Person Re-identification: What Features Are Important?

By Chunxiao Liu, Shaogang Gong, Chen Change Loy, Xinggang Lin. ECCV Workshops, 2012

315 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4fca83b685a6523f167da5cbe59a51e6b09db61e

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. Liang Zheng
2. Yi Yang
3. Qi Tian
4. Shiliang Zhang
5. Xiaogang Wang
6. Zhedong Zheng
7. Wen Gao
8. Chi Su

In Computer Vision and Pattern Recognition

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

Citations in the corpus

• Salient Color Names for Person Re-identification (2014, methodology): “Similar to [15], we partition an image into six horizontal stripes of equal size, as is shown in Fig.”
• Person Re-identification: Past, Present and Future (2016, background): “[49] propose discovering some pedestrian prototypes with common attributes in an unsupervised manner and adaptively determine the feature weights of different query person according to the prototypes.”
• Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification (2018, unknown): “[28] fuse them by learning person-specific weights.”
• Deep Representation Learning With Part Loss for Person Re-Identification (2017, background): “Existing approaches conquer this challenge by either seeking discriminative metrics [1], [2], [3], [4], [5], [6], [7], [8], [2], [9], [10], [11], or generating discriminative features [12], [13], [14], [15], [16], [17], [18], [19].”
• Re-id: Hunting Attributes in the Wild (2014, unknown): “[22] 0.”
• DeepReID: Deep Filter Pairing Neural Network for Person Re-identification (2014, background): “All the key components are jointly optimized to maximize the strength of each component when cooperating with others.”
• Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification (2015, background): “[34] learn person-specific weights to fuse multiple features to improve the description power of multiple features.”
• People reidentification in surveillance and forensics (2013, methodology): “The selection of important features is then processed by a machine learning algorithm in an explicit [Liu et al. 2012] or implicit way [Li et al. 2012; Zheng et al. 2012].”
• Unsupervised Salience Learning for Person Re-identification (2013, methodology): “The compared methods includes the classical metric learning approaches, such as LMNN [29], and ITML [29], and their variants modified for person re-identification, such as PRDC [29], attribute PRDC (denoted as aPRDC) [19], and PCCA [24].”
• Person Re-identification by Salience Matching (2013, methodology): “PRDC [23], LMNNR [4], PCCA [18], and attribute-based PRDC (aPRDC) [13], a boosting approach (ELF) [8] and Rank SVM (RankSVM) [19].”
• 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].”
• Distilled Person Re-Identification: Towards a More Scalable System (2019, background): “Person Reidentification has witnessed a fast growing development in recent years, from feature design [19, 15, 32, 31, 35, 69, 58] to distance metric learning [54, 19, 43, 25, 67, 36, 41, 30, 58, 33, 38, 31, 9, 68, 60, 63, 69, 29, 52, 6] and end-to-end deep learning [28, 1, 55, 57, 49, 22, 64, 65, 7”
• Joint Learning of Single-Image and Cross-Image Representations for Person Re-identification (2016, methodology): “We report the CMC curves and rank−1 accuracies of local Fisher discriminant analysis (LF) [29], pairwise constrained component analysis (PC− CA) [28], aPRDC [23], PRDC [43], enriched BiCov (eBi− Cov) [25], PRSVM [2], and ELF [10], saliency matching (SalMatch) [40], patch matching (PatMatch) [40], lo”
• Dissimilarity-based people re-identification and search for intelligent video surveillance (2013, background): “Many appearance descriptors use global colour histograms, to represent the whole body appearance [13, 73, 86] or the overall appearance of each body part [6, 14, 15, 16, 45, 55, 58, 78, 110, 133, 140].”
• Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification (2017, background): “tation learning [11, 19, 15, 38], distance metric learning [14, 41, 30, 36, 37, 21] and CNN-based schemes [33, 32, 24, 25].”
• Learning Mid-level Filters for Person Re-identification (2014, methodology): “Existing person re-identification approaches work on three aspects: distance learning [29, 4, 12, 18, 30, 16, 14], feature design and selection [5, 3, 17, 15, 28, 7, 20, 25], and mid-level feature learning [11, 22, 10, 13].”
• A survey of approaches and trends in person re-identification (2014, unknown): “The idea that certain features canbemore important thanothers is explored in [80].”