Evaluating Appearance Models for Recognition, Reacquisition, and Tracking

By Douglas T. Gray, Shane Brennan, Hai Tao. 2007

1,183 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/7847b1fbccadb780b655e72c66d3f9e93ddb880c

How researchers see this paper

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

1. Liang Zheng
2. Yi Yang
3. Xiaogang Wang
4. Wanli Ouyang
5. Tao A. Xiang
6. Mang Ye
7. Zhedong Zheng
8. Xiatian Zhu

Citations in the corpus

• Deep Metric Learning for Person Re-identification (2014, methodology): “Five popular databases were built for person reidentification: VIPeR [4], i-LIDS [20], ETHZ [21], CIVAR [22] and CUHK Campus [5].”
• Deep Attributes Driven Multi-Camera Person Re-identification (2016, methodology): “(a) VIPeR [24], (b) PRID [25], and (c) GRID [26].”
• Deeply-Learned Part-Aligned Representations for Person Re-identification (2017, background): “This dataset [14] contains two views of 632 persons.”
• Brownian descriptor: A rich meta-feature for appearance matching (2014, methodology): “The results are analyzed in terms of recognition rate, using the cumulative matching characteristic (CMC) curve [12].”
• Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-identification (2018, methodology): “We first pretrain the ResNet-50 model on image-based person re-identification datasets, including CUHK01 [23], CUHK03 [24], 3DPeS [3], VIPeR [12], DukeMTMC-reID [51] and CUHK-SYSU [44]. and then fine-tune it on PRID2011, iLIDS-VID and MARS training sets.”
• Deep Relative Distance Learning: Tell the Difference between Similar Vehicles (2016, methodology): “In this part, we adopted the widely used cumulative match curve(CMC) approach[6] in person re-identification problem and performed the vehicle re-identification experiments on “VehicleID” dataset.”
• Pose-Driven Deep Convolutional Model for Person Re-identification (2017, methodology): “Finally, we combine the augmented training images of VIPeR, training images of CUHK 03 and Market 1501 together, as the final training set.”
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval (2017, methodology): “VIPeR [10] is smaller than Market1501 and CUHK03.”
• MARS: A Video Benchmark for Large-Scale Person Re-Identification (2016, methodology): “In the MARS dataset, we stick to the cross-camera search mode as in previous datasets [12, 23, 43], i.”
• Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function (2016, background): “Given a query person’s image, in order to find the correct matches among a large set of candidate images captured by different cameras, two crucial problems must be addressed.”
• Person Search with Natural Language Description (2017, methodology): “We collected 40,206 images of 13,003 persons from five existing person re-identification datasets, CUHK03 [22], Market-1501 [42], SSM [38], VIPER [9], and CUHK01 [21], as the subjects for language descriptions.”
• Embedding Deep Metric for Person Re-identification: A Study Against Large Variations (2016, methodology): “entication rates on CUHK01 (a) and VIPeR (b). Fig.10. Some failed cases on CUHK01 by the proposed method. Left: true gallery. Middle: probe. Right: false positive. 4.7 Performance on VIPeR The VIPeR [9] data set includes 632 subjects, each of which has 2 images from two dierent cameras. Although VIP”
• Color Invariants for Person Reidentification (2013, methodology): “The Hist and PartsSC used without segmenting the silhouette from the background outperform the best baseline approach reported in [41]—the hand-localized histogram.”
• Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification (2017, methodology): “Instead, we conduct cross-dataset evaluation from the pretrained model on the Market1501, CUHK03 and MARS datasets to the VIPeR dataset.”
• An improved deep learning architecture for person re-identification (2015, result): “We also report results on the VIPeR data set [8].”
• Person re-identification by Local Maximal Occurrence representation and metric learning (2014, background): “(a) Example pairs of images from the VIPeR database [9].”