智能多媒体实验室

学术论文

期刊论文
Towards Robust Person Re-Identification by Defending Against Universal Attackers, Fengxiang Yang, Juanjuan Weng, Zhun Zhong, Hong Liu, Zheng Wang, Zhiming Luo, Donglin Cao, Shaozi Li, Shin'ichi Satoh, Nicu Sebe, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022. (CCF-A)

Source-Free Open Compound Domain Adaptation in Semantic Segmentation, Yuyang Zhao, Zhong Zhun*, Zhiming Luo, Gim Hee Lee, Nicu Sebe, IEEE Transactions on Circuits and Systems for Video Technology, 2022. (CCF-B)

Joint Representation Learning and Keypoint Detection for Cross-view Geo-localizationJinliang Lin, Zhedong Zheng, Zhun Zhong, Zhiming Luo*, Shaozi Li*, Yi Yang, Nicu SebeIEEE Transactions on Image Processing, 2022. (CCF-A)
* Graph-based Class-imbalance Learning with Label Enhancement, Du Guodong, Zhang Jia, Jiang Min, Long Jinyi, Li Shaozi(*), Tan Kay Chen, IEEE Transactions on Neural Networks and Learning Systems, 2021.  (CCF-B)
* Manifold Interpolation for Large-Scale Multiobjective Optimization via Generative Adversarial Networks, Z Wang, H Hong, K Ye, GE Zhang, M Jiang(*), KC Tan, IEEE Transactions on Neural Networks and Learning Systems, 2021.  (CCF-B)
* An Online Prediction Approach Based on Incremental Support Vector Machine for Dynamic Multiobjective Optimization, D Xu, M Jiang(*), W Hu, S Li, R Pan, GG Yen, IEEE Transactions on Evolutionary Computation, 2021.  (CCF-B)
* Solving hybrid charging strategy electric vehicle based dynamic routing problem via evolutionary multi-objective optimization, Z Wang, K Ye, M Jiang(*), J Yao, NN Xiong, GG Yen, Swarm and Evolutionary Computation, 2021
* Evolutionary Search with Multi-View Prediction for Dynamic Multi-objective Optimization,W Zhou, L Feng, KC Tan, M Jiang, Y Liu, IEEE Transactions on Evolutionary Computation, 2021.  (CCF-B)
* Inverse Gaussian Process Modeling for Evolutionary Dynamic Multiobjective Optimization, H Zhang, J Ding, M Jiang, KC Tan, T Chai, IEEE Transactions on Cybernetics, 2021.   (CCF-B)

* Improving Embedding Learning by Virtual Attribute Decoupling for Text-based Person Search, Chengji Wang, Zhiming Luo, Yaojin Lin, Shaozi Li,  Neural Computing and Application, 2021. (中科院2区)

* APRIL: Anatomical Prior-guided ReInforcement Learning for Accurate Carotid Lumen Diameter and Intima-media Thickness Measurement. Sheng Lian, Zhiming Luo, Cheng Feng, Shaozi Li, Shuo Li,  Medical Image Analysis, 2021. (中科院1区)

* Towards Graph-based Class-imbalance Learning for Hospital Readmission. Guodong Du, Jia Zhang, Fenglong Ma, Min Zhao, Yaojin Lin, Shaozi Li, Expert Systems with Applications, 2021. (中科院2区)

