Publications

2024

Yubo Chang, Fan Lyu, Zhang Zhang, Liang Wang. Understanding Driving Risks via Prompt Learning. In IEEE SMC, 2024. [pdf] [code]
Kaile Du, Yifan Zhou, Fan Lyu, Yuyang Li, Chen Lu, Guangcan Liu. Confidence Self-Calibration for Multi-Label Class-Incremental Learning. In ECCV, 2024. [pdf] [code]
Liqing Gao, Fan Lyu, Peng Shi, Lei Zhu, Junfu Pu, Liang Wan, Wei Feng. Overcoming Modality Bias in Question-Driven Sign Language Video Translation. IEEE TCSVT, 2024. [pdf] [code]
Ziqing Zhao, Fan Lyu, Linyan Li, Fuyuan Hu, Minming Gu, Sun Li. Towards Long-Term Remembering in Federated Continual Learning. Congnituve Computation, 2024. [pdf]
Jiayao Tan, Fan Lyu, Linyan Li, Fuyuan Hu, Tingliang Feng, Fenglei Xu, Zhang Zhang, Rui Yao, Liang Wang. Dynamic V2X Perception from Road-to-Vehicle Vision. IEEE TIV, 2024. [pdf] [code]
Dinghang Li, Zongqing Lu, Weiliang Zheng, Qingmin Liao, Fan Lyu. MetaMask: Improving Few-Shot Semantic Segmentation via Multi-Mask Calibriation. In IEEE IJCNN, 2024. [pdf] [code]
Liqing Gao, Wei Feng, Fan Lyu, Liang Wan. Combinational sign language recognition. CVIU, 2024. [pdf] [code]
Weiqi Li, Fan Lyu, Fanhua Shang, Liang Wan, Wei Feng. Long-Tailed Learning as Multi-Objective Optimization. In AAAI (Oral), 2024. [pdf] [code]

Kaile Du*, Fan Lyu*, Linyan Li, Fuyuan Hu, Wei Feng, Fenglei Xu, Xuefeng Xi, Hanjing Cheng. Multi-Label Continual Learning using Augmented Graph Convolutional Network. IEEE TMM [pdf]
Daofeng Liu*, Fan Lyu, Linyan Li, Fuyuan Hu. Centroid-based Re-hearsal for Online Continual Learning. In ICASSP, 2023.
Fan Lyu, Qing Sun, Fanhua Shang, Wei Feng, Liang Wan. Measuring Asymmetric Gradient Discrepancy in Paralllel Continual Learning. In ICCV, 2023.
Hao Chen, Linyan Li, Fan Lyu, Fuyuan Hu, Zhenping Xia, Fenglei Xu. Two-level Graph Network for Few-Shot Class-Incremental Learning. In ICME, 2023
Liqing Gao, Lianyu Hu, Fan Lyu, Lei Zhu, Liang Wan, Chi-Man Pun, Wei Feng. Difference-Guided Multi-Scale Spatial-Temporal Representation for Sign Lan-guage Recognition. The Visual Computer (TVC), 2023.

Qing Sun*, Fan Lyu*, Fanhua Shang, Wei Feng, Liang Wan. Explor-ing Example Influence on Plasticity or Stability in Continual Learning [C]. In NeurIPS, 2022.
Kaile Du*, Fan Lyu*, Fuyuan Hu, Linyan Li, Wei Feng, Fenglei Xu and Qiming Fu. AGCN: Augmented Graph Convolutional Network for Lifelong Multi-Label Image Recognition[C]. IEEE International Conference on Multimedia and Expo (ICME), 2022.
Hao Chen, Linyan Li, Fuyuan Hu, Fan Lyu, Liuqing Zhao, Kaizhu Huang, Wei Feng Zhenping Xia. Learning Multi-Semantic Hypergraph for Few-Shot Data[J]. Pattern Recognition, 2022(142), 109677.
Linyan Li, Kaile Du, Minming Gu, Fuyuan Hu, Fan Lyu. Region Collaborative Net-work for Detection-based Vision-Language Understanding[J]. Mathematics, 2022; 10(17):3110.
Ye Liu, Liang Wan, Fan Lyu, Wei Feng . Fine-Grained Scale Space Learn-ing for Single Image Super-Resolution[J]. The Visual Computer (TVC), 2022.

