职称 / 硕（博）导：副研究院 / 硕导
专硕招生专业 / 方向：人工智能 / 智能视听技术
主要研究领域：认知启发的人工智能，视觉表征学习，连续学习
电子邮箱Email：qxlai@cuc.edu.cn
个人简介
副研究员，校级青年拔尖人才。博士毕业于香港中文大学计算机科学与工程系，师从Prof. Xiang XU 和Prof. Hanqiu Sun；硕士、本科均就读于华中科技大学自动化学院。主要从事计算机视觉与智能感知研究，聚焦复杂环境下的视频图像表征学习、注意力机制及连续学习等方向，以第一作者或通讯作者在计算机视觉与人工智能领域顶级期刊和会议发表论文10余篇，包括IEEE TIP、IEEE TCSVT、PR、NeurIPS、CVPR、ICCV、IJCAI、Visual Intelligence等，谷歌学术引用超过3500次。担任IEEE TPAMI、ICLR、NeurIPS、ICML、CVPR、ICCV、ECCV等顶级期刊与会议审稿人。
个人主页：https://ashleylqx.github.io/
谷歌学术主页：https://scholar.google.com/citations?user=LwIItp4AAAAJ&hl=zh-CN。
欢迎对人工智能和视频图像表征学习方向感兴趣的本科生、研究生加入团队。
承担的主要科研项目
[1] 国家自然科学青年基金项目，连续学习中知识的表示、学习和反向迁移问题研究，在研，主持。
[2] 校级项目，基于提示的连续学习算法研究，结项，主持。
[3] 校级项目，基于眼动的视频自监督学习算法研究，结项，主持。
代表性学术成果
[1] Temporal consistency-aware text-to-motion generation, Visual Intelligence, EI, 2026, 通讯作者 Hongsong Wang, Wenjing Yan, Qiuxia Lai^, Xin Geng (^ Corresponding author)
[2] A Conditional Probability Framework for Compositional Zero-shot Learning, IEEE International Conference on Computer Vision (ICCV), 2025. CCF-A, 共同一作 Peng Wu*, Qiuxia Lai*, Hao Fang, Guo-Sen Xie, Yilong Yin, Xiankai Lu, Wenguan Wang (* Equal contribution)
[3] Cycle-Consistent Learning for Joint Layout-to-Image Generation and Object Detection, IEEE International Conference on Computer Vision (ICCV), 2025. CCF-A, 共同一作 Xinhao Cai*, Qiuxia Lai*, Gengsheng Pei, Xiangbo Shu, Yazhou Yao, Wenguan Wang (* Equal contribution)
[4] Vector Quantization Prompting for Rehearsal-Free Continual Learning, Neural Information Processing Systems (NeurIPS), 2024. CCF-A, 通讯作者 Li Jiao, Qiuxia Lai^ , Yu Li, Qiang Xu (^ Corresponding author)
[5] Poly Kernel Inception Network for Remote Sensing Detection, IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024. CCF-A, 共同一作 Xinhao Cai*, Qiuxia Lai*, Yuwei Wang*, Wenguan Wang, Zeren Sun, Yazhou Yao (* Equal contribution)
[6] Spatial Attention for Human-Centric Visual Understanding: An Information Bottleneck Method, Computer Vision and Image Understanding (CVIU), 2024. CCF-B, 第一作者Qiuxia Lai, Yongwei Nie, Yu Li, Hanqiu Sun, Qiang Xu
[7] Information Bottleneck-Inspired Spatial Attention for Robust Semantic Segmentation in Autonomous Driving, International Conference on Control, Automation, Robotics and Vision (ICARCV), 2024, EI, 第一作者Qiuxia Lai, Qipeng Tang
[8] Self-supervised Video Representation Learning via Capturing Semantic Changes Indicated by Saccades, IEEE Trans. on Circuits and Systems for Video Technology (IEEE TCSVT), 2023. SCI一区Top, 第一作者Qiuxia Lai, Ailing Zeng, Ye Wang, Lihong Cao, Yu Li, Qiang Xu
[9] Weakly Supervised Visual Saliency Prediction, IEEE Trans. on Image Processing (IEEE TIP), 2022. SCI一区Top,第一作者Qiuxia Lai, Tianfei Zhou, Salman Khan, Hanqiu Sun, Jianbing Shen, Ling Shao
[10] Information Bottleneck Approach to Spatial Attention Learning, International Joint Conference on Artificial Intelligence (IJCAI), 2021. CCF-A, 第一作者Qiuxia Lai, Yu Li, Ailing Zeng, Minhao Liu, Hanqiu Sun, Qiang Xu
[11] Understanding more about human and machine attention in deep neural networks. IEEE Trans. on Multimedia (IEEE TMM), 2020, SCI 一区 Top, 第一作者Qiuxia Lai, Salman Khan, Yongwei Nie, Hanqiu Sun, Jianbing Shen, Ling Shao.
[12] Video super-resolution via pre-frame constrained and deep-feature enhanced sparse reconstruction. Pattern Recognition (PR), 2020, SCI 一区 Top, 第一作者Qiuxia Lai, Yongwei Nie, Hanqiu Sun, Qiang Xu, Zhensong Zhang, Mingyu Xiao.
[13] Video saliency prediction using spatiotemporal residual attentive networks. IEEE Trans. on Image Processing (IEEE TIP), 2019, SCI 一区 Top, 第一作者Qiuxia Lai, Wenguan Wang, Hanqiu Sun, Jianbing Shen.
[14] Temporal coherent video super-resolution via pre-frame-constrained sparse reconstruction. Computer Graphics International (CGI), 2018, CCF-C，第一作者Qiuxia Lai, Yongwei Nie, Zhensong Zhang, Hanqiu Sun.