Joint Person Objectness and Repulsion for Person Search

  title={Joint Person Objectness and Repulsion for Person Search},
  author={Hantao Yao and Changsheng Xu},
  journal={IEEE Transactions on Image Processing},
Person search targets to search the probe person from the unconstrainted scene images, which can be treated as the combination of person detection and person matching. However, the existing methods based on the Detection-Matching framework ignore the person objectness and repulsion (OR) which are both beneficial to reduce the effect of distractor images. In this paper, we propose an OR similarity by jointly considering the objectness and repulsion information. Besides the traditional visual… 
SAN: Selective Alignment Network for Cross-Domain Pedestrian Detection
A novel Selective Alignment Network for cross-domain pedestrian detection is proposed, which consists of three components: a Base Detector, an Image-Level Adaptation Network, and an Instance-Leveladaptation Network.
An Improved Approach for Object Proposals Generation
An improved generic object detection approach, which predicts candidate object proposals from more than 10,000 proposals and can accurately detect 92.3% of the objects by using less than 200 proposals is presented.
Context-Aware Unsupervised Clustering for Person Search
This paper proposes a hard negative mining scheme based on the uniqueness property that only a single person has the same identity to a given query person in each image, and proposes efficient unsupervised clustering methods to substitute the supervision process using annotated person identity labels.
Efficient Person Search: An Anchor-Free Approach
This work presents an anchor-free approach to efficiently tackling person search, and names its model as FeatureAligned Person Search Network (AlignPS), which is augmented with an ROI-Align head, which significantly improves the robustness of re-id features while still keeping the model highly efficient.
Global-Local Context Network for Person Search
This paper dives into the rich context information globally and locally surrounding the target person, which it refers to scene and group context, respectively, and exploits them in a unified globallocal context network (GLCNet) with the intuitive aim of feature enhancement.
Unsupervised Vehicle Search in the Wild: A New Benchmark
  • Xian Zhong, Shilei Zhao, +4 authors Zheng Wang
  • Computer Science
    ACM Multimedia
  • 2021
A new vehicle search dataset is established and an unsupervised framework on this benchmark dataset is designed to generate pseudo labels for further training existing vehicle re-ID or person search models to advance the research of vehicle search.


Person Search by Multi-Scale Matching
This work proposes a Cross-Level Semantic Alignment (CLSA) deep learning approach capable of learning more discriminative identity feature representations in a unified end-to-end model that favourably eliminates the need for constructing a computationally expensive image pyramid and a complex multi-branch network architecture.
Re-ID Driven Localization Refinement for Person Search
A differentiable ROI transform layer is developed to effectively transform the bounding boxes from the original images so that the box coordinates can be supervised by the re-ID training other than the original detection task.
Large Margin Learning in Set-to-Set Similarity Comparison for Person Reidentification
This paper proposes using a deep learning technique to model a novel set-to-set (S2S) distance, in which the underline objective focuses on preserving the compactness of intraclass samples for each camera view, while maximizing the margin between the intraclasses set and interclass set.
Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities
This paper proposes a novel relevance metric learning method with listwise constraints (RMLLCs) by adopting listwise similarities, which consist of the similarity list of each image with respect to all remaining images, and develops an efficient alternating iterative algorithm to jointly learn the optimal metric and the rectification term.
Joint Detection and Identification Feature Learning for Person Search
A new deep learning framework for person search that jointly handles pedestrian detection and person re-identification in a single convolutional neural network and converges much faster and better than the conventional Softmax loss.
Unsupervised Salience Learning for Person Re-identification
A novel perspective for person re-identification based on unsupervised salience learning, which applies adjacency constrained patch matching to build dense correspondence between image pairs, which shows effectiveness in handling misalignment caused by large viewpoint and pose variations.
GLAD: Global–Local-Alignment Descriptor for Scalable Person Re-Identification
A robust and discriminative pedestrian image descriptor, namely, the Global–Local-Alignment Descriptor (GLAD), designed to perform offline relevance mining to eliminate the huge person ID redundancy in the gallery set, and accelerate the online Re-ID procedure.
Learning Context Graph for Person Search
This work proposes a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene, and builds a graph learning framework to effectively employ context pairs to update target similarity.
Deep feature learning with relative distance comparison for person re-identification
A scalable distance driven feature learning framework based on the deep neural network for person re-identification that achieves very promising results and outperforms other state-of-the-art approaches.
Person Search via A Mask-Guided Two-Stream CNN Model
A simple yet effective re-ID method is proposed, which models foreground person and original image patches individually, and obtains enriched representations from two separate CNN streams, and achieves mAP of 83.0% on the standard person search benchmark datasets.