李亮,博士,中科院计算所研究员,博士生导师,国家基金委优秀青年基金获得者,中科院青创会会员。研究领域为生成式人工智能、计算机视觉和多模态学习,发表TPAMI等汇刊和CCF-A类会议论文90余篇,谷歌引用4400余次,获国际会议最佳论文奖4次(包括CCF-A类会议ACM MM2024最佳论文奖),6项工作入选ESI高被引论文,编写译著1部;主持/参与科技部科技创新2030重大项目、973课题、NSFC应急管理重点项目、NSFC优青/面上/青年项目等20余项,担任国际期刊Electronics和JCST编委,国际会议ACL/EMNLP/NAACL高级领域主席,ACM MM领域主席,ACM SIGMM中国分会高校合作负责人,参与组织7次ACM/IEEE国际会议和6次国内会议。获2024年中国图象图形学学会青年科学家奖、2022年浙江省科技进步一等奖、2020年吴文俊人工智能自然科学一等奖、2013中科院院长奖、2012年计算所所长特别奖、2008年亚太大学生机器人大赛国内赛和国际赛冠军。参与起草发布了全球首个内容自动化生产标准《机器生产内容自动化分级》,相关技术在华为、淘宝、大华、华数传媒等公司使用,服务于2022北京冬奥会等任务。
2016年5月 — 至今:中科院计算所,助理研究员/副研究员/研究员
2013年6月 — 2016年5月:中国科学院大学,博士后
2008年7月 — 2013年6月:中国科学院计算技术研究所,工学博士
2004年9月 — 2008年7月:西安交通大学,电信学院,工学学士
期刊会议服务
[1] 国际期刊Electronics/Symmetry/JCST编委
[2] 国际会议ACL/EMNLP/NAACL高级领域主席,ACM MM领域主席,IEEE ICME领域主席
会议组织服务
[1] IEEE Forum on Intelligent Media Computing 2022, Public Chair
[2] ACM Multimedia Asia 2019, Local Arrangement Chair
[3] CSIG SOMIA 2018, Organization Chair
[4] IEEE GlobalSIP2017 Symposium of Knowledge-based Multimedia Computing, General Co-chair
[5] International Conference on Internet Multimedia Computing and Service (ICIMCS) 2017 Special Session Chair
[6] Pacific Rim Conference on Multimedia (PCM) 2017 Local Chair
[7] International Conference on Internet Multimedia Computing and Service (ICIMCS) 2015 Organization Chair
近期代表性期刊文章:
[1] Yunbin Tu, Liang Li*, Li Su, Zheng-Jun Zha, Qingming Huang. SMART: Syntax-calibrated Multi-Aspect Relation Transformer for Change Captioning, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024. (机器学习领域顶级期刊,CCF A类)
[2] Beichen Zhang, Liang Li*, Shuhui Wang, Shaofei Cai, Zheng-Jun Zha, Qi Tian, Qingming Huang. Inductive State-Relabeling Adversarial Active Learning with Heuristic Clique Rescaling. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024. (机器学习领域顶级期刊,CCF A类)
[3] Wei Tang, Liang Li, Xuejing Liu, Lu Jin, Jinhui Tang and Zechao Li, Context Disentangling and Prototype Inheriting for Robust Visual Grounding, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023. (机器学习领域顶级期刊,CCF A类)
[4] Xuejing Liu, Liang Li*, Shuhui Wang, Zheng-Jun Zha, Zechao Li, Qi Tian, Qingming Huang. Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. (机器学习领域顶级期刊,CCF A类)
[5] Hao Wang, Zheng-Jun Zha, Liang Li, Xuejin Chen, Jiebo Luo. Semantic and Relation Modulation for Audio-Visual Event Localization. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. (机器学习领域顶级期刊,CCF A类)
[6] Yukun Huang, Xueyang Fu, Liang Li, Zheng-Jun Zha: Learning Degradation-Invariant Representation for Robust Real-World Person Re-Identification. International Journal of Computer Vision (IJCV), 2022. (计算机视觉领域顶级期刊,CCF A类)
[7] Liang Li, Tongyu Lu, Yaoqi Sun, Yuhan Gao, Chenggang Yan, Zhenghui Hu and Qingming Huang. Progressive Decision Boundary Shifting for Unsupervised Domain Adaptation. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024. (机器学习领域顶级期刊,中科院1区)
[8] Yiting Liu, Liang Li*, Yunbin Tu, Beichen Zhang, Zheng-Jun Zha, Qingming Huang. Dynamic Strategy Prompt Reasoning for Emotional Support Conversation. IEEE Transactions on Multimedia (TMM), 2024. (多媒体领域顶级期刊,中科院1区)
[9] Beichen Zhang, Liang Li*, Zheng-jun Zha, Jiebo Luo, Qingming Huang. Downstream-Pretext Domain Knowledge Traceback for Active Learning, IEEE Transactions on Multimedia (TMM), 2024. (多媒体领域顶级期刊,中科院1区)
[10] Yunbin Tu, Liang Li*, Li Su, Junping Du, Ke Lu, Qingming Huang. Viewpoint-Adaptive Representation Disentanglement Network for Change Captioning, IEEE Transactions on Image Processing (TIP), 2023. (图象处理领域顶级期刊,CCF A类)
[11] Shaofei Cai, Liang Li*, Xinzhe Han, Shan Huang, Qi Tian and Qingming Huang. Semantic and Correlation Disentangled Graph Convolutions for Multi-label Image Recognition. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023. (机器学习领域顶级期刊,中科院1区)
[12] Hao Wang, Zheng-Jun Zha, Liang Li*, Xuejin Chen, Jiebo Luo. Context-Aware Proposal-Boundary Network with Structural Consistency for Audio-Visual Event Localization, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023. (机器学习领域顶级期刊,中科院1区)
[13] Yunbin Tu, Liang Li*, Li Su, Ke Lu and Qingming Huang, Neighborhood Contrastive Transformer for Change Captioning. IEEE Transactions on Multimedia (TMM), 2023. (多媒体领域顶级期刊,中科院1区)
