Xin Cheng

Xin Cheng

Auto-generated profile, based on publicly available information

Xin Cheng

School of Computer Science and the School of Software, Nanjing University of Information Science and Technology, Nanjing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
20 November 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XCXin Cheng
Xin Cheng
HWHao Wang
Hao Wang
LXLuo Xiangyang
Luo Xiangyang
QGQingxiao Guan
Qingxiao Guan
BMBin Ma
Bin Ma
JWJinwei Wang
Jinwei Wang
The manipulation history of Joint Photographic Experts Group (JPEG) compression plays an important role in JPEG image forensics and information hiding. For non-aligned recompressed images, different cropping methods produce non-aligned outputs with varying feature distributions. One such important factor is the shifts of the discrete cosine transform (DCT) grid (i.e., the misalignment parameters) between two compression processes. Although many methods have been proposed to estimate the misalignment parameters, the limited amount of useful information available in small-sized images leads to low accuracy of these methods. To enhance the accuracy of misalignment parameter estimation for small-sized non-aligned images, we propose a novel two-branch network structure that accounts for the unique horizontal and vertical characteristics of non-aligned images. This structure employs convolution to simulate second-order difference (SOD) and incorporates it throughout the training process to optimize the difference parameters dynamically. Based on the insight that cropping operations leave traces in all color channels, we derive the Cg channel through a color space transformation. This approach expands the input dimensionality to four channels (Y, Cb, Cr, and Cg), thereby compensating for the information scarcity in small-sized images. The experimental results show that our method outperforms existing methods on different image sizes, regardless of the known or unknown quality factor (QF) of the first compression. Finally, we propose a re-cropping framework based on the estimated misalignment parameters. The influence of the first cropping is counteracted by a re-cropping operation, which improves the accuracy of existing methods in estimating the first quantization step for non-aligned recompressed images.

23 April 2025 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
HWHao Wang
Hao Wang
XCXin Cheng
Xin Cheng
HWHao Wu
Hao Wu
XLXiangyang Luo
Xiangyang Luo
BMBin Ma
Bin Ma
JWJinwei Wang
Jinwei Wang

9 June 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XCXin Cheng
Xin Cheng
JWJinwei Wang
Jinwei Wang
HWHao Wang
Hao Wang
LXLuo Xiangyang
Luo Xiangyang
BMBin Ma
Bin Ma
The quantization step is a crucial parameter in JPEG compression, that can reveal the compression history of a JPEG image. Estimating the quantization steps for single compressed and recompressed images is attracting considerable interest in the field of image forensics and steganalysis. Several effective methods have been proposed, but the performance of these methods still needs to be improved on small-sized and low-quality images. To solve the above problems, feature enrichment is performed on images in the frequency domain, resulting in clustering discrete cosine transform (DCT) coefficients of the same frequency. Then, we construct a hierarchical connection within the residual blocks of the network to represent multi-scale features, enabling the network to learn deep features of the image. At the same time, we use multiple small-sized convolution kernels instead of one large-sized convolution kernel to minimize the impact of block artifacts. Based on the above two ideas, we construct a network model, Res2Net-C, to discover information about the quantization steps in the frequency domain. The integration of multi-channel information of color images is achieved by multi-channel convolution, and the quantization steps of the chrominance and luminance channels of the color images are estimated. The experimental results show that the accuracy of the proposed method for estimating the quantization steps is 29.97% better than that of the existing algorithm with a single compressed dataset and 4.87% better than that of the existing algorithm with a recompressed image dataset. In addition, the method has good performance with mixed datasets that contain both single compressed and recompressed images.

