Joint Learning of Single-Image and Cross-Image Representations for Person Re-identification

By Faqiang Wang, Wangmeng Zuo, Liang Lin, David Dapeng Zhang, Lei Zhang. Computer Vision and Pattern Recognition, 2016

412 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2e59865aa2ddcecaf9275abcad9b134558c686c2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Luc Van Gool
3. Xiaogang Wang
4. Liang Zheng
5. Dacheng Tao
6. Tao A. Xiang
7. Qi Tian
8. Ming-Hsuan Yang

Citations in the corpus

• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval (2017, methodology): “DeeplearningbasedmethodsincludeGatedSiamese[31], LSTMSiamese[32],SI-CI[33],PIE[43]andPIE+Mirror+MFA[43].”
• Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, background): “Joint training is mostly designed for positively related tasks [43, 14, 51].”
• Harmonious Attention Network for Person Re-identification (2018, background): “Most existing person re-id methods focus on supervised learning of identity-discriminative information, including ranking by pairwise constraints [23, 38], discriminative distance metric learning [13, 45, 40, 20, 41, 4], and deep learning [24, 18, 3, 39, 35, 19].”
• Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification (2018, methodology): “According to the used representation forms in matching stage, we roughly divide the existing meth-ods into two groups: feature vector based methods , e.g ., [10, 4, 19, 37, 41, 17, 12, 45, 35]; and feature set or feature sequence based methods , e.g ., [69, 60, 59, 57, 36, 18, 1, 38].”
• See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-identification (2017, positive): “As shown in Figure 2, our model is built upon [23, 28].”
• RGB-Infrared Cross-Modality Person Re-identification (2017, background): “Networks with two inputs similar to two-stream structure are also favorable in Re-ID tasks, for example, Ahmed’s net [1], SIR-CIR net [42], gated siamese net [41], etc.”
• Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification (2018, methodology): “Most existing re-id studies follow the supervised learning paradigm such as optimising pairwise matching distance metrics [20, 52, 57, 49, 54, 47, 50, 5] or deep learning methods [27, 45, 51, 44, 4, 28].”
• Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification (2017, methodology): “[32] use a fully connected layer with a one-dimensional output to learn the value g(xi, xj) as shown Fig.”
• Attention-Aware Compositional Network for Person Re-identification (2018, background): “The first category mainly includes the traditional feature descriptors [53, 52, 51, 27, 7, 31, 35] and deep learning features [43, 41, 42, 12, 25, 40].”
• Person Re-Identification by Deep Joint Learning of Multi-Loss Classification (2017, methodology): “In terms of loss function, the HER model [Wang et al. , 2016b] similarly does not exploit pair-wise re-id labels but defines a single identity label per training person for regression loss (vs. the classification loss in the JLML) based re-id feature embedding optimisation.”
• Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification (2017, methodology): “CUHK03: For the CUHK03 dataset, we compare our method with many existing approaches, including Filter Pair Neural Networks (FPNN) [20], Improved Deep Learning Architecture (IDLA) [1], Cross-view Quadratic Discriminant Analysis (XQDA) [22], PSD constrained asymmetric metric learning (denoted as MLAPG”
• Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification (2017, background): “Recently, deep learning has been adopted to RE-ID community [1, 32, 28, 27] and has gained promising results.”
• CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization (2018, background): “The most widely used loss function in image retrieval task is the max-margin triplet loss [9, 3, 8, 11, 24, 42, 47, 14, 32, 19] that enforces the distances of positive pairs to be less than the distances of negative pairs.”
• AANet: Attribute Attention Network for Person Re-Identifications (2019, background): “[21] proposed to formulate the re-ID problem as a joint learning framework that learns feature representations using not only the query image but also query and gallery image pairs.”
• Person Re-Identification by Camera Correlation Aware Feature Augmentation (2017, background): “Nowadays, deep feature learning for person re-id has attracted increasing attention [26,27,29,56,57,58,59,60,61,62].”
• Person Re-identification by Deep Learning Multi-scale Representations (2017, background): “Existing works focus on designing identity discriminative feature representation [17, 13, 74, 29, 38, 36] or learning matching distance metrics [22, 68, 77, 64, 40, 72, 62, 63, 65, 8] or their combination in a deep learning framework [25, 3, 60, 67, 51, 66].”
• Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies (2017, neutral): “6 SI-CI [75] 52.”