Zhongpeng Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zhongpeng Cai has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Jun Yu
University of Science and Technology of China, Hefei, China
7 shared publications - Fang Gao
School of Electrical Engineering, Guangxi University, Nanning, China
2 shared publications - Gongpeng Zhao
University of Science and Technology of China, Hefei, China
2 shared publications - Lei Wang
University of Science and Technology of China, Hefei, China
2 shared publications - Shenshen Du
University of Science and Technology of China, Hefei, China
2 shared publications - Cong Wang
Huawei Techologies
1 shared publication
Latest Publications
- Open Access
Semi-Supervised Facial Expression Recognition based on Dynamic Threshold and Negative Learning
Facial expression recognition is a key task in human-computer interaction and affective computing. However, acquiring a large amount of labeled facial expression data is often costly. Therefore, it is particularly important to design a semi-supervised facial expression recognition algorithm that makes full use of both labeled and unlabeled data. In this paper, we propose a semi-supervised facial expression recognition algorithm based on Dynamic Threshold Adjustment (DTA) and Selective Negative Learning (SNL). Initially, we designed strategies for local attention enhancement and random dropout of feature maps during feature extraction, which strengthen the representation of local features while ensuring the model does not overfit to any specific local area. Furthermore, this study introduces a dynamic thresholding method to adapt to the requirements of the semi-supervised learning framework for facial expression recognition tasks, and through a selective negative learning strategy, it fully utilizes unlabeled samples with low confidence by mining useful expression information from complementary labels, achieving impressive results. We have achieved state-of-the-art performance on the RAF-DB and AffectNet datasets. Our method surpasses fully supervised methods even without using the entire dataset, which proves the effectiveness of our approach.
Open AccessSemi-Supervised Facial Expression Recognition based on Dynamic Threshold and Negative Learning
Facial expression recognition is a key task in human-computer interaction and affective computing. However, acquiring a large amount of labeled facial expression data is often costly. Therefore, it is particularly important to design a semi-supervised facial expression recognition algorithm that makes full use of both labeled and unlabeled data. In this paper, we propose a semi-supervised facial expression recognition algorithm based on Dynamic Threshold Adjustment (DTA) and Selective Negative Learning (SNL). Initially, we designed strategies for local attention enhancement and random dropout of feature maps during feature extraction, which strengthen the representation of local features while ensuring the model does not overfit to any specific local area. Furthermore, this study introduces a dynamic thresholding method to adapt to the requirements of the semi-supervised learning framework for facial expression recognition tasks, and through a selective negative learning strategy, it fully utilizes unlabeled samples with low confidence by mining useful expression information from complementary labels, achieving impressive results. We have achieved state-of-the-art performance on the RAF-DB and AffectNet datasets. Our method surpasses fully supervised methods even without using the entire dataset, which proves the effectiveness of our approach.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11490-11496
Micro-Expression Spotting Based on Optical Flow Feature with Boundary Calibration
Micro-expressions, as a type of facial expression corresponding to macro-expressions, usually have a short duration and low intensity. Due to these characteristics, micro-expression spotting holds significant value in medical care and public safety. Recent years have witnessed advancements in micro-expression spotting methods; however, spotting micro-expressions remains a challenging task due to their brief duration and low intensity. In this paper, we propose a micro-expression spotting method based on optical flow features with boundary calibration. We first perform face detection, cropping, and alignment on images containing faces. Then, regions of interest (ROIs) are defined, and optical flow features are extracted. Furthermore, candidate expression segments are identified based on the magnitude of the processed optical flows. Finally, a boundary calibration module is utilized to calibrate the boundaries. The effectiveness of the proposed method is evaluated on the MEGC2024 test set, resulting in an overall F1-score of 0.27.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11490-11496
Open AccessMicro-Expression Spotting Based on Optical Flow Feature with Boundary Calibration
Micro-expressions, as a type of facial expression corresponding to macro-expressions, usually have a short duration and low intensity. Due to these characteristics, micro-expression spotting holds significant value in medical care and public safety. Recent years have witnessed advancements in micro-expression spotting methods; however, spotting micro-expressions remains a challenging task due to their brief duration and low intensity. In this paper, we propose a micro-expression spotting method based on optical flow features with boundary calibration. We first perform face detection, cropping, and alignment on images containing faces. Then, regions of interest (ROIs) are defined, and optical flow features are extracted. Furthermore, candidate expression segments are identified based on the magnitude of the processed optical flows. Finally, a boundary calibration module is utilized to calibrate the boundaries. The effectiveness of the proposed method is evaluated on the MEGC2024 test set, resulting in an overall F1-score of 0.27.
