Person Reidentification Using Spatiotemporal Appearance

By Niloofar Gheissari, Thomas B. Sebastian, Richard I. Hartley. Computer Vision and Pattern Recognition, 2006

643 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/41bef2ef849cb8d1972a63aa360d540b884d99bd

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. Shaogang Gong
5. Tao A. Xiang
6. Xiaogang Wang
7. Xiatian Zhu
8. Shiliang Zhang

In Computer Vision and Pattern Recognition

1. Xiaogang Wang
2. Yi Yang
3. Qi Tian
4. Liang Zheng
5. Luc Van Gool
6. Wanli Ouyang
7. Shaogang Gong
8. Tao A. Xiang

Citations in the corpus

• Joint Detection and Identification Feature Learning for Person Search (2016, background): “Person re-identification (re-id) [8, 38] aims at matching a target person with a gallery of pedestrian images.”
• Learning Discriminative Appearance-Based Models Using Partial Least Squares (2009, background): “Other representations include spatialtemporal appearance modeling [8] and part-based appearance modeling [10].”
• Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-identification (2018, methodology): “[11] designed a spatial-temporal segmentation method to extract visual cues and employed color and salient edges for foreground detection.”
• 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”
• Local Descriptors Encoded by Fisher Vectors for Person Re-identification (2012, background): “The typical features for person re-identification are: color (widely used since the color of clothing constitutes simple but efficient visual signatures) [1], HOG like signatures [2, 3], texture [4–6], differential filters [6], Haar-like filters [7], co-occurrence matrices [3], interest points [8], ”
• Person re-identification by symmetry-driven accumulation of local features (2010, methodology): “Re-identification methods that rely only on visual information are addressed here as appearance-based techniques [2, 3, 6, 8, 9, 12, 15, 19, 20, 21].”
• Embedding Deep Metric for Person Re-identification: A Study Against Large Variations (2016, methodology): “We compare our model with IDLA [1], DeepFeature [6], visual word (visWord) [37], saliency matching (SalMatch), patch matching (PatMatch) [39], ELF [8], PRSVM [3], LMNNR [2], eBiCov [21], local Fisher discriminant analysis (LF) [28], PRDC [43], aPRDC [20], PCCA [25], mid-level filters (mFilter) [41] ”
• A survey of approaches and trends in person re-identification (2014, neutral): “Current work in person Re-ID Re-ID has been a topic of intense research in the past five years [13] [14] [15] [16] [17].”
• Pedestrian Recognition with a Learned Metric (2010, background): “Matching spatio-temporal appearance of segments have been considered by Gheissari et al. [7].”
• Multi-camera activity correlation analysis (2009, background): “Most previous work on multi-camera activity analysis with non-overlapping views focuses on two related issues: (1) object re-identification (inter-camera object tracking) [2, 6, 7, 14] and (2) camera network topology inference [6, 12, 16].”
• Person re-identification by Local Maximal Occurrence representation and metric learning (2014, background): “Many existing person re-identification approaches try to build a robust feature representation which is both distinctive and robust for describing a person's appearance under various conditions [10] [15] [7] [12] [41] [3].”
• An improved deep learning architecture for person re-identification (2015, methodology): “In addition to the methods listed in section 7.2 and 7.1, we compare our method against local Fisher discriminant analysis (LF) [23], PCCA [22], aPRDC [18], PRDC [32], eBiCov [19], LMNNR [1], PRSVM [2], and ELF [7].”
• Relaxed Pairwise Learned Metric for Person Re-identification (2012, background): “[1] try to fit a triangulated graph to each person to cope with pose variations.”
• Person Re-identification by Video Ranking (2014, methodology): “More specifically, the Rank-1 re-id performance of using multi-shot colour feature (MS-Colour) was boosted by 40.7% and 99.4% on PRID 2011 T. Wang et al .”
• Person Re-identification by Attributes (2012, background): “Re-identification Contemporary approaches to re-identification typically exploit low-level features such as colour [16], texture, spatial structure [4], or combinations thereof [5, 19].”
• Unsupervised Salience Learning for Person Re-identification (2013, background): “Several appoaches were developed to handle pose variations [27, 11, 1, 7].”
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks (2016, background): “THE task of person re-identification (re-id) is to match pedestrian images observed from multiple nonoverlapping camera views with varied visual features [2]–[10].”
• Part-based clothing segmentation for person retrieval (2011, methodology): “[5, 10, 11, 14, 18]), and hybrid approaches (e.”