Zhenche Xia
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
Research Subjects
Zhenche Xia has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Zhenhua Tan
Software College, Northeastern University, Shenyang, China
6 shared publications - Danke Wu
Software College, Northeastern University, Shenyang, China
3 shared publications - Jingyu Ning
Northeastern University
2 shared publications - Wang Pengfei
Software College, Northeastern University, Shenyang, China
2 shared publications - Wencheng Li
School of Software Northeastern University 110819 Shen Yang China
2 shared publications - Bin Zhang
Northeastern University
1 shared publication
Latest Publications
- Open Access
- 12 November 2025
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 9 (11) , 286
Overcoming Domain Shift in Violence Detection with Contrastive Consistency Learning
Automated violence detection in video surveillance is critical for public safety; however, existing methods frequently suffer notable performance degradation across diverse real-world scenarios due to domain shift. Substantial distributional discrepancies between source training data and target environments severely hinder model generalization, limiting practical deployment. To overcome this, we propose CoMT-VD, a new contrastive Mean Teacher-based violence detection model, engineered for enhanced adaptability in unseen target domains. CoMT-VD innovatively integrates a Mean Teacher architecture to adequately leverage unlabeled target domain data, fostering stable, domain-invariant feature representations by enforcing consistency regularization between student and teacher networks, crucial for bridging the domain gap. Furthermore, to mitigate supervisory noise from pseudo-labels and refine the feature space, CoMT-VD incorporates a dual-strategy contrastive learning module. DCL systematically refines features through intra-sample consistency, minimizing latent space distances for compact representations, and inter-sample consistency, maximizing feature dissimilarity across distinct categories to sharpen decision boundaries. This dual regularization purifies the learned feature space, boosting discriminativeness while mitigating noisy pseudo-labels. Broad evaluations on five benchmark datasets unequivocally demonstrate that CoMT-VD achieves the superior generalization performance (in the four integrated scenarios from five benchmark datasets, the improvements were 5.0∼12.0%, 6.0∼12.5%, 5.0∼11.2%, 5.0∼11.2%, and 6.3∼12.3%, respectively), marking a notable advancement towards robust and reliable real-world violence detection systems.
- 12 November 2025
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 9 (11) , 286
Open AccessOvercoming Domain Shift in Violence Detection with Contrastive Consistency Learning
Automated violence detection in video surveillance is critical for public safety; however, existing methods frequently suffer notable performance degradation across diverse real-world scenarios due to domain shift. Substantial distributional discrepancies between source training data and target environments severely hinder model generalization, limiting practical deployment. To overcome this, we propose CoMT-VD, a new contrastive Mean Teacher-based violence detection model, engineered for enhanced adaptability in unseen target domains. CoMT-VD innovatively integrates a Mean Teacher architecture to adequately leverage unlabeled target domain data, fostering stable, domain-invariant feature representations by enforcing consistency regularization between student and teacher networks, crucial for bridging the domain gap. Furthermore, to mitigate supervisory noise from pseudo-labels and refine the feature space, CoMT-VD incorporates a dual-strategy contrastive learning module. DCL systematically refines features through intra-sample consistency, minimizing latent space distances for compact representations, and inter-sample consistency, maximizing feature dissimilarity across distinct categories to sharpen decision boundaries. This dual regularization purifies the learned feature space, boosting discriminativeness while mitigating noisy pseudo-labels. Broad evaluations on five benchmark datasets unequivocally demonstrate that CoMT-VD achieves the superior generalization performance (in the four integrated scenarios from five benchmark datasets, the improvements were 5.0∼12.0%, 6.0∼12.5%, 5.0∼11.2%, 5.0∼11.2%, and 6.3∼12.3%, respectively), marking a notable advancement towards robust and reliable real-world violence detection systems.
- 24 July 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (12) , 36899-36919
SCTF: an efficient neural network based on local spatial compression and full temporal fusion for video violence detection
- 24 July 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (12) , 36899-36919
SCTF: an efficient neural network based on local spatial compression and full temporal fusion for video violence detection
- Open Access
PF-Net: Personalized Filter for Speaker Recognition from Raw Waveform
Speaker recognition using i-vector has been replaced by speaker recognition using deep learning. Speaker recognition based on Convolutional Neural Networks (CNNs) has been widely used in recent years, which learn low-level speech representations from raw waveforms. On this basis, a CNN architecture called SincNet proposes a kind of unique convolutional layer, which has achieved band-pass filters. Compared with standard CNNs, SincNet learns the low and high cut-off frequencies of each filter. This paper proposes an improved CNNs architecture called PF-Net, which encourages the first convolutional layer to implement more personalized filters than SincNet. PF-Net parameterizes the frequency domain shape and can realize band-pass filters by learning some deformation points in frequency domain. Compared with standard CNN, PF-Net can learn the characteristics of each filter. Compared with SincNet, PF-Net can learn more characteristic parameters, instead of only low and high cut-off frequencies. This provides a personalized filter bank for different tasks. As a result, our experiments show that the PF-Net converges faster than standard CNN and performs better than SincNet. Our code is available at github.com/TAN-OpenLab/PF-NET.
Open AccessPF-Net: Personalized Filter for Speaker Recognition from Raw Waveform
Speaker recognition using i-vector has been replaced by speaker recognition using deep learning. Speaker recognition based on Convolutional Neural Networks (CNNs) has been widely used in recent years, which learn low-level speech representations from raw waveforms. On this basis, a CNN architecture called SincNet proposes a kind of unique convolutional layer, which has achieved band-pass filters. Compared with standard CNNs, SincNet learns the low and high cut-off frequencies of each filter. This paper proposes an improved CNNs architecture called PF-Net, which encourages the first convolutional layer to implement more personalized filters than SincNet. PF-Net parameterizes the frequency domain shape and can realize band-pass filters by learning some deformation points in frequency domain. Compared with standard CNN, PF-Net can learn the characteristics of each filter. Compared with SincNet, PF-Net can learn more characteristic parameters, instead of only low and high cut-off frequencies. This provides a personalized filter bank for different tasks. As a result, our experiments show that the PF-Net converges faster than standard CNN and performs better than SincNet. Our code is available at github.com/TAN-OpenLab/PF-NET.
- 6 June 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (4) , 4218-4230
FTCF: Full temporal cross fusion network for violence detection in videos
- 6 June 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (4) , 4218-4230
FTCF: Full temporal cross fusion network for violence detection in videos
- 11 April 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (1) , 1459-1475
TCSE: Trend and cascade based spatiotemporal evolution network to predict online content popularity
- 11 April 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (1) , 1459-1475
TCSE: Trend and cascade based spatiotemporal evolution network to predict online content popularity
- 1 January 2022
- Published by Springer Nature
- p. 362-374
PF-Net: Personalized Filter for Speaker Recognition from Raw Waveform
- 1 January 2022
- Published by Springer Nature
- p. 362-374
PF-Net: Personalized Filter for Speaker Recognition from Raw Waveform