Fan Lyu, Shuai Wang, Wei Feng, Zihan Ye, Fuyuan Hu, Song Wang. Multi-domain Multi-task Rehearsal for Lifelong Learning[C]. In Proceedings of The Thirty-Fifth AAAI Conference on Artiﬁcial Intelligence (AAAI), 2021.
Liuqing Zhao*, Fan Lyu*, Fuyuan Hu, Fenglei Xu, Kaizhu Huang and Linyan Li. Each Attribute Matters: Contrastive Attention for Sentence-based Image Edit-ing[C]. In BMVC, 2021.
Zihan Ye, Fuyuan Hu, Fan Lyu, Linyan Li, and Kaizhu Huang. Disentan-gling Semantic-to-visual Confusion for Zero-shot Learning[J]. IEEE Transactions on Multimedia (TMM), 2021.

Chaorui Deng, Qi Wu, Qingyao Wu, Fan Lyu, Fuyuan Hu, Mingkui Tan. Visual Grounding via Accumulated Attention[J]. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence (TPAMI), 2020.
Fan Lyu, Wei Feng, Song Wang. vtGraphNet: Learning weakly-supervised scene graph for complex visual grounding[J]. Neurocomputing, 2020, 413: 51-60.
Zhongguo Li, Fan Lyu, Wei Feng, Song Wang. Modeling Cross-View Interaction Consistency for Paired Egocentric Interaction Recognition[C]. 2020 IEEE International Conference on Multimedia and Expo (ICME). 2020.
Shuai Wang, Fan Lyu, Wei Feng, Song Wang. MutAtt: Visual-Textual Mutual Guidance for Referring Expression Comprehension[C]. 2020 IEEE International Conference on Mul-timedia and Expo (ICME). 2020.
Zihan Ye, Fuyuan Hu, Yin Liu, Zhenping Xia, Fan Lyu, Pengqing Liu. Associat-ing Multi-Scale Receptive Fields for Fine-grained Recognition[C]. IEEE International Conference on Image Processing (ICIP), 2020: 1-5.

Fan Lyu, Qi Wu, Fuyuan Hu, Qingyao Wu and Mingkui Tan. Attend and Imagine: Multi-label Image Classification with Visual Attention and Recurrent Neural Networks[J]. IEEE Transactions on Multimedia (TMM), 2019,21(8),1971-1981.
Zihan Ye*, Fan Lyu*, Linyan Li, Yu Sun, Qiming Fu and Fuyuan Hu. SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning[C]. IEEE International Conference on Multimedia and Expo (ICME), 2019. (Oral)
Fan Lyu, Fuyuan Hu, Yanning Zhang, Zhenping Xia and Vector S. Sheng. Image Captioning Based on The Feedback Attention Mechanism[J]. Journal of Comput-er-Aided Design & Computer Graphics, 2019.
Fan Lyu, Linyan Li, Shengli Victor Sheng, Qiming Fu and Fuyuan Hu. Multi-label image classification in smart cities via coarse-to-fine attention[J]. Chi-nese Journal of Electronics, 2019,28(6),1118-1126.

Chaorui Deng, Qi Wu, Qingyao Wu, Fuyuan Hu, Fan Lyu, Mingkui Tan, Qingyao Wu. Visual Grounding via Accumulated Attention[C]. In Proceedings of IEEE Conference on Comput-er Vision and Pattern Recognition (CVPR), 2018.
Zihan Ye*, Fan Lyu*, Linyan Li, Yu Sun, Qiming Fu and Fuyuan Hu. Unsupervised Object Transﬁguration with Attention[J]. Cognitive Computation, 2018, 11(6), 869-878.
Fan Lyu, Fuyuan Hu, Victor S. Sheng, Zhengtian Wu, Qiming Fu and Baochuan Fua. Coarse to Fine: Multi-label Image Classification with Global/Local Attention[C]. IEEE In-ternational Smart Cities Conference (ISC2), 2018.
Zihan Ye*, Fan Lyu*, Linyan Li, Yu Sun, Qiming Fu and Fuyuan Hu. DAU-GAN: Unsupervised object transfiguration via Deep Attention Unit[C]. International Conference on Brain Inspired Cognitive Systems (BICS), 2018. (Best Poster Paper)