Neural Person Search Machines

@article{Liu2017NeuralPS,
  title={Neural Person Search Machines},
  author={Hao Liu and Jiashi Feng and Zequn Jie and Jayashree Karlekar and Bo Zhao and Meibin Qi and Jianguo Jiang and Shuicheng Yan},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={493-501}
}
We investigate the problem of person search in the wild in this work. Instead of comparing the query against all candidate regions generated in a query-blind manner, we propose to recursively shrink the search area from the whole image till achieving precise localization of the target person, by fully exploiting information from the query and contextual cues in every recursive search step. We develop the Neural Person Search Machines (NPSM) to implement such recursive localization for person… 

Figures and Tables from this paper

Learning Discriminative Part Features Through Attentions For Effective And Scalable Person Search
TLDR
This paper proposes a new method for person search, the task of detecting a specific person exemplified by a query image from a gallery of scene images, and argues that a concise framework with a single neural network can achieve both of scalability and performance at once.
Person Search Based on Attention Mechanism
TLDR
A convolutional neural network for person search based on attention mechanism that gets better mean Average Precision result of 78.9% on a large-scale benchmark dataset CUHK-SYSU.
Global-Local Context Network for Person Search
TLDR
This paper delves 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 global-local context network (GLCNet) with the intuitive aim of feature enhancement.
Learning Context-Aware Embedding for Person Search
TLDR
A novel contextual feature head named Attention Context-Aware Embedding (ACAE) which enhances contextual information in person search task and achieves state-of-the-art results compared with previous one-step methods.
Query-Guided End-To-End Person Search
TLDR
A novel query-guided end-to-end person search network (QEEPS) to address both person detection and re-identification and outperform the previous state-of-the-art datasets by a large margin.
Instance Guided Proposal Network for Person Search
TLDR
A new detection network for person search, named Instance Guided Proposal Network (IGPN), which can learn the similarity between query persons and proposals and can decrease proposals according to the similarity scores is proposed.
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.
TCTS: A Task-Consistent Two-Stage Framework for Person Search
TLDR
A Task-Consist Two-Stage (TCTS) person search framework, which includes an identity-guided query (IDGQ) detector and a Detection Results Adapted (DRA) re-ID model, outperforming the previous state of the art methods.
Norm-Aware Embedding for Efficient Person Search
TLDR
A novel approach called Norm-Aware Embedding is presented to disentangle the person embedding into norm and angle for detection and re-ID respectively, allowing for both effective and efficient multi-task training.
...
...

References

SHOWING 1-10 OF 48 REFERENCES
End-to-End Deep Learning for Person Search
TLDR
An end-to-end deep learning framework to jointly handle pedestrian detection and person re-identification is proposed and a random sampling softmax loss is proposed to effectively train the model under the supervision of sparse and unbalanced labels.
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.
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.
PersonNet: Person Re-identification with Deep Convolutional Neural Networks
TLDR
A deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification and an adaptive Root- Mean-Square (RMSProp) gradient decent algorithm is integrated into this architecture, which is beneficial to deep nets.
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
TLDR
A novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter is proposed and significantly outperforms state-of-the-art methods on this dataset.
An improved deep learning architecture for person re-identification
TLDR
This work presents a deep convolutional architecture with layers specially designed to address the problem of re-identification, and significantly outperforms the state of the art on both a large data set and a medium-sized data set, and is resistant to over-fitting.
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
TLDR
An attention based model that automatically learns to describe the content of images is introduced that can be trained in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound.
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.
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
End-to-End Comparative Attention Networks for Person Re-Identification
TLDR
This paper proposes a new soft attention-based model, i.e., the end-to-end comparative attention network (CAN), specifically tailored for the task of person re-identification that outperforms well established baselines significantly and offers the new state-of-the-art performance.
...
...