* SAFD: single shot anchor free face detector. Chengji Wang, Zhiming Luo, Zhun Zhong, Shaozi Li, Multimedia Tools and Applications, 2021 (CCF-C)
* Towards a unified multi-source-based optimization framework for multi-label learning. Jia Zhang, Candong Li, Zhenqing Sun, Zhiming Luo, Changen Zhou, Shaozi Li:  Applied Soft Computing, 2019. (中科院2区)
* Camstyle: a novel data augmentation method for person re-identification, Zhong Zhong, Liang Zheng, Zhedong Zheng, Shaozi Li, Yi Yang, IEEE Transactions on Image Processing 2019.  (CCF-A)
* Multi-label learning with label-specific features by resolving label correlations, Jia Zhang, Candong Li, Donglin Cao, Yaojin Lin, Songzhi Su, Liang Dai, Shaozi Li, Knowledge-Based Systems 2019. (CCF-C)
* Leveraging Virtual and Real Person for Unsupervised Person Re-identification, Fengxiang Yang, Zhun Zhong, Zhiming Luo, Shaozi Li, IEEE Transactions on Multimedia, 2018. (CCF-B)
* Mutual information based multi-label feature selection via constrained convex optimization, Zhenqiang Sun, Jia Zhang, Liang Dai, Candong Li, Changen Zhou, Jiliang Xin, Shaozi Li. Neurocomputing, 2018. (CCF-C)
* Discriminative parts learning for 3D human action recognition, Min Huang, Guorong Cai, Hongbo Zhang, Sheng Yu, Dongying Gong, Donglin Cao, Shaozi Li, Songzhi Su, Neurocomputing, 2018. (CCF-C)
* Multifeature Selection for 3D Human Action Recognition, Min Huang, Song-Zhi Su, Hong-Bo Zhang, Guo-Rong Cai, Dongying Gong, Donglin Cao, Shao-Zi Li, ACM Transactions on Multimedia Computing, Communications, and Applications, 2018. (CCF-B)
* Liang Dai, Jia Zhang, Candong Li, Changen Zhou, Shaozi Li: Multi‐label feature selection with application to TCM state identification. Concurrency and Computation:Practice and Experience. (2018. 4区)
* Zhun Zhong, Liang Zheng, Zhedong Zheng, Shaozi Li, Yi Yang: CamStyle: A Novel Data Augmentation Method for Person Re-Identification. IEEE Transactions on Image Processing. (2018. 2区. A类)
* Zhiming Luo, B Frederic, Carl Lemaire, Janusz Konrad, Shaozi Li, Akshaya Mishra, Andrew Achkar, Justin Eichel, Pierre-Marc Jodoin: MIO-TCD: A new benchmark dataset for vehicle classification and localization. IEEE Transactions on Image Processing (2018. 2区A类)
* Wei Liu, Zhiming Luo, Shaozi Li: Improving Deep Ensemble Vehicle Classification by Using Selected Adversarial Samples. Knowledge-Based Systems (2018. 2区C类)
* Clement Zotti, Zhiming Luo, Alain Lalande, Pierre-Marc Jodoin: Convolutional Neural Network with Shape Prior Applied to Cardiac MRI Segmentation. IEEE Journal of Biomedical and Health Informatics (2018. 2区)
* Sheng Lian, Zhiming Luo, Zhun Zhong, Xiang Lin, Songzhi Su, Shaozi Li: Attention guided U-Net for accurate iris segmentation. Journal of Visual Communication and Image Representation(2018,3区C类)
* Min Huang, Guo-Rong Cai, Hongbo Zhang, Sheng Yu, Dong-Ying Gong, Donglin Cao, Shaozi Li, Song-Zhi Su: D iscriminative parts learning for 3D human action recognition. Neurocomputing 291:84-96 (2018. 2区)
* G Cai, S Su, W He, Y Wu, S Li: Combining 2D and 3D features to improve road detection based on stereo cameras. IET Computer Vision 12 (6), 834-843(2018. 4区)
* Minghui Shi, Changle Zhou, Jun Xie, Shaozi Li, Qingyang Hong, Min Jiang, Fei Chao, Weifeng Ren, Xiangqian Liu, Dajun Zhou, Tianyu Yang: Electroence phalogram-based brain-computer interface for the Chinese spelling system:a survey. Frontiers of IT & EE 19(3):423-436 (2018)
* Zhiming Luo, Pierre-Marc Jodoin, Song-Zhi Su, Shao-Zi Li, Hugo Larochelle: T raffic Analytics With Low-Frame-Rate Videos. IEEE Trans. Circuits Syst. Video Techn. 28(4): 878-891 (2018)
* Jia Zhang, Candong Li, Yaojin Lin, Youwei Shao, Shaozi Li: C omputational drug repositioning using collaborative filtering via multi-source fusion. Expert Syst. Appl. 84:281-289 (2017)
* Min Huang, Song-Zhi Su, Guo-Rong Cai, Hongbo Zhang, Donglin Cao, Shao-Zi Li: M eta-action descriptor for action recognition in RGBD video. IET Computer Vision 11(4):301-308 (2017)
* Sheng Yu, Yun Cheng, Li Xie, Shao-Zi Li: F ully convolutional networks for action recognition. IET Computer Vision 11(8):744-749 (2017)
