Huizhu Jia

Huizhu Jia

Auto-generated profile, based on publicly available information

Huizhu Jia

School of Computer Science, Peking University, Beijing, China

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
12 June 2020 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
FYFan Yang
Fan Yang
KYKe Yan
Ke Yan
SLShijian Lu
Shijian Lu
HJHuizhu Jia
Huizhu Jia
DXDon Xie
Don Xie
WGWen Gao
Wen Gao
Unsupervised domain adaptation (UDA) aims to mitigate the domain shift that occurs when transferring knowledge from a labeled source domain to an unlabeled target domain. While it has been studied for application in unsupervised person re-identification (ReID), the relations of feature distribution across the source and target domains remain underexplored, as they either ignore the local relations or omit the in-depth consideration of negative transfer when two domains do not share identical label spaces. In light of the above, this paper presents an innovative part-aware progressive adaptation network (PPAN) that exploits global and local relations for UDA-based ReID across domains. A multi-branch network is developed that explicitly learns discriminative feature representation from both whole-body images and body-part images under the supervision of a labeled source domain. Within each network branch, an independent UDA constraint is designed that aligns the global and local feature distributions from a labeled source domain with those of an unlabeled target domain. In addition, a novel progressive adaptation strategy (PAS) is designed that effectively alleviates the negative influence of outlier source identities. The proposed unsupervised ReID model is evaluated on five widely used datasets (Market-1501, DukeMTMC-reID, CUHK03, VIPeR and PRID), and experimental results demonstrate its superior robustness and effectiveness relative to state-of-the-art approaches.

16 August 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
WGWen Gao
Wen Gao
SMSiwei Ma
Siwei Ma
LDLingyu Duan
Lingyu Duan
YTYonghong Tian
Yonghong Tian
Peiyin XingPeiyin Xing
Peiyin Xing
THTiejun Huang
Tiejun Huang
The ubiquitous camera networks in the city brain system grow at a rapid pace, creating massive amounts of images and videos at a range of spatial-temporal scales and thereby forming the “biggest” big data. However, the sensing system often lags behind the construction of the fast-growing city brain system, in the sense that such exponentially growing data far exceed today’s sensing capabilities. Therefore, critical issues arise regarding how to better leverage the existing city brain system and significantly improve the city-scale performance in intelligent applications. To tackle the unprecedented challenges, we articulate a vision towards a novel visual computing framework, termed as digital retina , which aligns high-efficiency sensing models with the emerging Visual Coding for Machine (VCM) paradigm. In particular, digital retina may consist of video coding, feature coding, model coding, as well as their joint optimization. The digital retina is biologically-inspired, rooted on the widely accepted view that the retina encodes the visual information for human perception, and extracts features by the brain downstream areas to disentangle the visual objects. Within the digital retina framework, three streams, i.e., video stream, feature stream, and model stream, work collaboratively over the end-edge-cloud platform. In particular, the compressed video stream serves for human vision, the compact feature stream targets for machine vision, and the model stream incrementally updates deep learning models to improve the performance of human/machine vision tasks. We have developed a prototype to demonstrate the technical advantages of digital retina, and extensive experiments have been conducted to validate that it is able to effectively support the video big data analysis and retrieval in the intelligent city system. In particular, up to $7000\times $ compression ratio could be realized for visual data compression while maintaining competitive performance with pristine signal in a series of visual analysis tasks.

15 October 2021 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
CMCong Ma
Cong Ma
FYFan Yang
Fan Yang
YLYuan Li
Yuan Li
HJHuizhu Jia
Huizhu Jia
XXXiaodong Xie
Xiaodong Xie
WGWen Gao
Wen Gao

26 October 2021 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
GXGuoqing Xiang
Guoqing Xiang
XZXinfeng Zhang
Xinfeng Zhang
XHXiaofeng Huang
Xiaofeng Huang
FYFan Yang
Fan Yang
CZChuang Zhu
Chuang Zhu
XXXiaodong Xie
Xiaodong Xie
Rate control is an important technique for practical video coding applications by allocating suitable quantization parameters (QPs) for CTUs or frames to satisfy bandwidth requirement. However, rate control may result in video quality fluctuation because neighboring regions are quantized into different quality levels, which may affect viewing experience seriously, especially at low bitrate scenarios. In this paper, we propose a novel CTU (Coding Tree Unit) level rate control approach for intra frame of the high efficiency video coding (HEVC) standard with consistent perceptual quality. In particular, a new perceptual hyperbolic rate distortion (R-D) optimization method is proposed for rate control with the constraint of constant perceptual quality, which shows good compatibility with other R-D models. Herein, a novel CTU level perceptual distortion model is presented to achieve the optimal rate control of intra frames for HEVC, where the Lagrange multiplier is adjusted by taking advantage of the different perceptual characteristics to achieve the minimal perceptual distortion variation across CTUs within one frame. Extensive experiments prove that the proposed algorithm outperforms the state-of-the-art CTU level rate control methods by considering R-D performance. In addition, subjective simulation results demonstrate that our algorithm further improves the visual quality of compressed videos by reducing perceptual quality fluctuation.

1 March 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
YHYi Hou
Yi Hou
SZShanghang Zhang
Shanghang Zhang
RMRui Ma
Rui Ma
HJHuizhu Jia
Huizhu Jia
XXXiaodong Xie
Xiaodong Xie
Since video data contains temporal information, video crowd counting demonstrates more potential than single-frame crowd counting for scenarios requiring high accuracy. However, learning robust relationships among frames efficiently and cheaply is very challenging. Existing methods for video crowd counting lack explicit temporal correlation modeling and robustness, and they are complex. In this paper, we propose the Frame-Recurrent Video Crowd Counting (FRVCC) framework to solve these issues. Specifically, we design a frame-recurrent manner to recursively relate the density maps in the temporal dimension, which efficiently explores long-term inter-frame knowledge and ensures the continuity of feature map responses. FRVCC consists of three plug-in modules: an optical flow estimation module, a single-frame counting module, and a density map fusion module. For the fusion module, we propose the ResTrans network to robustly learn complementary features between visual-based and correlation-based feature maps through residual strategy and vision transformer. To constrain the output distribution to be consistent with the ground truth distribution, we introduce an adversarial loss to rectify the training process. Additionally, we release a large-scale synthetic video crowd-counting dataset, CrowdXV, to evaluate the proposed method and further improve its performance. We have conducted extensive experiments on several video-counting datasets. The results demonstrate that FRVCC achieves state-of-the-art performance and, concurrently, high generalization, high flexibility, and less complexity.

23 May 2022
Verified
Conference Paper
Open access
YHYi Hou
Yi Hou
CLChengyang Li
Chengyang Li
YLYuheng Lu
Yuheng Lu
LZLiping Zhu
Liping Zhu
YLYuan Li
Yuan Li
XXXiaodong Xie
Xiaodong Xie
In this article, we propose a simulated crowd counting dataset CrowdX, which has a large scale, accurate labeling, parameterized realization, and high fidelity. The experimental results of using this dataset as data enhancement show that the performance of the proposed streamlined and efficient benchmark network ESA-Net can be improved by 8.4%. The other two classic heterogeneous architectures MCNN and CSRNet pre-trained on CrowdX also show significant performance improvements. Considering many influencing factors determine performance, such as background, camera angle, human density, and resolution. Although these factors are important, there is still a lack of research on how they affect crowd counting. Thanks to the CrowdX dataset with rich annotation information, we conduct a large number of data-driven comparative experiments to analyze these factors. Our research provides a reference for a deeper understanding of the crowd counting problem and puts forward some useful suggestions in the actual deployment of the algorithm.