28 October 2024
Verified
Conference Paper
Open access
XCXin Cheng
Xin Cheng
HWHao Wang
Hao Wang
JWJinwei Wang
Jinwei Wang
LXLuo Xiangyang
Luo Xiangyang
BMBin Ma
Bin Ma
In Joint Photographic Experts Group (JPEG) image steganalysis and forensics, the quantization step can reveal the history of image operations. Several methods for estimating the quantization step have been proposed by researchers. However, existing algorithms fail to account for robustness, which limits the application of these algorithms. To solve the above problems, we propose a two-stream network structure based on Swin Transformer. The spatial domain features of JPEG images exhibit strong robustness but low accuracy. Conversely, frequency domain features demonstrate high accuracy but weak robustness. Therefore, we design a two-stream network with the multi-scale feature of Swin Transformer to extract spatial domain features with high robustness and frequency domain features with high accuracy, respectively. Furthermore, to adaptively fuse features in both the frequency domain and spatial domain,we design a Spatial-frequency Information Dynamic Fusion (SIDF) module to dynamically allocate weights. Finally, we modify the network from a regression model to a classification model to speed up convergence and improve the accuracy of the algorithm. The experiment results show that the accuracy of the proposed method is higher than 98% on clean images. Meanwhile, in robust environments, the algorithm proposed maintains an average accuracy of over 81%.

9 November 2026
Verified
Conference Paper
Open access
HWHao Wu
Hao Wu
YZYi Zhang
Yi Zhang
JZJiawei Zhang
Jiawei Zhang
HWHao Wang
Hao Wang
XCXin Cheng
Xin Cheng
LXLuo Xiangyang
Luo Xiangyang
Audio–visual synchronization aims to accurately determine the temporal alignment between lip motions and the corresponding speech signal. However, existing approaches often struggle to achieve an optimal balance between in-sync and out-of-sync detection accuracy. In this paper, we provide a formal analysis of this performance bottleneck and rigorously show that both clip-level and frame-level synchronization models are inherently constrained by the alignment–uniformity trade-off on the representation hypersphere. To overcome this fundamental limitation, we propose HybridSyncNet, an efficient hybrid-level synchronization paradigm that leverages adaptive gating and multi-level contrastive learning to fuse the complementary strengths of clip-level and frame-level information in alignment and uniformity. Crucially, we theoretically demonstrate that, compared with single-level models, the proposed HybridSyncNet simultaneously achieves alignment improvement and uniformity gain. Extensive experiments validate the effectiveness of our approach. With only 2.46M parameters, HybridSyncNet outperforms state-of-the-art audio–visual synchronization models on the CREMA-D and HDTF benchmarks, establishing a new paradigm for audio–visual synchronization. The code is available at~https://github.com/tlemangen/HybridSyncNet.

19 February 2026 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
XCXin Cheng
Xin Cheng
HWHao Wang
Hao Wang
LXLuo Xiangyang
Luo Xiangyang
BMBin Ma
Bin Ma
BWBaowei Wang
Baowei Wang
JWJinwei Wang
Jinwei Wang
The quantization step is a crucial parameter in the JPEG compression process, and provides prior knowledge for JPEG image steganography and forensics. Existing neural network-based methods typically estimate the quantization steps for all discrete cosine transform (DCT) subbands jointly, by treating the entire quantization table as a unified input and leveraging the inter-subband relationships. However, subband relationships vary across different quantization tables, leading to poor generalization for methods that rely heavily on such relationships. To address the above issues, we depart from the strategy that relies on inter-subband relationships and instead train the model on a specific single subband. To compensate for the possible decrease in accuracy due to the lack of relationships between subbands, we extract the ranking features and histogram features from the DCT coefficient histograms of the subbands. Ranking features capture local patterns in DCT histograms by modeling the relative relationships between neighboring coefficients, thereby compensating for the absence of local detail. On the other hand, histogram features represent the overall distribution pattern of the DCT coefficient histograms and capture the global trends and statistical properties in the subbands. We subsequently employ convolutional groups and multilayer perceptron (MLP) structures to extract compression artifacts from these two features. Finally, we introduce a comprehensive evaluation metric, called GenAQt, to quantify the algorithm’s generalization ability across quantization tables. The experimental results demonstrate that our method maintains high accuracy across quantization tables, with RelGenAQt (relative accuracy decrease) exceeding 81% and AbsGenAQt (absolute accuracy decrease) being less than 0.38.