Journal Articles
Sheng Liu, Zhongwei Cheng, Lin Chen, Jiebo Luo, Junsong Yuan, "A Compositional Model for Visual Relationship Grounding," IEEE Transactions on Image Processing (T-IP), 2022 (in press)
Yiming Xu, Lin Chen, Lixin Duan, Ivor Tsang, Jiebo Luo, "Open Set Domain Adaptation with Soft Unknown-Class Rejection," IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 2021 (in press).
Jin Chen, Xinxiao Wu, Lixin Duan, Lin Chen, "Sequential Instance Refinement for Cross-Domain Object Detection in Images," IEEE Transactions on Image Processing (T-IP), 2021.
Wen Li, Lin Chen, Dong Xu, Luc Van Gool, "Visual Recognition in RGB Images and Videos by Learning from RGB-D Data," IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2017
Li Niu, Xinxing Xu, Lin Chen, Lixin Duan, and Dong Xu, "Action and Event Recognition in Video by Learning From Heterogenous Web Sources," IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), March 2016 [link]
Lin Chen, Dong Xu, Ivor W. Tsang, and Xuelong Li, "Spectral Embedded Hashing for Scalable Image Retrieval," IEEE Transactions on Systems, Man, and Cybernetics, Part B (T-SMCB), November 2013.
Lin Chen, Dong Xu, Ivor W. Tsang, and Jiebo Luo, "Tag-based Image Retrieval Improved by Augmented Features and Group-based Refinement," IEEE Transactions on Multimedia (T-MM), 14(4):1057-1067, August 2012
Lin Chen, Ivor W. Tsang, Dong Xu, "Laplacian Embedded Regression for Scalable Manifold Regularization," IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 23(6): 902-915, June 2012.
An efficient algorithm is proposed to handle large-scale Manifold Regularization problem and our proposed method can scale up to dataset with around 70,000 samples.
Conference Papers
Mohammad Mahdi Kamani, Yuhang Yao, Hanjia Lyu, Zhongwei Cheng, Lin Chen, Liangju Li, Carlee Joe-Wong, Jiebo Luo, "Wyze Rule: Federated Rule Dataset for Rule Recommendation Benchmarking," NeurIPS 2023 Datasets and Benchmark, 2023.
Zhongjie Yu, Shuyang Wang, Lin Chen, Zhongwei Cheng, "HalluAudio: Hallucinate Frequency as Concepts for Few-Shot Audio Classification," IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023.
Yuhang Yao, Mohammad M. Kamani, Zhongwei Cheng, Lin Chen, Carlee Joe-Wong, Tianqiang Liu, "FedRule: Federated Rule Recommendation System with Graph Neural Networks," ACM/IEEE Conference on Internet of Things Design and Implementation (IoTDI), 2023. [PDF]
Yuhang Yao, Mohammad M. Kamani, Zhongwei Cheng, Lin Chen, Carlee Joe-Wong, Tianqiang Liu, "FedRule: Federated Rule Recommendation System with Graph Neural Networks," International Workshop on Federated Learning: Recent Advances and New Challenges in Conjunction with NeurIPS 2022 (FL-NeurIPS'22). [PDF]
Zhongjie Yu, Gaoang Wang, Lin Chen, Jiebo Luo, Sebastian Raschka, "When Few-Shot Learning Meets Video Object Detection," International Conference on Pattern Recognition (ICPR), Montreal, Quebec, Canada, 2022.
Sumanth Chennupati, Mohammad Mahdi Kamani, Zhongwei Cheng, Lin Chen, "Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation," The British Machine Vision Conference (BMVC), 2021
Gaoang Wang, Lin Chen, Tianqiang Liu, Mingwei He, Jiebo Luo, "DAIL: Dataset-Aware and Invariant Learning for Face Recognition," International Conference on Pattern Recognition (ICPR), Milan, Italy, December 2020.
Yiming Xu , Lin Chen, Zhongwei Cheng, Lixin Duan, Jiebo Luo, "Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation," The Conference on Empirical Methods in Natural Language Processing (EMNLP), Findings of EMNLP, November 2020.
Zhongjie Yu, Lin Chen, Zhongwei Cheng, Jiebo Luo, "TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning," in IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
Lixin Duan, Yanwu Xu, Wen Li, Lin Chen, Damon Wing Kee Wong, Tien Yin Wong, and Jiang Liu, "Incorporating Privileged Genetic Information for Fundus Image Based Glaucoma Detection,'' in International Conference on Medical Image Analysis and Computer Aided Intervention, (MICCAI), Boston, Massachusetts, September 2014. [PDF]
Yanwu Xu, Ying Quan, Ruoying Li, Lixin Duan, Lin Chen, Huiying Liu, Damon Wing Kee Wong, Jiang Liu, Mani Baskaran, Shamira Perera, Ting Aung, and Tien Ying Wong, "Local Patch Reconstruction Framework for Optic Cup Localization in Glaucoma Detection,'' in International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2014. [PDF coming soon]
Lin Chen, Wen Li, and Dong Xu, "Recognizing RGB Images by Learning from RGB-D Data," in IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2014. [PDF]
A new method called domain adaptation from multi-view to single-view (DA-M2S) is proposed for object recognition and gender classification in RGB images, by learning from RGB-D data. DA-M2S can effectively use the additional depth data in the source domain, at the meantime minimise the domain distribution mismatches between the source domain and target domain.
Lin Chen, Lixin Duan, and Dong Xu, "Event Recognition in Videos by Learning from Heterogeneous Web Sources," in IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 2666-2673. [PDF][Poster] [BibTex]
A new method called multi-domain adaptation with heterogeneous sources (MDA-HS) is proposed for event recognition in (unlabeled) consumer videos (target domain) by leveraging a larger number of web videos and web images (heteregeneous source domains). In MDA-HS, we learn an optimal classifier by simultaneously seeking the optimal weights for different source domains and inferring the labels of the unlabeled target domain data. An efficient group-based multiple kernel learning algorithm is employed to solve our optimization problem.
Lin Chen, Lixin Duan, Ivor W. Tsang, and Dong Xu, "Efficient Discriminative Learning of Class Hierarchy for Many Class Prediction," in Asian Conference on Computer Vision (ACCV), 2012, pp. 274-288. [PDF][Poster][BibTex]
An efficient adaptive algorithm to learn the class hierarchy.
Lin Chen, Dong Xu, Ivor W. Tsang and Jiebo Juo, "Tag-based Web Photo Retrieval Improved by Batch Mode Re-Tagging," in IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2010, pp. 3440-3446. [PDF][Poster] [BibTex]
We proposed a very simple but highly effective classification method called AFSVM to learn visual concepts, and a group-based refinement method to remove noisy tags as well as to add new tags for images within one group. The proposed AFSVM can learn robust classifiers for concepts with limited labeled training data, by transferring knowledge from pre-learnt classifiers of concepts with sufficient labeled training data.