- 29 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10637-10650
Language-Guided Dual-Modal Local Correspondence for Single Object Tracking
This paper focuses on the advancement of single object tracking technologies in computer vision, which have broad applications including robotic vision, video surveillance, and sports video analysis. Current methods relying solely on the target's initial visual information encounter performance bottlenecks and limited applications, due to the scarcity of target semantics in appearance features and the continuous change in the target's appearance. To address these issues, we propose a novel approach, combining visual-language dual-modal single object tracking, that leverages natural language descriptions to enrich the semantic information of the moving target. We introduce a dual-modal single-object tracking algorithm based on local correspondence modeling. The algorithm decomposes visual features into multiple local visual semantic features and pairs them with local language features extracted from natural language descriptions. In addition, we also propose a new global relocalization method that utilizes visual language bimodal information to perceive target disappearance and misalignment and adaptively reposition the target in the entire image. This improves the tracker's ability to adapt to changes in target appearance over long periods of time, enabling long-term single target tracking based on bimodal semantic and motion information. Experimental results show that our model outperforms stateof-the-art methods, which demonstrates the effectiveness and efficiency of our approach
- 29 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10637-10650
Language-Guided Dual-Modal Local Correspondence for Single Object Tracking
This paper focuses on the advancement of single object tracking technologies in computer vision, which have broad applications including robotic vision, video surveillance, and sports video analysis. Current methods relying solely on the target's initial visual information encounter performance bottlenecks and limited applications, due to the scarcity of target semantics in appearance features and the continuous change in the target's appearance. To address these issues, we propose a novel approach, combining visual-language dual-modal single object tracking, that leverages natural language descriptions to enrich the semantic information of the moving target. We introduce a dual-modal single-object tracking algorithm based on local correspondence modeling. The algorithm decomposes visual features into multiple local visual semantic features and pairs them with local language features extracted from natural language descriptions. In addition, we also propose a new global relocalization method that utilizes visual language bimodal information to perceive target disappearance and misalignment and adaptively reposition the target in the entire image. This improves the tracker's ability to adapt to changes in target appearance over long periods of time, enabling long-term single target tracking based on bimodal semantic and motion information. Experimental results show that our model outperforms stateof-the-art methods, which demonstrates the effectiveness and efficiency of our approach
- 27 November 2023
- Published by Springer Nature
- p. 91-102
SAR2EO: A High-Resolution Image Translation Framework with Denoising Enhancement
- 27 November 2023
- Published by Springer Nature
- p. 91-102
SAR2EO: A High-Resolution Image Translation Framework with Denoising Enhancement
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 137-143
Responsive Listening Head Synthesis with 3DMM and Dual-Stream Prediction Network
In a conversation, it is crucial for the listener to provide appropriate reactions to the speaker, as the dialogue becomes challenging to sustain without the listener's involvement. Consequently, responsive listening head synthesis has become an important task. However, the existing methods fail to adequately utilize the audio and video of the speaker to generate listening heads, resulting in unnatural or even distorted generated videos. In this paper, we propose a framework to effectively encode audio and video features to address this problem. The framework includes speaker audio encoder, speaker video encoder, a Dual-Stream Prediction Network and a rendering network. The audio encoder utilizes a transformer encoder to encode the audio features, enabling better focus on the contextual features of long audio inputs. The speaker video encoder uses a 3D morphable model (3DMM) to extract the speaker's video features. Then we fuse the speaker's audio-video features with the listener's identity information extracted by 3DMM to preserve the listener's style. Additionally, a Dual-Stream Prediction Network is introduced to further enhance the prediction capability of the network. Finally, a rendering network is used to generate the listening heads based on the result of the prediction network. Comprehensive experiments demonstrate that our approach is capable of generating responsive listening heads with higher visual quality, better naturalness and higher reconstruction fidelity.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 137-143
Open AccessResponsive Listening Head Synthesis with 3DMM and Dual-Stream Prediction Network
In a conversation, it is crucial for the listener to provide appropriate reactions to the speaker, as the dialogue becomes challenging to sustain without the listener's involvement. Consequently, responsive listening head synthesis has become an important task. However, the existing methods fail to adequately utilize the audio and video of the speaker to generate listening heads, resulting in unnatural or even distorted generated videos. In this paper, we propose a framework to effectively encode audio and video features to address this problem. The framework includes speaker audio encoder, speaker video encoder, a Dual-Stream Prediction Network and a rendering network. The audio encoder utilizes a transformer encoder to encode the audio features, enabling better focus on the contextual features of long audio inputs. The speaker video encoder uses a 3D morphable model (3DMM) to extract the speaker's video features. Then we fuse the speaker's audio-video features with the listener's identity information extracted by 3DMM to preserve the listener's style. Additionally, a Dual-Stream Prediction Network is introduced to further enhance the prediction capability of the network. Finally, a rendering network is used to generate the listening heads based on the result of the prediction network. Comprehensive experiments demonstrate that our approach is capable of generating responsive listening heads with higher visual quality, better naturalness and higher reconstruction fidelity.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9541-9545