[14] Liang Li, Xingyu Gao, Jincan Deng, Yunbin Tu, Zheng-Jun Zha and Qingming Huang. Long Short-Term Relation Transformer with Global Gating for Video Captioning, IEEE Transactions on Image Processing (TIP), 2022. (图象处理领域顶级期刊,CCF A类)
[15] Yunbin Tu, Liang Li*, Li Su, Shengxiang Gao, Zhengtao Yu and Qingming Huang. I2Transformer: Intra- and-inter-relation Embedding Transformer for TV Show Captioning, IEEE Transactions on Image Processing (TIP), 2022. (图象处理领域顶级期刊,CCF A类)
近期代表性会议文章:
[1] Jiadong Pan, Hongcheng Gao, Zongyu Wu, Taihang Hu, Li Su, Qingming Huang, Liang Li*. Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning. Annual Conference on Neural Information Processing Systems (NeurIPS), 2024, Spotlight. (机器学习领域顶级会议,CCF-A类)
[2] Zhedong Zhang, Liang Li*, Gaoxiang Cong, Haibing Yin, Yuhan Gao, Chenggang Yan, Anton van den Hengel, Yuankai Qi. From Speaker to Dubber: Movie Dubbing with Prosody and Duration Consistency Learning. ACM Multimedia (MM), 2024, Oral,最佳论文奖. (多媒体领域顶级会议,CCF-A类)
[3] Yunbin Tu, Liang Li*, Li Su, Zheng-Jun Zha, Chenggang Yan, Qingming Huang. Context-aware Difference Distilling for Multi-change Captioning, Association of Computational Linguistics (ACL), 2024. (自然语言处理领域顶级会议,CCF-A类)
[4] Junxi Chen, Liang Li*, Li Su, Zheng-Jun Zha, Qingming Huang. Prompt-enhanced Multiple Instance Learning for Weakly Supervised Anomaly Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024. (计算机视觉领域顶级会议,CCF-A类)
[5] Henglei Lv, Jiayu Xiao, Liang Li*. Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image Personalization. ACM Multimedia (MM), 2024. (多媒体领域顶级会议,CCF-A类)
[6] Yiming Cui, Liang Li*, Jiehua Zhang, Chenggang Yan, Hongkui Wang, Shuai Wang, Jin Heng, Wu Li. Stochastic Context Consistency Reasoning for Domain Adaptive Object Detection. ACM Multimedia (MM), 2024. (多媒体领域顶级会议,CCF-A类)
[7] Yunbin Tu, Liang Li*, Li Su, Chenggang Yan, Qingming Huang. Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning, European Conference on Computer Vision (ECCV), 2024. (计算机视觉领域顶级会议,CCF-B类)
[8] Jiayu Xiao, Henglei Lv, Liang Li*, Shuhui Wang, Qingming Huang, R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation, International Conference on Learning Representations (ICLR), 2024. (机器学习领域顶级会议)
[9] Yunbin Tu, Liang Li*, Li Su, Zheng-Jun Zha, Chenggang Yan, Qingming Huang. Self-Supervised Cross-View Representation Reconstruction for Change Captioning, IEEE International Conference on Computer Vision (ICCV), 2023. (计算机视觉领域顶级会议,CCF-A类)
[10] Zhenhuan Liu, Liang Li*, Jiayu Xiao, Zheng-Jun Zha, Qingming Huang. Text-Driven Generative Domain Adaptation with Spectral Consistency Regularization, IEEE International Conference on Computer Vision (ICCV), 2023. (计算机视觉领域顶级会议,CCF-A类)
[11] Yang Wang, Long Peng, Liang Li, Yang Cao, Zheng-Jun Zha. Decoupling-and-Aggregating for Image Exposure Correction, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. (计算机视觉领域顶级会议,CCF-A类)
[12] Gaoxiang Cong, Liang Li*, Yuankai Qi, Zheng-Jun Zha, Qi Wu, Wenyu Wang, Bin Jiang, Ming-Hsuan Yang, Qingming Huang. Learning to Dub Movies via Hierarchical Prosody Models. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. (计算机视觉领域顶级会议,CCF-A类)
[13] Yiting Liu, Liang Li*, Beichen Zhang, Shan Huang, Zheng-Jun Zha, Qingming Huang. MaTCR: Modality-Aligned Thought Chain Reasoning for Multimodal Task-Oriented Dialogue Generation, ACM International Conference on Multimedia (MM), 2023. (多媒体领域顶级会议,CCF-A类)
[14] Jiayu Xiao, Liang Li*, Chaofei Wang, Zheng-Jun Zha and Qingming Huang. Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (计算机视觉领域顶级会议,CCF-A类)
[15] Shaofei Cai, Liang Li*, Xinzhe Han, Jiebo Luo, Zheng-Jun Zha and Qingming Huang. Automatic Relation-aware Graph Network Proliferation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022, Oral. (计算机视觉领域顶级会议,CCF-A类)
专利:
[1] 一种候选回答语句生成和自然语言选择方法及系统(专利号:ZL201911017584.2);
[2] 一种图像分割、模型训练方法、装置、设备及介质(专利号:ZL202211076329.7);
[3] 数据流的生成方法、电子设备及计算机可读存储介质(专利号:ZL202211059878.3);
[4] 目标检测模型的训练方法、目标检测方法及相关设备(专利号:ZL202211064180.0);
[5] 一种有效的显著性预测模型方法(专利号:ZL2019106264059).