Jia Li received the B.E. degree from Tsinghua University in July 2005 and Ph.D. degree from Chinese Academy of Sciences in January 2011, respectively. During 2011 and 2013, he used to serve as a Research Fellow and Visiting Assistant Professor in Nanyang Technological University, Singapore. As an attempt to link academic and industry, he worked at Shanda Innovations as a Senior Researcher during July 2011 and September 2012. In June 2014, he joined Beihang University, where he is currently an associate professor in School of Computer Science and Engineering, Beihang University.
- Computer Vision
- Artificial Intelligence
- Virtual Reality
Selected Honors & Awards
- Outstanding Young Scholar Program, Beihang University, 2016 (北航青年拔尖人才支持计划）
- Hundred Excellent Scholar Program, Beihang University, 2014 (北航卓越百人计划）
- Best Paper Award, IEEE International Conference on Multimedia Big Data, 2015 (最佳论文奖）
- Excellent Doctoral Dissertation Award, Beijing Municipal Education Commission, 2012 (北京市优博)
- Excellent Doctoral Dissertation Award, Chinese Academy of Sciences, 2012 (中科院优博)
- Special Prize of President Scholarship, Chinese Academy of Sciences, 2011 (中科院院长特别奖)
- Science-Technology Progress Award, First Grade (Rank: 9/11), Ministry of Education, 2010 (教育部科学技术进步奖一等奖)
【Book】Visual Saliency Computation: A Machine-Learning PerspectiveSpringer LNCS Series, May, 2014 (240 pages)
Finding the Secret of Image Saliency in the Frequency DomainIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.
Semantic Object Segmentation in Tagged Videos via DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
Measuring Visual Surprise Jointly from Intrinsic and Extrinsic Contexts for Image Saliency EstimationInternational Journal of Computer Vision (IJCV), 2016.
Learning Complementary Saliency Priors for Foreground Object Segmentation in Complex ScenesInternational Journal of Computer Vision (IJCV), 2015.
Visual Saliency with Statistical PriorsInternational Journal of Computer Vision (IJCV), 2014.
Probabilistic Multi-Task Learning for Visual Saliency Estimation in VideoInternational Journal of Computer Vision (IJCV), 2010.
Salient Object Detection: A BenchmarkIEEE Transactions on Image Processing (TIP), 2015.
Removing Label Ambiguity in Learning-Based Visual Saliency EstimationIEEE Transactions on Image Processing (TIP), 2012.
What is and What is not a Salient Object? Learning Salient Object Detector by Ensembling Linear Exemplar RegressorsIEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
Detecting Masked Faces in the Wild with LLE-CNNsIEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
Semantic Object Segmentation via Detection in Weakly Labeled VideoIEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
Primary Video Object Segmentation via Complementary CNNs and Neighborhood Reversible FlowInternational Conference on Computer Vision (ICCV), 2017.
Look Perceive and Segment: Finding the Salient Objects in Images via Two-stream Fixation-Semantic CNNsInternational Conference on Computer Vision (ICCV), 2017.
Embedding 3D Geometric Features for Rigid Object Part SegmentationInternational Conference on Computer Vision (ICCV), 2017.
A Data-driven Metric for Comprehensive Evaluation of Saliency ModelsInternational Conference on Computer Vision (ICCV), 2015.
Two-Stream Attentive CNNs for Image RetrievalACM International Conference on Multimedia (ACM MM), 2017.[Full paper,Oral]
Learning Discriminative Subspaces on Random Contrasts for Image Saliency AnalysisIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2017.
6-DOF Image Localization from Massive Geo-tagged Reference ImagesIEEE Transactions on Multimedia (TMM), 2016.
Multi-Task Rank Learning for Visual Saliency EstimationIEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2011.
Multi-task Rank Learning for Image Quality AssessmentIEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2016.
Structure-adaptive Shape Editing for Man-made ObjectsComputer Graphics Forum (CGF), 2016.
Robust Multiple Cameras Pedestrian Detection with Multi-view Bayesian NetworkPattern Recognition, 2015.
Fast estimation of relative poses for 6-DOF image localizationIEEE International Conference on Multimedia Big Data (BigMM), 2015. [Best Paper Award]
Cost-Sensitive Rank Learning from Positive and Unlabeled Data for Visual Saliency EstimationIEEE Signal Processing Letter (SPL), 2010. (Front Cover Article)
Selected Projects as PI and Co-PI
- PI: Visual Knowledge Transer and Salient Object Monitor on UAV platform driven by Multi-Scale Big Data, H863, 2017.3-2018.3 (国防科技创新特区课题，军口部分, 2.0M)
- PI: Outstanding Young Scholar Program, Beihang U., 2016.11-2019.12 (北京航空航天大学青年拔尖人才支持计划，1.2M)
- PI: Semantic Understanding of Visual Salient Content driven by Data Aggregation, State Key Laboratory of Virtual Reality Technology and Systems, 2017.4-2017.12 (虚拟现实技术与系统国家重点实验室自主课题, 70K)
- PI: Saliency-guided Segmentation and Semantic Analysis of Foreground Objects, NSFC, 2017.1-2020.12(国家自然科学基金面上项目, 0.63M)
- PI: Technologies of *** Intelligence, H863, 2015.7-2016.6 (国家863课题，军口部分, 0.2M)
- PI: Visual Attention-guided Image Object Understanding and 3D Modeling, State Key Laboratory of Virtual Reality Technology and Systems, 2015.3-2016.12 (虚拟现实技术与系统国家重点实验室自主课题, 0.1M)
- PI: Hundred Excellent Scholar Program, Beihang U., 2014.6-2020.5 (北京航空航天大学卓越百人支持计划，0.5M)
- PI: Learning-based Visual Saliency Computation using Latent Correlations, NSFC, 2014.1-2017.12 (国家自然科学基金面上项目, 0.8M)
- PI: Learning-based Computation of Selective Visual Attention, China Postdoctoral Science Foundation, 2013.5-2014.6 (国家博士后科学基金面上项目一等资助, 80K)
- Co-PI: Technologies of *** Video Detection, CNCERT/CC, 2015.2-2016.7 (国家互联网应急中心242课题, 0.65M/1.3M)
- Co-PI: Data-driven Editing and Generation of Interactable Content, NSFC, 2016.1-2020.12 (国家自然科学基金重点项目，0.3M/2.95M)
Professional Membership & Services
- Member, CCF Technical Committee of Virtual Reality and Visualization
- Member, CCF Technical Committee of Computer Vision,
- Senior Member, China Computer Federation (CCF)
- Senior Member, IEEE
- Member, ACM
- SIGGRAPH Asia 2015 Technical Briefs and Poster Program Assistant
- Technical Program Committee Member of IEEE BigMM 2015-2016, ICVRV 2016, CCPR 2016, IGTA 2016
- Journal Reviewer of TPAMI, IJCV, TIP, TCYB, TNNLS, TCSVT, TMM, TVCJ, etc.
- Ph.D. Student (3): Changqun Xia (2013, Deputy-Advisor, Co-supervised with Prof. Xiaowu Chen), Kui Fu (2016), Junjie Wu (2017)
- Master Student (9): Lishi Zhang (2015), Pengcheng Yuan (2016), Ruizhi Zhang (2016), Jinming Su (2017), Chenghan Fu (2017), Kaiwen Yu (2017), Weihua Ye (2017), Hongze Shen (2017), Hao Xu (2017)
- Undergraduate Student (1): Daxin Gu (will be my Ph.D. Student at 2018)