Person re-identification by symmetry-driven accumulation of local features

By Michela Farenzena, Loris Bazzani, Alessandro Perina, Vittorio Murino, Marco Cristani. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

1,654 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ff0a68bcbf72e35c70510ffba07f13ea585e98b4

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

Citations in the corpus

• Person re-identification by probabilistic relative distance comparison (2011, background): “Most existing studies have tried to address the above problems by seeking a more distinctive and stable feature representation of people’s appearance, ranging widely from color histogram [10, 7], graph model [4], spatial cooccurrence representation model [14], principal axis histogram [8], rectangle”
• Clothing Attributes Assisted Person Reidentification (2015, methodology): “In reidentification, the AIR is combined with symmetry-driven accumulation of local features (SDALF) [6], while our approach still use the features of Zheng et al. [7].”
• Beyond frontal faces: Improving Person Recognition using multiple cues (2015, background): “Existing work is mainly focused on metric learning [27, 17, 22], mid-level feature learning [16, 39, 40, 10, 20, 26].”
• 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].”
• Knowledge Distillation for End-to-End Person Search (2019, neutral): “Earlier approaches have focused on manual feature design [17, 22, 51, 65] and metric learning [26, 32, 33, 34, 38, 40, 66].”
• Custom Pictorial Structures for Re-identification (2011, methodology): “4(a) shows that PS performs slightly worse than SCR, but better than SDALF and the Contextbased strategy (Cbased) of [26], which is learning-based.”
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks (2016, methodology): “Farenzena et al. [11] propose the symmetry-driven accumulation of local features (SDALF) which exploits both symmetry and asymmetry, and represents each part of a person by a weighted color histogram, maximally stable color regions and texture information.”
• Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification (2017, background): “Model SDALF CPS UDML GL GTS SDC CAMEL [8] [7] [24] [12] [29] [35]”
• 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].”
• Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification (2017, methodology): “A majority of recent works mainly develop their solutions from two aspects: extracting reliable feature representations [28, 6, 11, 19, 15, 38] or learning a robust distance metric [14, 41, 2, 30, 36, 37, 21, 13].”
• Dissimilarity-based people re-identification and search for intelligent video surveillance (2013, methodology): “13 Comparison of the best performing score combination rule with two state-of-the art methods, CPS [28] and SDALF [45], in terms of CMC curve attained on the iLIDS data set (MvsM scenario).”
• Locally Aligned Feature Transforms across Views (2013, result): “But when learning the discriminative metric in 4Notice that PS [2] and SDALF [5] are the only published results on CAVIAR.”
• Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification (2017, neutral): “r = 1 r = 5 r = 10 r = 20 r = 1 r = 5 r = 10 r = 20 r = 1 r = 5 r = 10 r = 20 SDALF [8] 5.”
• Deep Metric Learning for Person Re-identification (2014, background): “The most popular features include HSV color histogram [8], [5], LAB color histogram [9], SIFT [9], LBP histogram [5], Gabor features [5] and their fusion.”
• Scalable Person Re-identification on Supervised Smoothed Manifold (2017, background): “Current research interests can be coarsely divided into two mainstreams: 1) those focus on designing robust visual descriptors [55, 13, 37, 26, 64] to accurately model the appearance of person; 2) those seek for a discriminative metric [65, 25, 54, 28, 18], under which instances of the same identity”
• Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification (2015, methodology): “As for feature design, different kinds of features have been tailored and employed in previous work, including histogram features from various color and textture channels [15, 49], symmetry-driven accumulation of local features [12], features from body parts with pictorial structures [9] to estimate”