Locally Aligned Feature Transforms across Views

By Wei Li, Xiaogang Wang. 2013

614 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Faceless Person Recognition: Privacy Implications in Social Media (2016, background): “Like other areas of computer vision, the last years have seen a shift from classifiers based on handcrafted features and metric learning approaches [13, 14, 15, 16, 17, 18, 19] towards methods based on deep learning [20, 21, 22, 23, 24, 25, 26, 27].”
Person Recognition in Personal Photo Collections (2015, background): “Both settings have seen a recent shift from sophisticated classifiers based on hand-crafted features and metric learning approaches [20, 7, 5, 29, 26, 41, 1], towards methods based on deep learning [37, 36, 43, 33, 27, 38, 21].”
Human Semantic Parsing for Person Re-identification (2018, methodology): “In addition to these datasets that were used in evaluation, we utilize 3DPeS [4], CUHK01 [23], CUHK02 [22], PRID [17], PSDB [41], Shinpuhkan [20] and VIPeR [15] datasets to augment our training data.”
Person re-identification by Local Maximal Occurrence representation and metric learning (2014, background): “In [21], local experts were considered to learn a common feature space for person re-identification across views.”
End-to-End Deep Learning for Person Search (2016, background): “Many person reidentification datasets have emerged in recent years, including VIPeR [9], ETHZ [29], i-LIDS [39], PRID2011 [13], RGB-D [2], GRID [22], CUHK01 [17], CUHK02 [16], and Multi-Camera Surveillance Database [3].”
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification (2014, methodology): “The purpose of person re-identification is to match pedestrians observed in non-overlapping camera views with visual features [13, 9, 35, 1, 7, 3, 51, 20, 19, 16, 29, 26, 24, 48, 2, 41].”
Online Multi-Object Tracking with Dual Matching Attention Networks (2018, background): “In numerous public person re-identiﬁcation datasets (e.g., [31,30,32]), pedestrians given by manually annotated bounding boxes are well separated.”
Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function (2016, methodology): “Features that have been used for the person re-id task include color histograms and their variants [41, 20, 21, 28, 23, 46], local binary patterns(LBP) [41, 20, 21, 28, 23, 46], Gabor features [23], color names [44], and other visual appearance or contextual cues [3].”
Patch-based Knowledge Distillation for Lifelong Person Re-Identification (2022, background): “It consists of twelve ReID datasets, including five seen datasets (Market-1501 [73], CUHK-SYSU [64], DukeMTMC-reID [48], MSMT17_V2 [61] and CUHK03 [32]) for non-forgetting evaluation and seven unseen datasets (VIPeR [16], PRID [22], GRID [39], iLIDS [74], CUHK01 [31], CUHK02 [30] and SenseReID [70])”
Scalable Person Re-identification: A Benchmark (2015, background): “Datasets Market-1501 RAiD [5] CUHK03 [20] VIPeR [10] i-LIDS [44] OPeRID [22] CUHK02 [19] CAVIAR [4]”
Deep Transfer Learning for Person Re-Identification (2016, neutral): “Five widely used datasets are used including two large datasets (CUHK03 [19] and Market1501 [20]) and three small ones (VIPeR [21], PRID [27] and CUHK01 [28]).”
Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification (2016, background): “Images in CUHK01 [21] and CUHK03 [23] are captured on campus, where many students wear backpacks.”
Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification (2017, background): “Many hand-crafted features are proposed to capture visual features for pedestrians [1,5,6,12,16,28].”
Unsupervised Salience Learning for Person Re-identification (2013, background): “Li and Wang [17] partitioned the image spaces of two camera views into different configurations and learned different metrics for different locally aligned common feature spaces.”
Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion (2017, methodology): “As for the feature learning step, traditional features [5, 6, 12, 14, 17, 21, 33] are widely used in existing pipelines.”
Person Re-identification by Video Ranking (2014, background): “There are also attempts on training an appearance model from image sets [32] or by selecting best pairs [28].”
Lifelong Person Re-Identification via Adaptive Knowledge Accumulation (2021, methodology): “Specifically, we first merge VIPeR [6], PRID [8], GRID [25], i-LIDS [41], CUHK01 [17], CUHK02 [16], SenseReID [50] in accordance with their original train/test splits as a new benchmark.”
Pedestrian Alignment Network for Large-scale Person Re-Identification (2017, methodology): “C V ] 3 J u l 2017 tings, the hand-drawn bounding boxes, existing in some previous datasets such as VIPER [Gray et al., 2007], CUHK01 [Li et al., 2012] and CUHK02 [Li and Wang, 2013], are infeasible to acquire when millions of bounding boxes are to be generated.”
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.”
Person Re-identification: Past, Present and Future (2016, methodology): “A number of datasets for image-based re-ID have been released, and some commonly used datasets are summarized in Table 3 [16], [36], [44], [82], [83], [84], [85], [86], [87], [88], [89], [90] for image-based re-ID. and testing sets.”