Person Search by Multi-Scale Matching

@inproceedings{Lan2018PersonSB,
  title={Person Search by Multi-Scale Matching},
  author={Xu Lan and Xiatian Zhu and Shaogang Gong},
  booktitle={ECCV},
  year={2018}
}
We consider the problem of person search in unconstrained scene images. Existing methods usually focus on improving the person detection accuracy to mitigate negative effects imposed by misalignment, mis-detections, and false alarms resulted from noisy people auto-detection. In contrast to previous studies, we show that sufficiently reliable person instance cropping is achievable by slightly improved state-of-the-art deep learning object detectors (e.g. Faster-RCNN), and the under-studied multi… 
Person Search via Deep Integrated Networks
TLDR
An integrated deep network consisting of a detection and identification module for person search, based on the Faster R-CNN, designed herein a framework for the practical surveillance scenarios in which the scene images are captured.
Anchor-Free Person Search
TLDR
This work presents the Feature-Aligned Person Search Network (AlignPS), the first anchor-free framework to efficiently tackle this challenging task, and proposes an aligned feature aggregation module to generate more discriminative and robust feature embeddings by following a "re-id first" principle.
3W-AlignNet: a Feature Alignment Framework for Person Search with Three-Way Decision Theory
TLDR
A three-way-based feature alignment framework (3W-AlignNet) to optimize the re-ID feature localization and a Granularity Weighted Similarity (GWS) algorithm to relieve the granularity mismatch problem.
Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
TLDR
An end-to-end Integrated Net is introduced, called DC-I-Net, which outperforms the state-of-the-art tasks-integrated and tasks-separated image search models and makes two new contributions: two modules are tailored to handle different tasks separately in the integrated framework, such that the task specification is guaranteed.
Re-ID Driven Localization Refinement for Person Search
  • Chuchu Han, Jiacheng Ye, N. Sang
  • Computer Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
TLDR
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.
Multi-Attribute Enhancement Network for Person Search
TLDR
A simple and effective model called Multi-Attribute Enhancement (MAE) which introduces attribute tags to learn local features to promote the search performance and achieves state-of-the-art among end-to-end methods.
Anchor-Free Detector and Re-Identification with Joint Loss for Person Search
TLDR
This work proposes offset guided erasing instead of random erasing to solve the occlusion problem in person search task preferably and shows that this method performs more effectively against the state-of-the-art methods on two widely used person search datasets.
Hierarchical Online Instance Matching for Person Search
TLDR
A Hierarchical Online Instance Matching (HOIM) loss is proposed which exploits the hierarchical relationship between detection and re-ID to guide the learning of the network and justifies the effectiveness of the proposed HOIM loss on learning robust features.
Efficient Person Search: An Anchor-Free Approach
TLDR
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.
Weakly Supervised Person Search
TLDR
A clustering and patch based weakly supervised learning (CPBWSL) framework, which separately addresses two sub-tasks including pedestrian detection and person re-identification, and introduces multiple detectors to provide more detection results as well as fuzzy c-means clustering algorithm to cluster these results and remove low membership ones.
...
...

References

SHOWING 1-10 OF 46 REFERENCES
Joint Detection and Identification Feature Learning for Person Search
TLDR
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.
Deep Low-Resolution Person Re-Identification
TLDR
This work develops a novel approach called Super-resolution and Identity joiNt learninG (SING) to simultaneously optimise image super- resolution and person re-id matching and introduces an adaptive fusion algorithm for accommodating multi-resolution LR images.
Harmonious Attention Network for Person Re-identification
  • Wei Li, Xiatian Zhu, S. Gong
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
A novel Harmonious Attention CNN (HA-CNN) model is formulated for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images.
Multi-scale Deep Learning Architectures for Person Re-identification
TLDR
A novel multi-scale deep learning model is proposed that is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching.
Person Re-identification by Deep Learning Multi-scale Representations
TLDR
A novel Deep Pyramid Feature Learning (DPFL) CNN architecture for multi-scale appearance feature fusion optimised simultaneously by concurrent per-scale re-id losses and interactive cross-scale consensus regularisation in a closed-loop design is formulated.
Multi-Scale Triplet CNN for Person Re-Identification
TLDR
A multi-scale triplet convolutional neural network which captures visual appearance of a person at various scales is proposed, addressing the problem of small training set in person re-identification.
Person Re-identification by Video Ranking
TLDR
A novel model to automatically select the most discriminative video fragments from noisy image sequences of people where more reliable space-time features can be extracted, whilst simultaneously to learn a video ranking function for person re-id is presented.
Unsupervised Salience Learning for Person Re-identification
TLDR
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.
Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function
TLDR
A novel multi-channel parts-based convolutional neural network model under the triplet framework for person re-identification that significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based ones, on the challenging i-LIDS, VIPeR, PRID2011 and CUHK01 datasets.
Scalable Person Re-identification: A Benchmark
TLDR
A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset.
...
...