L
Liang Zheng
Researcher at Australian National University
Publications - 179
Citations - 32465
Liang Zheng is an academic researcher from Australian National University. The author has contributed to research in topics: Discriminative model & Image retrieval. The author has an hindex of 58, co-authored 162 publications receiving 21575 citations. Previous affiliations of Liang Zheng include Singapore University of Technology and Design & University of Texas at San Antonio.
Papers
More filters
Proceedings ArticleDOI
Scalable Person Re-identification: A Benchmark
TL;DR: A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset.
Proceedings ArticleDOI
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro
TL;DR: A simple semisupervised pipeline that only uses the original training set without collecting extra data, which effectively improves the discriminative ability of learned CNN embeddings and proposes the label smoothing regularization for outliers (LSRO).
Journal ArticleDOI
Random Erasing Data Augmentation
TL;DR: Random Erasing as mentioned in this paper randomly selects a rectangle region in an image and erases its pixels with random values, which reduces the risk of overfitting and makes the model robust to occlusion.
Book ChapterDOI
Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)
TL;DR: In this paper, a part-based convolutional baseline (PCB) is proposed to learn discriminative part-informed features for person retrieval and two contributions are made: (i) a network named Part-based Convolutional Baseline (PCBB) which outputs a convolutionAL descriptor consisting of several part-level features.
Proceedings ArticleDOI
Re-ranking Person Re-identification with k-Reciprocal Encoding
TL;DR: This paper proposes a k-reciprocal encoding method to re-rank the re-ID results, and hypothesis is that if a gallery image is similar to the probe in the k- Reciprocal nearest neighbors, it is more likely to be a true match.