Jun Zhu

Mr. Jun Zhu


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
1 January 2018 in Annals of Mathematical Sciences and Applications
Verified
Journal Article
Open access
PDF file
JWJianyu Wang
Jianyu Wang
ZZZhishuai Zhang
Zhishuai Zhang
CXCihang Xie
Cihang Xie
YZYuyin Zhou
Yuyin Zhou
VPVittal Premachandran
Vittal Premachandran
AYAlan Yuille
Alan Yuille
International Press of Boston - publishers of scholarly mathematical and scientific journals and books

20 June 2013 in Journal of Signal Processing Systems
Verified
Journal Article
Closed access
PDF file
JZJun Zhu
Jun Zhu
YQYuanyuan Qiu
Yuanyuan Qiu
RZRui Zhang
Rui Zhang
JHJun Huang
Jun Huang
WZWenjun Zhang
Wenjun Zhang

2 May 2014 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
YZYukun Zhu
Yukun Zhu
JZJun Zhu
Jun Zhu
RZRui Zhang
Rui Zhang
Contextual information is widely exploited in state-of-the-art object detection systems, most of which utilize pre-defined spatial relationships (e.g., above, below, next to, etc.). However, we observe that the spatial arrangement manifests heterogeneous statistical distributions for different object class pairs, which suggests mining class-specified prototypes of spatial contexts in a data-driven manner. This paper proposes a novel contrast K-Means clustering algorithm for automatically discovering spatial context prototypes to beyond the pre-defined spatial relationship representation in literature. Based on the learned prototypes, we further construct the spatial context features by using a simple localized soft assignment quantization method. Besides, considering the large number of real object categories that might lead to overcomplicated spatial context features, we propose a feature refinement method based on the number of context occurrences and K-L divergence to efficiently reduce the complexity of our contextual model. The experiment results on PASCAL VOC dataset and SUN 09 dataset demonstrate that our method can effectively capture meaningful spatial context prototypes as well as most contributing contextual features for different object class pairs and thus boost recognition performance on object detection task.

24 October 2013 in Sensors
Verified
Journal Article
Open access
PDF file
JZJun Zhu
Jun Zhu
QZQuan Zhou
Quan Zhou
WZWeijia Zou
Weijia Zou
RZRui Zhang
Rui Zhang
WZWenjun Zhang
Wenjun Zhang
Human action recognition is an increasingly important research topic in the fields of video sensing, analysis and understanding. Caused by unconstrained sensing conditions, there exist large intra-class variations and inter-class ambiguities in realistic videos, which hinder the improvement of recognition performance for recent vision-based action recognition systems. In this paper, we propose a generalized pyramid matching kernel (GPMK) for recognizing human actions in realistic videos, based on a multi-channel “bag of words” representation constructed from local spatial-temporal features of video clips. As an extension to the spatial-temporal pyramid matching (STPM) kernel, the GPMK leverages heterogeneous visual cues in multiple feature descriptor types and spatial-temporal grid granularity levels, to build a valid similarity metric between two video clips for kernel-based classification. Instead of the predefined and fixed weights used in STPM, we present a simple, yet effective, method to compute adaptive channel weights of GPMK based on the kernel target alignment from training data. It incorporates prior knowledge and the data-driven information of different channels in a principled way. The experimental results on three challenging video datasets (i.e., Hollywood2, Youtube and HMDB51) validate the superiority of our GPMK w.r.t. the traditional STPM kernel for realistic human action recognition and outperform the state-of-the-art results in the literature.

25 July 2017 in arXiv
Verified
Preprint
Open access
PDF file
JWJianyu Wang
Jianyu Wang
CXCihang Xie
Cihang Xie
ZZZhishuai Zhang
Zhishuai Zhang
JZJun Zhu
Jun Zhu
LXLingxi Xie
Lingxi Xie
AYAlan Yuille
Alan Yuille
In this paper, we address the task of detecting semantic parts on partially occluded objects. We consider a scenario where the model is trained using non-occluded images but tested on occluded images. The motivation is that there are infinite number of occlusion patterns in real world, which cannot be fully covered in the training data. So the models should be inherently robust and adaptive to occlusions instead of fitting / learning the occlusion patterns in the training data. Our approach detects semantic parts by accumulating the confidence of local visual cues. Specifically, the method uses a simple voting method, based on log-likelihood ratio tests and spatial constraints, to combine the evidence of local cues. These cues are called visual concepts, which are derived by clustering the internal states of deep networks. We evaluate our voting scheme on the VehicleSemanticPart dataset with dense part annotations. We randomly place two, three or four irrelevant objects onto the target object to generate testing images with various occlusions. Experiments show that our algorithm outperforms several competitors in semantic part detection when occlusions are present.