Efficient Micro-Expression Spotting Based on Main Directional Mean Optical Flow Feature
Human facial expressions can convey a great deal of information in daily life. Spotting macro-expression (MaE) and micro-expression (ME) intervals from long video sequences is a difficult challenge. In this paper, we propose an efficient framework for the expression spotting task. This framework consists of three main modules: Face Cropping and Alignment Module (FCAM), optical flow Feature Extraction Module (FEM), and expression Proposal Generation Module (PGM). The noise of optical flow features is reduced by face cropping and alignment, and the Main Directional Mean Optical Flow Feature of the regions of interest is extracted as the feature for expression spotting. Finally, the expression intervals are spotted by our designed expression proposal generation module. Our approach achieves very good results on the SAMM Long Videos and CAS(ME)^2. To demonstrate the transferability of our method, we tested it on the MEGC2023 unseen dataset and finally achieved the third place, proving the effectiveness of our method.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9541-9545
Open AccessEfficient Micro-Expression Spotting Based on Main Directional Mean Optical Flow Feature
Human facial expressions can convey a great deal of information in daily life. Spotting macro-expression (MaE) and micro-expression (ME) intervals from long video sequences is a difficult challenge. In this paper, we propose an efficient framework for the expression spotting task. This framework consists of three main modules: Face Cropping and Alignment Module (FCAM), optical flow Feature Extraction Module (FEM), and expression Proposal Generation Module (PGM). The noise of optical flow features is reduced by face cropping and alignment, and the Main Directional Mean Optical Flow Feature of the regions of interest is extracted as the feature for expression spotting. Finally, the expression intervals are spotted by our designed expression proposal generation module. Our approach achieves very good results on the SAMM Long Videos and CAS(ME)^2. To demonstrate the transferability of our method, we tested it on the MEGC2023 unseen dataset and finally achieved the third place, proving the effectiveness of our method.
- Open Access
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5785-5792
Local Region Perception and Relationship Learning Combined with Feature Fusion for Facial Action Unit Detection
Human affective behavior analysis plays a vital role in human-computer interaction (HCI) systems. In this paper, we introduce our submission to the CVPR 2023 Competition on Affective Behavior Analysis in-the-wild (ABAW). We propose a single-stage trained AU detection framework. Specifically, in order to effectively extract facial local region features related to AU detection, we use a local region perception module to effectively extract features of different AUs. Meanwhile, we use a graph neural network-based relational learning module to capture the relationship between AUs. In addition, considering the role of the overall feature of the target face on AU detection, we also use the feature fusion module to fuse the feature information extracted by the backbone network and the AU feature information extracted by the relationship learning module. We also adopted some sampling methods, data augmentation techniques and post-processing strategies to further improve the performance of the model. On the official test set, our method ranks third in the AU detection track. This result and subsequent ablation experiments prove the effectiveness of our proposed method.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5785-5792
Open AccessLocal Region Perception and Relationship Learning Combined with Feature Fusion for Facial Action Unit Detection
Human affective behavior analysis plays a vital role in human-computer interaction (HCI) systems. In this paper, we introduce our submission to the CVPR 2023 Competition on Affective Behavior Analysis in-the-wild (ABAW). We propose a single-stage trained AU detection framework. Specifically, in order to effectively extract facial local region features related to AU detection, we use a local region perception module to effectively extract features of different AUs. Meanwhile, we use a graph neural network-based relational learning module to capture the relationship between AUs. In addition, considering the role of the overall feature of the target face on AU detection, we also use the feature fusion module to fuse the feature information extracted by the backbone network and the AU feature information extracted by the relationship learning module. We also adopted some sampling methods, data augmentation techniques and post-processing strategies to further improve the performance of the model. On the official test set, our method ranks third in the AU detection track. This result and subsequent ablation experiments prove the effectiveness of our proposed method.
- Open Access
A Dual Branch Network for Emotional Reaction Intensity Estimation
Emotional Reaction Intensity(ERI) estimation is an important task in multimodal scenarios, and has fundamental applications in medicine, safe driving and other fields. In this paper, we propose a solution to the ERI challenge of the fifth Affective Behavior Analysis in-the-wild(ABAW), a dual-branch based multi-output regression model. The spatial attention is used to better extract visual features, and the Mel-Frequency Cepstral Coefficients technology extracts acoustic features, and a method named modality dropout is added to fusion multimodal features. Our method achieves excellent results on the official validation set.
