Liwei Wang

Liwei Wang

Auto-generated profile, based on publicly available information

Liwei Wang

National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, People’s Republic of China

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 January 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LWLiwei Wang
Liwei Wang
YLYin Li
Yin Li
JHJing Huang
Jing Huang
SLSvetlana Lazebnik
Svetlana Lazebnik
Image-language matching tasks have recently attracted a lot of attention in the computer vision field. These tasks include image-sentence matching, i.e., given an image query, retrieving relevant sentences and vice versa, and region-phrase matching or visual grounding, i.e., matching a phrase to relevant regions. This paper investigates two-branch neural networks for learning the similarity between these two data modalities. We propose two network structures that produce different output representations. The first one, referred to as an embedding network, learns an explicit shared latent embedding space with a maximum-margin ranking loss and novel neighborhood constraints. Compared to standard triplet sampling, we perform improved neighborhood sampling that takes neighborhood information into consideration while constructing mini-batches. The second network structure, referred to as a similarity network, fuses the two branches via element-wise product and is trained with regression loss to directly predict a similarity score. Extensive experiments show that our networks achieve high accuracies for phrase localization on the Flickr30K Entities dataset and for bi-directional image-sentence retrieval on Flickr30K and MSCOCO datasets.

9 October 2018
Verified
Book Chapter
Closed access
PDF file
ZYZe Yang
Ze Yang
TLTiange Luo
Tiange Luo
DWDong Wang
Dong Wang
ZHZhiqiang Hu
Zhiqiang Hu
JGJun Gao
Jun Gao
LWLiwei Wang
Liwei Wang

20 June 2005 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LWLiwei Wang
Liwei Wang
YZYan Zhang
Yan Zhang
JFJufu Feng
Jufu Feng
We present a new Euclidean distance for images, which we call image Euclidean distance (IMED). Unlike the traditional Euclidean distance, IMED takes into account the spatial relationships of pixels. Therefore, it is robust to small perturbation of images. We argue that IMED is the only intuitively reasonable Euclidean distance for images. IMED is then applied to image recognition. The key advantage of this distance measure is that it can be embedded in most image classification techniques such as SVM, LDA, and PCA. The embedding is rather efficient by involving a transformation referred to as standardizing transform (ST). We show that ST is a transform domain smoothing. Using the face recognition technology (FERET) database and two state-of-the-art face identification algorithms, we demonstrate a consistent performance improvement of the algorithms embedded with the new metric over their original versions.

4 September 2017
Verified
Book Chapter
Closed access
PDF file
JDJia Ding
Jia Ding
ALAoxue Li
Aoxue Li
ZHZhiqiang Hu
Zhiqiang Hu
LWLiwei Wang
Liwei Wang

13 February 2024 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
RLRuichen Li
Ruichen Li
HYHaotian Ye
Haotian Ye
DJDu Jiang
Du Jiang
XWXuelan Wen
Xuelan Wen
CWChuwei Wang
Chuwei Wang
LWLiwei Wang
Liwei Wang

23 October 2015 in Knowledge and Information Systems
Verified
Journal Article
Closed access
PDF file
WZWayne Xin Zhao
Wayne Xin Zhao
SLSui Li
Sui Li
YHYulan He
Yulan He
LWLiwei Wang
Liwei Wang
JWJi-Rong Wen
Ji-Rong Wen
XLXiaoming Li
Xiaoming Li