长期致力于图像视频处理和可解释性神经网络方向的研究工作，取得了重要理论和技术突破。解决了高倍率图像复原过程中无法兼顾图像主观和客观质量的问题；同时针对现有神经网络可解释性差的问题，提出基于卷积稀疏表示的可解释性神经网络架构，在保证准确度的同时显著提高网络的可解释性和鲁棒性。近5年来在人工智能顶级期刊TPAMI、图像处理顶级期刊TIP、视频编码权威期刊TCSVT，计算机视觉领域顶级会议ICCV、ECCV等发表论文20余篇。谷歌学术引用400 余次，单篇最高引用94 次 发表的主要论文如下： ◆ 字典学习和可解释性神经网络 [1] Xin Deng, and Pier Luigi Dragotti, “ Deep Convolutional Neural Network for Multi-modal image restoration and fusion”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)，2020. 期刊论文 （录用）SCI [2] Xin Deng and Pier Luigi Dragotti, “Deep Coupled ISTA Network for Multi-modal Image Super-resolution”, IEEE Transactions on Image Processing (TIP), vol 29, pp 1683 –1698, 2019. 期刊论文 （已发表） SCI [3] Xin Deng, and Pier Luigi Dragotti, “Coupled ISTA Network for Multi-modal Image Super-resolution”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 1862-1866, 2019. 会议论文 （已发表）EI [4] Xin Deng, Junjie Huang, Mengying Liu, and Pier Luigi Dragotti, “An FRI-based Single Image Super-Resolution Algorithm and an Application in Image Compression”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 1807-1811, 2018. 会议论文 （已发表）EI ◆ 视频压缩和显著性模型 [5] Mai Xu, Tianyi Li, Zulin Wang, Xin Deng, Ren Yang, “Reducing complexity of HEVC: A deep learning approach”. IEEE Transactions on Image Processing （TIP）, 2018, 27(10): 5044-5059. 期刊论文 （已发表）SCI [6] Tianyi Li, Mai Xu, Xin Deng, Liquan Shen, “Accelerate CTU Partition to Real Time for HEVC Encoding with Complexity Control”. IEEE Transactions on Image Processing （TIP）, 2020, DOI: 10.1109/TIP.2020.3003730 [7] Mai Xu, Xin Deng, Shengxi Li, and Zulin Wang, “Region-of-Interest Based Conversational HEVC Coding with Hierarchical Perception Model of Face”， IEEE Journal of Selected Topics in Signal Processing (JSTSP) , vol 8, pp 475-489, 2014. 期刊论文 （已发表）SCI [8] Xin Deng, Mai Xu, Lai Jiang, Xiaoyan Sun, and Zulin Wang, “Subjective-driven Complexity Control Approach for HEVC”, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol 26, pp 91-106, 2016. 期刊论文 （已发表）SCI [9] Xin Deng and Mai Xu, “Hierarchical Complexity Control of HEVC for Live Video Encoding”, IEEE Access, vol 4, pp 7014-7027, 2016. 期刊论文 （已发表）SCI [10] Shengxi Li, Mai Xu, Xin Deng, and Zulin Wang, “Weight-based r-λ rate control for perceptual HEVC coding on conversational videos,” Signal Processing: Image Communication, vol 38, pp 127-140, 2015 期刊论文 （已发表）SCI [11] Xin Deng, and Mai Xu, “Complexity Control of HEVC for Video Conferencing”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 1552-1556, 2017 会议论文 （已发表）EI [12] Xin Deng, Mai Xu, Shengxi Li and Zulin Wang, “Complexity Control of HEVC Based on Region-of-Interest Attention Model”，Visual Communications and Image Processing Conference (VCIP), pp 225-228, 2014 会议论文 （已发表）EI ◆ 图像视频超分辨与质量提升 [13] Jianyi Wang, Xin Deng, Mai Xu, Congyong Chen and Yuhang Song, “Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Video”, IEEE European Conference on Computer Vision (ECCV), 2020 会议论文 （已接收）EI [14] Xin Deng, Ren Yang, Mai Xu and Pier Luigi Dragotti, “Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-resolution”, IEEE International Conference on Computer Vision (ICCV) oral, pp 3076-3085, 2019 会议论文 （已发表）EI [15] Xin Deng, “Enhancing Image Quality via Style Transfer for Single Image Super-Resolution”, IEEE Signal Processing Letters, vol. 25, pp 571-575, 2018. 期刊论文 （已发表）SCI [16] Pingfan Song, Xin Deng (共同一作), Joao F.C. Mota, Nikos Deligiannis, Pier Luigi Dragotti, and Miguel R.D. Rodrigues,“Multimodal Image Super-resolution via Joint Sparse Representations induced by Coupled Dictionaries”, IEEE Transactions on Computational Imaging (TCI), vol 6，pp 57-72, 2020. 期刊论文 （已发表）SCI [17] Xin Deng, Pingfan Song, Miguel R. D. Rodrigues and Pier Luigi Dragotti, “RADAR: Robust Algorithm for Depth Image Super Resolution Based on FRI Theory and Multimodal Dictionary Learning”, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019. 期刊论文 （录用）SCI |
