Qi Zou

Qi Zou

Auto-generated profile, based on publicly available information

Qi Zou

Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

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

Representative Publications

View All Publications
1 November 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YPYanting Pei
Yanting Pei
YHYaping Huang
Yaping Huang
QZQi Zou
Qi Zou
XZXingyuan Zhang
Xingyuan Zhang
SWSong Wang
Song Wang
Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep learning neural networks, especially the Convolutional Neural Networks (CNNs). Most of the existing works focused on classifying very clear natural images, evidenced by the widely used image databases such as Caltech-256, PASCAL VOCs and ImageNet. However, in many real applications, the acquired images may contain certain degradations that lead to various kinds of blurring, noise, and distortions. One important and interesting problem is the effect of such degradations to the performance of CNN-based image classification and whether degradation removal helps CNN-based image classification. More specifically, we wonder whether image classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image classification performance. In this paper, we empirically study those problems for nine kinds of degraded images - hazy images, motion-blurred images, fish-eye images, underwater images, low resolution images, salt-and-peppered images, images with white Gaussian noise, Gaussian-blurred images and out-of-focus images. We expect this work can draw more interests from the community to study the classification of degraded images.

12 April 2019 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JLJunbo Liu
Junbo Liu
YHYaping Huang
Yaping Huang
QZQi Zou
Qi Zou
MTMei Tian
Mei Tian
SWShengchun Wang
Shengchun Wang
SRShengwei Ren
Shengwei Ren
Vision-based automatic railway fastener inspection, instead of manual operation, remains a great challenge. Even though many supervised learning-based methods have been developed, expensive training labels and imbalanced data are the main obstacles to leverage the performance of the fastener inspection task. To tackle the problems, we present a novel vision-based fastener inspection system (VFIS) which is inspired by few-shot learning. VFIS can automatically collect and annotate a large number of fastener samples by using the proposed online template matching-based classification method, and it only requires a very small number of annotated fastener templates. Moreover, we employ a similarity-based deep network to solve the problem of the imbalanced dataset. The comprehensive experiments are conducted on a large scale fastener dataset. VFIS yields competitive performance on both fastener localization and fastener classification. Specifically, an average detection rate of 99.36% is achieved for fastener localization, and an average accuracy of 92.69% is achieved for fastener classification. Moreover, for identifying defective fasteners, our proposed method achieves an average precision of 92.63% and an average recall of 92.88%.

19 August 2020 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
RZRunsheng Zhang
Runsheng Zhang
YHYaping Huang
Yaping Huang
MPMengyang Pu
Mengyang Pu
JZJian Zhang
Jian Zhang
QGQingji Guan
Qingji Guan
HLHaibin Ling
Haibin Ling
The goal of our work is to discover dominant objects in a very general setting where only a single unlabeled image is given. This is far more challenge than typical colocalization or weakly-supervised localization tasks. To tackle this problem, we propose a simple but effective pattern mining-based method, called Object Location Mining (OLM), which exploits the advantages of data mining and feature representation of pretrained convolutional neural networks (CNNs). Specifically, we first convert the feature maps from a pre-trained CNN model into a set of transactions, and then discovers frequent patterns from transaction database through pattern mining techniques. We observe that those discovered patterns, i.e., co-occurrence highlighted regions, typically hold appearance and spatial consistency. Motivated by this observation, we can easily discover and localize possible objects by merging relevant meaningful patterns. Extensive experiments on a variety of benchmarks demonstrate that OLM achieves competitive localization performance compared with the state-of-the-art methods. We also evaluate our approach compared with unsupervised saliency detection methods and achieves competitive results on seven benchmark datasets. Moreover, we conduct experiments on finegrained classification to show that our proposed method can locate the entire object and parts accurately, which can benefit to improving the classification results significantly.

20 February 2020 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
XXXixia Xu
Xixia Xu
QZQi Zou
Qi Zou
XLXue Lin
Xue Lin
YHYaping Huang
Yaping Huang
YTYi Tian
Yi Tian
Both accuracy and efficiency are of equal importance to the human pose estimation. Most of the existing methods simply pursue excellent performance, sacrificing massive computing resources and memory. Out of this consideration, we present a novel compact and lightweight framework to train more efficient estimators using knowledge distillation. Three distillation mechanisms are proposed in our method from different perspectives, including logit distillation, feature distillation and structure distillation. Concretely, the logit distillation regards the output of teacher model as soft target to stimulate the student model. The feature distillation distills the high-level features of the teacher model to assist the student. Unlike the above strategies, the structure distillation considers the problem in a global view, aiming at ensuring the student prediction contains quite abundant structure knowledge like the teacher. We empirically demonstrate the effectiveness and efficiency of our methods on two multi-person pose estimation datasets (COCO and MPII). Specifically, our model can achieve competitive performance with the most state-of-the-art methods and consume only 35% model parameters and GFLOPs of our baseline (SimpleBaseline-ResNet-50) on the COCO dataset.

10 April 2020 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XLXue Lin
Xue Lin
QZQi Zou
Qi Zou
XXXixia Xu
Xixia Xu
YHYaping Huang
Yaping Huang
YTYi Tian
Yi Tian
Video prediction is challenging, due to the pixel-level precision requirement and the difficulty in capturing scene dynamics. Most approaches tackle the problems by pixel-level reconstruction objectives and two decomposed branches, which still suffer from blurry generations or dramatic degradations in long-term prediction. In this paper, we propose a Motion-Aware Feature Enhancement (MAFE) network for video prediction to produce realistic future frames and achieve relatively long-term predictions. First, a Channel-wise and Spatial Attention (CSA) module is designed to extract motion-aware features, which enhances the contribution of important motion details during encoding, and subsequently improves the discriminability of attention map for the frame refinement. Second, a Motion Perceptual Loss (MPL) is proposed to guide the learning of temporal cues, which benefits to robust long-term video prediction. Extensive experiments on three human activity video datasets: KTH, Human3.6M, and PennAction demonstrate the effectiveness of the proposed video prediction model compared with the state-of-the-art approaches.

6 November 2020 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
XZXing-Yuan Zhang
Xing-Yuan Zhang
YHYa-Ping Huang
Ya-Ping Huang
YMYang Mi
Yang Mi
YPYan-Ting Pei
Yan-Ting Pei
QZQi Zou
Qi Zou
SWSong Wang
Song Wang