Jincai Chen

Dr. Jincai Chen

Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan 430074, 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
1 March 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
RWRui Wang
Rui Wang
YHYixue Hao
Yixue Hao
LHLong Hu
Long Hu
Jincai ChenJincai Chen
Jincai Chen
Min ChenMin Chen
Min Chen
DWDi Wu
Di Wu
Due to the expensive and laborious annotations of labeled data required by fully-supervised learning in the crowd counting task, it is desirable to explore a method to reduce the labeling burden. There exists a large number of unlabeled images in the wild that can be easily obtained compared to labeled datasets. Based on the characteristics of consistent spatial transformation with the annotations of heads and image, this paper proposes a self-supervised learning framework with unlabeled and limited labeled data for pre-training and fine-tuning crowd counting model (SSL-FT). It includes an online network and a target network that receive the same image but are randomly processed by two defined augmentation transformations. We leverage unlabeled data to pre-train the online network based on a self-supervised loss and small-scale labeled data to transfer the model to a specific domain based on a fully-supervised loss. We demonstrate the effectiveness of the SSL-FT on four public datasets including ShanghaiTech PartA, PartB, UCF-QNRF and WorldExpo'10 utilizing a classical counting model. Experimental results show that our approach performs better than state-of-art semi-supervised methods.

28 January 2025 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
CSChao Sun
Chao Sun
Min ChenMin Chen
Min Chen
CZChuanbo Zhu
Chuanbo Zhu
SZSheng Zhang
Sheng Zhang
PLPing Lu
Ping Lu
Jincai ChenJincai Chen
Jincai Chen
In real-world physiological and psychological scenarios, there often exists a robust complementary correlation between audio and visual signals. Audio-Visual Event Localization (AVEL) aims to identify segments with Audio-Visual Events (AVEs) that contain both audio and visual tracks in unconstrained videos. Prior studies have predominantly focused on audio-visual cross-modal fusion methods, overlooking the fine-grained exploration of the cross-modal information fusion mechanism. Moreover, due to the inherent heterogeneity of multi-modal data, inevitable new noise is introduced during the audio-visual fusion process. To address these challenges, we propose a novel Cross-modal Contrastive Learning Network (CCLN) for AVEL, comprising a backbone network and a branch network. In the backbone network, drawing inspiration from physiological theories of sensory integration, we elucidate the process of audio-visual information fusion, interaction, and integration from an information-flow perspective. Notably, the Self-constrained Bi-modal Interaction (SBI) module is a bi-modal attention structure integrated with audio-visual fusion information, and through gated processing of the audio-visual correlation matrix, it effectively captures inter-modal correlation. The Foreground Event Enhancement (FEE) module emphasizes the significance of event-level boundaries by elongating the distance between scene events during training through adaptive weights. Furthermore, we introduce weak video-level labels to constrain the cross-modal semantic alignment of audio-visual events and design a weakly supervised cross-modal contrastive learning loss (WCCL Loss) function, which enhances the quality of fusion representation in the dual-branch contrastive learning framework. Extensive experiments conducted on the AVE dataset for both fully supervised and weakly supervised event localization, as well as Cross-Modal Localization (CML) tasks, demonstrate the superior performance of our model compared to state-of-the-art approaches. The code will be available from https://github.com/Supersunn/CCLN.

7 January 2021 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
ZHZhenxing Huang
Zhenxing Huang
ZCZixiang Chen
Zixiang Chen
Jincai ChenJincai Chen
Jincai Chen
PLPing Lu
Ping Lu
GQGuotao Quan
Guotao Quan
ZHZhanli Hu
Zhanli Hu
Many deep learning (DL)-based image restoration methods for low-dose CT (LDCT) problems directly employ the end-to-end networks on low-dose training data without considering dose differences. However, the radiation dose difference has a great impact on the ultimate results, and lower doses increase the difficulty of restoration. Moreover, there is increasing demand to design and estimate acceptable scanning doses for patients in clinical practice, necessitating dose-aware networks embedded with adaptive dose estimation. In this paper, we consider these dose differences of input LDCT images and propose an adaptive dose-aware network. First, considering a large dose distribution range for simulation convenience, we coarsely define five dose levels in advance as lowest, lower, mild, higher and highest radiation dose levels. Instead of directly building the end-to-end mapping function between LDCT images and high-dose CT counterparts, the dose level is primarily estimated in the first stage. In the second stage, the adaptively learned low-dose level is used to guide the image restoration process as the pattern of prior information through the channel feature transform. We conduct experiments on a simulated dataset based on original high dose parts of American Association of Physicists in Medicine challenge datasets from the Mayo Clinic. Ablation studies validate the effectiveness of the dose-level estimation, and the experimental results show that our method is superior to several other DL-based methods. Specifically, our method provides obviously better performance in terms of the peak signal-to-noise ratio and visual quality reflected in subjective scores. Due to the dual-stage process, our method may suffer limitations under more parameters and coarse dose-level definitions, and thus, further improvements in clinical practical applications with different CT equipment vendors are planned in future work.