* Zhun Zhong, Mingyi Lei, Donglin Cao, Jianping Fan, Shaozi Li: C lass-specific object proposals re-ranking for object detection in automatic driving. Neurocomputing 242:187-194 (2017)
* Sheng Yu, Yun Cheng, Li Xie, Zhiming Luo, Min Huang, Shaozi Li: A novel recurrent hybrid network for feature fusion in action recognition. J. Visual Communication and Image Representation 49:192-203 (2017)
* Dao-Xun Xia, Song-Zhi Su, Li-Chuan Geng, Guo-xi Wu, Shao-Zi Li: L earning rich features from objectness estimation for human lying-pose detection. Multimedia Syst. 23(4):515-526 (2017)
* Sheng Yu, Yun Cheng, Songzhi Su, Guo-Rong Cai, Shaozi Li: S tratified pooling based deep convolutional neural networks for human action recognition. Multimedia Tools Appl. 76(11):13367-13382 (2017)
* Zhun Zhong, Songzhi Su, Donglin Cao, Shaozi Li, Zhihan Lv: D etecting ground control points via convolutional neural network for stereo matching. Multimedia Tools Appl. 76(18):18473-18488 (2017)
* Wei Liu, Shaozi Li, Donglin Cao, Songzhi Su, Rongrong Ji: D etection based object labeling of 3D point cloud for indoor scenes. Neurocomputing 174:1101-1106 (2016)
* Li-Chuan Geng, Pierre-Marc Jodoin, Song-Zhi Su, Shao-Zi Li: C BDF: Compressed Binary Discriminative Feature. Neurocomputing 184:43-54 (2016)
* Yuanzheng Cai, Rongrong Ji, Shaozi Li: D ynamic programming based optimized product quantization for approximate nearest neighbor search. Neurocomputing 217:110-118 (2016)
* Yuanzheng Cai, Shaozi Li, Yun Cheng, Rongrong Ji: L ocal consistent hierarchical Hough Match for image re-ranking. J. Visual Communication and Image Representation 37:32-39 (2016)
* Si Chen, Shaozi Li, Rongrong Ji, Yan Yan, Shunzhi Zhu: D iscriminative local collaborative representation for online object tracking. Knowl.-Based Syst. 100:13-24 (2016)
* Shaozi Li, Miaohui Zhang, Songzhi Su, Bing Shuai, Rongrong Ji: D ecomposed human localization from social photo album. Multimedia Syst. 22(1):137-148 (2016)
* Wei Liu, Shaozi Li, Xianming Lin, Yun-Dong Wu, Rongrong Ji: S pectral-spatial co-clustering of hyperspectral image data based on bipartite graph. Multimedia Syst. 22(3):355-366 (2016)
* Donglin Cao, Rongrong Ji, Dazhen Lin, Shaozi Li: A cross-media public sentiment analysis system for microblog. Multimedia Syst. 22(4):479-486 (2016)
* Miaohui Zhang, Shaozi Li, Xianming Lin, Songzhi Su, Rongrong Ji: F ast verification via statistical geometric for mobile visual search. Multimedia Syst. 22(4) :525-534 (2016)
* Songzhi Su, Sin-Sian Wu, Shu-Yuan Chen, Der-Jyh Duh, Shaozi Li: M ulti-view fall detection based on spatio-temporal interest points. Multimedia Tools Appl. 75(14) :8469-8492 (2016)
* Donglin Cao, Rongrong Ji, Dazhen Lin, Shaozi Li: Visual sentiment topic model based microblog image sentiment analysis. Multimedia Tools Appl. 75(15):8955-8968 (2016)
* Shao-Zi Li, Bin Yu, Wei Wu, Song-Zhi Su, Rongrong Ji: Feature learning based on SAE-PCA network for human gesture recognition in RGBD images. Neurocomputing 151:565-573 (2015)
* Songzhi Su, Zhi-Hui Liu, Suping Xu, Shaozi Li, Rongrong Ji: Sparse auto-encoder based feature learning for human body detection in depth image. Signal Processing 112:43-52 (2015)
* Hongbo Zhang, Shaozi Li, Shu-Yuan Chen, Songzhi Su, Xianming Lin, Donglin Cao: Locating and recognizing multiple human actions by searching for maximum score subsequences. Signal, Image and Video Processing 9(3):705-714 (2015)
* Si Chen, Shaozi Li, Songzhi Su, Qi Tian, Rongrong Ji: Online MIL tracking with instance-level semi-supervised learning. Neurocomputing 139:272-288 (2014)
* Li-Chuan Geng, Songzhi Su, Donglin Cao, Shaozi Li: Perspective-Invariant Image Matching Framework with Binary Feature Descriptor and APSO. IJPRAI 28(8)(2014)
* Si Chen, Shaozi Li, Songzhi Su, Donglin Cao, Rongrong Ji: Online semi-supervised compressive coding for robust visual tracking. J. Visual Communication and Image Representation 25(5):793-804 (2014)
* Hongbo Zhang, Shang-An Li, Shu-Yuan Chen, Songzhi Su, Der-Jyh Duh, Shaozi Li: Adaptive photograph retrieval method. Multimedia Tools Appl. 70(3):2189-2209 (2014)
* Kuo-Wei Li, Shu-Yuan Chen, Songzhi Su, Der-Jyh Duh, Hongbo Zhang, Shaozi Li: Logo detection with extendibility and discrimination. Multimedia Tools Appl. 72(2):1285-1310 (2014)