Learning Mid-level Filters for Person Re-identification

By Rui Zhao, Wanli Ouyang, Xiaogang Wang. 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

568 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3fd7bfd90f0dfc3369bfe718e27aff30cf268c23

How researchers see this paper

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

In Biomedical Engineering

1. Yi Yang
2. Liang Zheng
3. Qi Tian
4. Zhedong Zheng
5. Shaogang Gong
6. Shiliang Zhang
7. Tao A. Xiang
8. Xiatian Zhu

In Computer Vision and Pattern Recognition

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

Citations in the corpus

• Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification (2015, methodology): “We first compare our approach with 8 completing methods for multi-short re-identification: Salience Matching (Salmatch) [47], Learning Mid-level Filters (LMF) [48], Multi-short Symmetry-driven Accumulation of Local Features (MS-SDALF) [12], Multi-short color with RankSVM (MS-color+RSVM) [41], Multi-”
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks (2016, methodology): “exploring the partial area under the ROC curve (pAUC) score [4].”
• Multi-scale Deep Learning Architectures for Person Re-identification (2017, methodology): “We compare with the deep learning based methods including DeepReID [27], Imp-Deep [1], En-Deep [55], and G-Dropout [48], Gated Sia [50], EMD [44], SI-CI [51], and MSTC 2 [36], as well as other non-deep competitors, such as Mid-Filter [62], and XQDA [32], LADF [31], eSDC [61], LMNN [16], and LDM [14]”
• A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification (2019, background): “They mainly focus on designing feature representations (Zhao, Ouyang, and Wang 2014) or learning robust distance metrics (Zheng, Gong, and Xiang 2011; Liao et al. 2015).”
• Person Re-Identification by Camera Correlation Aware Feature Augmentation (2017, background): “In current person re-id literature, the best performers are discriminative learning basedmethods [2], [3], [4], [5], [6], [7],”
• Learning to rank in person re-identification with metric ensembles (2015, methodology): “Since a better rank-1 recognition rate is often preferred [47], our aim is to improve the recognition rate among the k best candidates, e.”
• Person re-identification by Local Maximal Occurrence representation and metric learning (2014, methodology): “For feature representation, several effective approaches have been proposed , for example, the ensemble of local features (ELF) [10], SDALF [2], kBiCov [33], fisher vectors (LDFV) [32], salience match [46], and mid-level filter [48].”
• Unsupervised Person Re-identification (2017, background): “Gray and Tao [28] use 8 color channels and 21 texture filters on the luminance channel, and the pedestrian is partitioned into horizontal stripes.”
• Pose Transferrable Person Re-identification (2018, methodology): “Recently, DCNN is widely used in the filed of ReID [44, 19, 36, 4, 6, 55, 48].”
• Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification (2016, methodology): “[46, 47, 48] proposed to combine SIFT features with color histogram as features.”
• Mask-Guided Contrastive Attention Model for Person Re-identification (2018, methodology): “In the testing phase, following the same setting of [46], 3,368 hand-drawn person images are selected as probe set to query the correct identities across the testing set.”
• Deeply-Learned Part-Aligned Representations for Person Re-identification (2017, background): “Person attributes or salient patterns, such as female/male, wearing hat or not, have also been exploited to distinguish persons [40, 41, 61].”
• Learning a Discriminative Null Space for Person Re-identification (2016, methodology): “We randomly partition the dataset into 485 people for training and 486 for testing (multi-shot) following [22, 41], again over 10 trials.”
• Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification (2015, background): “[18], salience match [30], mid-level filter [32], local fisher discriminant analysis (LF) [22], to name a few.”
• Deep feature learning with relative distance comparison for person re-identification (2015, methodology): “Comparison on VIPeR dataset Using the VIPeR dataset, we compared our method with such state-of-the-art methods as MtMCML [30], LMLF [13], SDALF [5], eBiCov [31], eSDC [32], PRDC [9], aPRDC [33], PCCA [14], KISSME [34], LF [35] and SalMatch [36].”
• Beyond frontal faces: Improving Person Recognition using multiple cues (2015, background): “Existing work is mainly focused on metric learning [27, 17, 22] and mid-level feature learning [16, 39, 40, 10, 20, 26].”