Person Re-identification by Video Ranking

By Taiqing Wang, Shaogang Gong, Xiatian Zhu, Shengjin Wang. European Conference on Computer Vision, 2014

617 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9a828410bcbe584d2503a8efb36f756a240a0425

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. Mang Ye
6. Zhedong Zheng
7. Pong Chi Yuen
8. Xiatian Zhu

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Liang Zheng
3. Qi Tian
4. Luc Van Gool
5. Xiaogang Wang
6. Ling Shao
7. Dacheng Tao
8. Tao A. Xiang

Citations in the corpus

• Person Re-identification: Past, Present and Future (2016, methodology): “As suggested by [105], extracting features within a walking cycle is a good practise, so generating long tracking sequences may not bring much re-ID improvement.”
• Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification (2015, methodology): “In terms 2We do not compare with DVR [41] that uses 89 persons for testing. of the accuracy at rank 1 and rank 5, our approach achieves a matching rate 18% at rank 1 and 37.4% at rank 5, respectively, leading to a 3.5% and 3.1% performance gain over KCCA.”
• Person Re-identification in the Wild (2016, methodology): “For metric learning algorithms, the 4 tested methods are KISSME [26], XQDA [1], DVR [41] and the Discriminative Null Space (DNS) [25].”
• Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “The query person can be represented by an image [4], [5], a video sequence [6], [7], and even a text description [8], [9].”
• Deep Attributes Driven Multi-Camera Person Re-identification (2016, background): “Currently, research on this topic mainly focus on two aspects: a) extracting and coding local invariant features to represent the visual appearance of a person [1,2,3,4,5,6] and b) learning a discriminative distance metric hence the distance of features from the same person can be smaller [7,8,9,10,”
• Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification (2018, methodology): “As for feature design, previous works design and use a variety of customized features, including histogram features from various color and texture channels [24], [25], symmetry-driven accumulation of local features [26], features from body parts with pictorial structures [27] to estimate human body ”
• Unsupervised Person Re-identification (2017, background): “These works typically deal with the relatively small datasets [16], [17] and to our knowledge, none of these works are integrated into the deep learning framework that has been proven as the state of the art under the large-scale datasets [2], [8], [18], [19].”
• Robust Anchor Embedding for Unsupervised Video Person re-IDentification in the Wild (2018, methodology): “Three publicly available video re-ID datasets are selected for evaluation: two small-scale datasets, PRID-2011 dataset [12], iLIDS-VID dataset [39] and one large-scale MARS dataset [53].”
• Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras (2017, background): “Although there are several public databases for person identification research such as the CUHK01 [49] and CUHK03 databases [50], the VIPeR database [51], the iLIDS-VID database [52], and the PRID2011 database [53], these databases cannot be used in our research because they contain only visible lig”
• Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification (2019, background): “Partial-iLIDS is derived from iLIDS [24], which is collected in an airport and the lower-body of a pedestrian is frequently occluded by the luggage.”
• Mixed High-Order Attention Network for Person Re-Identification (2019, background): “Person ReID & Attention Mechanism: Person ReID intends to correctly match images of pedestrians across videos captured from different cameras, it has been widely studied, such as ranking by pairwise constraints [34, 48], metric learning [54, 51], deep embedding learning [63, 43], re-ranking [62, 16]”
• Person Re-Identification by Camera Correlation Aware Feature Augmentation (2017, neutral): “[35], [36], [37], [38], [39], [40], [41], [42], [43] dominate cur-”
• Person Re-Identification by Deep Joint Learning of Multi-Loss Classification (2017, methodology): “Specifically, the JLML method is related to the saliency learning based models [Zhao et al. , 2013; Wang et al. , 2014a] in terms of modelling localised part importance.”
• MARS: A Video Benchmark for Large-Scale Person Re-Identification (2016, methodology): “This paper, among a few contemporary works [25, 29, 36, 38, 41], makes initial attempts on video-based re-identification.”
• Deep feature learning with relative distance comparison for person re-identification (2015, methodology): “All the images were resized to 250 100 pixels to train our network: iLIDS dataset: The iLIDS dataset [26] was constructed from video images captured in a busy airport arrival hall.”