ID) samples, while producing relatively lower norm …

Person search is a time-consuming computer vision task that entails locating and
recognizing query people in scenic pictures. Body components are commonly mismatched …

Person search aims to simultaneously localize and identify a query person from uncropped
images. To achieve this goal, state-of-the-art models typically add a re-id branch upon two …

Multiple object tracking (MOT), as a typical application scenario of computer vision, has
attracted significant attention from both academic and industrial communities. With its rapid …

Text-based person search is a challenging cross-modal retrieval task. Existing works reduce
the inter-modality and intra-class gaps by aligning local features extracted from image and …

为实现全时全域“泛在连接”, 构建天空地一体化网络已成为国家重大需求, 而基于天空地一体化
网络下跨域协同系统进行多目标跟踪是其中一个重要的发展方向, 其在军民用领域都极具应用 …

Person search is a challenging task that involves detecting and retrieving individuals from a
large set of un-cropped scene images. Existing person search applications are mostly …

Large-scale pre-training has proven to be an effective method for improving performance
across different tasks. Current person search methods use ImageNet pre-trained models for …

Person re‐identification is aimed at searching for specific target pedestrians from non‐
intersecting cameras. However, in real complex scenes, pedestrians are easily obscured …