19 July 2021 in IEEE Sensors Journal
Verified
Journal Article
Closed access
HLHan Liang
Han Liang
WJWanting Ji
Wanting Ji
Ruili WangRuili Wang
Ruili Wang
YMYaxiong Ma
Yaxiong Ma
Jincai ChenJincai Chen
Jincai Chen
Min ChenMin Chen
Min Chen
Sound event detection (SED) and acoustic scene classification (ASC) are two key tasks related to each other in the field of computational auditory scene analysis. For example, during sound event detection, scene information can be used to exclude sound events that are unlikely to occur in this scene. In other words, scene information can improve the accuracy of sound event detection. However, existing works rarely detect sound events by considering acoustic scene information. Based on the internal relationship between sound events and scene information, this paper proposes a scene-dependent sound event detection (SDSED) approach, which combines scene information and sound event information using multi-task learning. In the proposed approach, we share common feature representation for the two tasks simultaneously. Meanwhile, a temporal attention mechanism is used to extract informative features from sound recordings. We test the proposed approach on Synthetic Sound Scenes dataset. Experimental results show that our proposed approach outperforms the state-of-the-art approaches. Compared with the referenced approach, our approach improves the segment-based F-score by 4.29% and reduces the segment-based error rate by 4.8%.

15 August 2019 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
KLKe Luo
Ke Luo
SWShaobing Wang
Shaobing Wang
KCKheong Sann Chan
Kheong Sann Chan
WCWei Chen
Wei Chen
Jincai ChenJincai Chen
Jincai Chen
WCWeiming Cheng
Weiming Cheng
To achieve a high track density, two-dimensional magnetic recording (TDMR) is combined with shingled magnetic recording (SMR). SMR makes it possible to record 1 bit on a few grains. However, the performance will be remarkably deteriorated by the increased media noise, the inter-track and inter-symbol interference (ITI and ISI). Therefore, the application of effective equalization and error control coding are required. In this paper, we investigate a simple block-based neural network equalizer (NNE) that mitigates the influence of ITI and ISI. We compare the equalization effects of the NNE and a conventional 2-D equalizer with low-density parity-check (LDPC) coding based on a random Voronoi grain media model. Simulation results show the proposed block-based NNE achieves better bit error rate performance than the conventional 2-D linear equalizer followed by the a posteriori probability (APP) detector and a sum-product (SP) decoder. In addition, we find the block-based NNE is sensitive to write errors.

9 January 2020 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
TWTing Wang
Ting Wang
LCLele Cheng
Lele Cheng
CWChengxu Wang
Chengxu Wang
WCWeiming Cheng
Weiming Cheng
HWHaiwei Wang
Haiwei Wang
XMXiangshui Miao
Xiangshui Miao
Pt/BiFeO3/SrRuO3/SrTiO3 heterostructures with significant resistive switching characterisitics have been successfully fabricated via magnetron sputtering and the effect of thicknesses and deposition temperatures on the resistive switching properties has also been investigated. The resistive behaviors and conduction mechanisms can be modulated by the thickness and deposition temperatures of BFO films. BFO films with smaller thickness of 80nm and higher deposition temperature of 670℃ show larger memory window over 1000 and lower switching voltage below 1.5v. Moreover, the conduction mechanisms of Pt/BiFeO3/SrRuO3/SrTiO3 resistive cell changes from the space charge limited conduction model to conductive filament type with the decrease of BFO film thickness possibly due to the more oxygen vacancies and defects. Furthermore, oxygen partial pressure also influences the memory window and conduction mechanism of BFO resistive cells by increasing or decreasing the oxygen vacancy defects in BFO films.