Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning

@article{Lin2017CrossDomainVM,
  title={Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning},
  author={Liang Lin and Guangrun Wang and Wangmeng Zuo and Xiangchu Feng and Lei Zhang},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2017},
  volume={39},
  pages={1089-1102}
}
  • Liang Lin, Guangrun Wang, +2 authors Lei Zhang
  • Published 13 May 2016
  • Computer Science, Mathematics, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
Cross-domain visual data matching is one of the fundamental problems in many real-world vision tasks, e.g., matching persons across ID photos and surveillance videos. Conventional approaches to this problem usually involves two steps: i) projecting samples from different domains into a common space, and ii) computing (dis-)similarity in this space based on a certain distance. In this paper, we present a novel pairwise similarity measure that advances existing models by i) expanding traditional… Expand
Face Sketch Matching via Coupled Deep Transform Learning
TLDR
A novel transform learning based approach termed as DeepTransformer, which learns a transformation and mapping function between the features of two domains, and can be applied with any existing learned or hand-crafted feature. Expand
Large Margin Learning in Set-to-Set Similarity Comparison for Person Reidentification
TLDR
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. Expand
Attend to the Difference: Cross-Modality Person Re-Identification via Contrastive Correlation
TLDR
A dual-path cross-modality feature learning framework which preserves intrinsic spatial structures and attends to the difference of input cross- modality image pairs, which outperforms state-of-the-art algorithms by a large margin with both full and simplified evaluation modes. Expand
SCAN: Self-and-Collaborative Attention Network for Video Person Re-Identification
TLDR
A novel and practical deep architecture for video person re-identification termed self-and-collaborative attention network (SCAN), which adopts the video pairs as the input and outputs their matching scores and can be predicted by the binary classifier. Expand
Dual-alignment Feature Embedding for Cross-modality Person Re-identification
TLDR
A dual-alignment feature embedding method that can extract modality-invariant features with robust and rich identity embeddings for cross-modality person re-identification and achieves competitive results with the state-of-the-art methods on two datasets. Expand
Visible Thermal Person Re-Identification via Dual-Constrained Top-Ranking
TLDR
A dual-path network with a novel bi-directional dual-constrained top-ranking loss to learn discriminative feature representations and identity loss is further incorporated to model the identity-specific information to handle large intra-class variations. Expand
Learning Modality-Specific Representations for Visible-Infrared Person Re-Identification
TLDR
This paper proposes a novel framework that employs modality-specific networks to tackle with the heterogeneous matching problem and demonstrates that the MSR effectively improves the performance of deep networks on VI-REID and remarkably outperforms the state-of-the-art methods. Expand
Deep feature learning with attributes for cross-modality person re-identification
TLDR
This work provides a different view of the cross-modality person Re-ID problem, which uses additional attribute labels as auxiliary information to increase intraclass cross- modality similarity, and proposes an end-to-end network to learn modality-invariant and identity-specific local features with the joint supervision of attribute classification loss and identity classification loss. Expand
MOTS R-CNN: Cosine-margin-triplet loss for multi-object tracking
TLDR
This paper proposescosine-margin-contrastive (CMC) and cosine-margintriplet (CMT) loss by reformulating both contrastive and triplet loss functions from the perspective of cosine distance and proposes the MOTS RCNN framework for joint multi-object tracking and segmentation, particularly targeted at improving the tracking performance. Expand
Bi-Directional Center-Constrained Top-Ranking for Visible Thermal Person Re-Identification
TLDR
A dual-path network with a novel bi-directional dual-constrained top-ranking (BDTR) loss to learn discriminative feature representations and the extensive experiments on two cross-modality re-ID datasets demonstrate the superiority of the proposed method compared to the state-of-the-arts. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 105 REFERENCES
Deep feature learning with relative distance comparison for person re-identification
TLDR
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. Expand
Deep Ranking for Person Re-Identification via Joint Representation Learning
TLDR
A novel approach to person re-identification, a fundamental task in distributed multi-camera surveillance systems, is proposed that significantly outperforms all the state-of-the-art approaches, including both traditional and CNN-based methods on the challenging VIPeR, CUHK-01, and CAVIAR4REID datasets. Expand
DARI: Distance Metric and Representation Integration for Person Verification
TLDR
This work proposes an end-to-end learning framework called DARI, i.e. Distance metric And Representation Integration, and validates the effectiveness of DARI in the challenging task of person verification. Expand
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. Expand
Deep Metric Learning for Practical Person Re-Identification
TLDR
A more general way that can learn a similarity metric from image pixels directly by using a "siamese" deep neural network that can jointly learn the color feature, texture feature and metric in a unified framework is proposed. Expand
Cross-Modal Similarity Learning: A Low Rank Bilinear Formulation
TLDR
The proposed cross-modal similarity learning algorithm takes a bilinear formulation, and with the nuclear-norm penalization, it achieves low-rank representation and the accelerated proximal gradient algorithm is successfully imported to find the optimal solution with a fast convergence rate O(1/t2). Expand
Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-Identification
TLDR
A supervised learning framework to generate compact and bit-scalable hashing codes directly from raw images that outperforms state-of-the-arts on public benchmarks of similar image search and achieves promising results in the application of person re-identification in surveillance. Expand
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. Expand
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
TLDR
This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. Expand
Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval
TLDR
A novel coding framework called Cross-Age Reference Coding (CARC), which is able to encode the low-level feature of a face image with an age-invariant reference space and can achieve state-of-the-art performance on both the dataset and other widely used dataset for face recognition across age, MORPH dataset. Expand
...
1
2
3
4
5
...