Open AccessA Dual Branch Network for Emotional Reaction Intensity Estimation
Emotional Reaction Intensity(ERI) estimation is an important task in multimodal scenarios, and has fundamental applications in medicine, safe driving and other fields. In this paper, we propose a solution to the ERI challenge of the fifth Affective Behavior Analysis in-the-wild(ABAW), a dual-branch based multi-output regression model. The spatial attention is used to better extract visual features, and the Mel-Frequency Cepstral Coefficients technology extracts acoustic features, and a method named modality dropout is added to fusion multimodal features. Our method achieves excellent results on the official validation set.
- Open Access
- 1 January 2021
- Published by Zoological Research in Zoological Research
- Vol. 42 (4) , 461-468
Clonal spread of Escherichia coli O101:H9-ST10 and O101:H9-ST167 strains carrying fosA3 and blaCTX-M-14 among diarrheal calves in a Chinese farm, with Australian Chroicocephalus as the possible origin of E. coli O101:H9-ST10
During a 2018 antimicrobial resistance surveillance of Escherichia coli isolates from diarrheal calves in Xinjiang Province, China, an unexpectedly high prevalence (48.5%) of fosfomycin resistance was observed. This study aimed to reveal the determinants of fosfomycin resistance and the underlying transmission mechanism. Polymerase chain reaction (PCR) screening showed that all fosfomycin-resistant E. coli carried the fosA3 gene. Pulsed-field gel electrophoresis (PFGE) and southern blot hybridization revealed that the 16 fosA3-positive isolates belonged to four different PFGE patterns (i.e., A, B, C, D). The fosA3 genes of 11 clonally related strains (pattern D) were located on the chromosome, while others were carried by plasmids. Whole-genome and long-read sequencing indicated that the pattern D strains were E. coli O101: H9-ST10, and the pattern C, B, and A strains were O101: H9-ST167, O8: H30-ST1431, and O101: H9 with unknown ST, respectively. Among the pattern C strains, the bla CTX-M-14 gene was co-localized with the fosA3 gene on the F18: A-: B1 plasmids. Interestingly, phylogenetic analysis based on core genome single nucleotide polymorphisms (cgSNPs) showed that the O101: H9-ST10 strains were closely related to a Australian-isolated Chroicocephalus-origin E. coli O101: H9-ST10 strain producing CTX-M-14 and FosA3, with a difference of only 11 SNPs. These results indicate possible international dissemination of the high-risk E. coli clone O101: H9-ST10 by migratory birds.
- 1 January 2021
- Published by Zoological Research in Zoological Research
- Vol. 42 (4) , 461-468
Open AccessClonal spread of Escherichia coli O101:H9-ST10 and O101:H9-ST167 strains carrying fosA3 and blaCTX-M-14 among diarrheal calves in a Chinese farm, with Australian Chroicocephalus as the possible origin of E. coli O101:H9-ST10
During a 2018 antimicrobial resistance surveillance of Escherichia coli isolates from diarrheal calves in Xinjiang Province, China, an unexpectedly high prevalence (48.5%) of fosfomycin resistance was observed. This study aimed to reveal the determinants of fosfomycin resistance and the underlying transmission mechanism. Polymerase chain reaction (PCR) screening showed that all fosfomycin-resistant E. coli carried the fosA3 gene. Pulsed-field gel electrophoresis (PFGE) and southern blot hybridization revealed that the 16 fosA3-positive isolates belonged to four different PFGE patterns (i.e., A, B, C, D). The fosA3 genes of 11 clonally related strains (pattern D) were located on the chromosome, while others were carried by plasmids. Whole-genome and long-read sequencing indicated that the pattern D strains were E. coli O101: H9-ST10, and the pattern C, B, and A strains were O101: H9-ST167, O8: H30-ST1431, and O101: H9 with unknown ST, respectively. Among the pattern C strains, the bla CTX-M-14 gene was co-localized with the fosA3 gene on the F18: A-: B1 plasmids. Interestingly, phylogenetic analysis based on core genome single nucleotide polymorphisms (cgSNPs) showed that the O101: H9-ST10 strains were closely related to a Australian-isolated Chroicocephalus-origin E. coli O101: H9-ST10 strain producing CTX-M-14 and FosA3, with a difference of only 11 SNPs. These results indicate possible international dissemination of the high-risk E. coli clone O101: H9-ST10 by migratory birds.