个人简介

Education Ph. D. in College of Computing, Georgia Institute of Technology, 2009; Advisor Prof. Jim Rehg. B.S. & M.S., 1999 & 2002, in Nanjing University, China Career 2013.7 -- present Professor, Department of Computer Science and Technology & School of Artificial Intelligence, Nanjing University, China 2009.8 -- 2013.7 Assistant professor, School of Computer Engineering, Nanyang Technological University, Singapore Services Associate Editor IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), 2020.09--Pattern Recognition, 2017.1-- Tutorial chair Area chair/senior AC SPC/AC CVPR 2023 ICCV 2015, CVPR 2017, AAAI 2019, CVPR 2020, ECCV 2020, CVPR 2021, IJCAI 2021 AAAI 2016 (this year does not have the area chair rank), 2017, 2018, 2020, IJCAI 2013, 2018, 2019 Area chair Publication chair Finance chair ACCV 2012, PSIVT 2010, 2011, 2013, ICPR 2020 ACCV 2014, PCM 2012 ACML 2012 Publications Most of my papers are available for download in this Publications page, and here is my Google Scholar Citations profile. A list of the LAMDA group publications also include my papers. Teaching The 2022 version of the Pattern Recognition course is here Research I am mainly interested in computer vision (CV) and machine learning (ML), especially when the computing resources (CPU, GPU, running time, memory, model size, etc.) or data resources (size and distribution of training set, quality of labels and annotations, etc.) are limited. Deep learning (DL) with resource constraints are my current focus. .CV & ML with limited computing resources Deep network compression, acceleration, and generation Feature mimicking: a new knowledge distillation paradigm: Paper [J46]New! CURL: Network compression with only small dataset and/or residual connections: Paper [C51] AutoPruner: Variable ratio channel pruning: Paper [J42] Channel pruning based on activation approximation: Papers [C41], [J37] A simple acceleration trick for detection using deep networks: Paper [C42] Deep learning beyond CNN/RNN/Attention NRS: Nerual random subspace: Paper [J45] .CV & ML with limited data resources Weakly supervised localization & detection Weakly supervised object localization (WSOL): Paper [C52] (proposing a paradigm shift for WSOL) Object co-localization using deep models: Papers [C39], [J38] Learning with zero, partial, incomplete, noisy, and weak labels Tobias: A random network (without any training) can localize objects! Papers [C58]New! Theoretical results and practical algorithm for semi-supervised deep learning: Paper [C50] End-to-end deep learning in the presence of noisy labels: Paper [C48] Using weak labels for recognition: Papers [C38], [J32], [C46], CSRA [C57] (simple but powerful multi-label recognition) Fine-grained classification and retrieval without using bounding box annotations: Papers [J22], [J31], New datasets [C55]New! Dealing with imbalanced & long-tailed data distribution Long-tailed recognition: AAAI'21 paper (bag of tricks for long-tailed recognition), ICCV'21 paper (DiVE: balanced virtual example distribution) Learning with imbalanced datasets: Papers [C5], [C12], [J6] Imbalance in face detection: Papers [C4], [J4], [J5] Multi-instance learning Scalable MIL: Papers [C33], [J21] MIL with multi-view: Paper [C34] Earlier work & other work .CV & ML with limited computing resources Kernel approximation (in SVM and beyond): Papers [C10], [C17], [J10], [J19], [C25] Cascade structured classifier and detector: Papers [C3], [C4], [J4], [J5] Creating visual codebooks using additive kernels: Papers [C8], [J8], [J17] High-dimensional visual features and their compact representations: Papers [C28], [C37], [J24] Real time object detection based on HIK: Papers [C10], [C13], [J12] Detection and recognition using sensors beyond camera (RFID, mobile sensor, etc.), and beyond the computer (robot, mobile phone etc.): Papers [C6], [C11],[C15] Visual representation based on the Census Transform: Papers [C7], [C8], [J7], [J14] .Actions: Papers [J11], [J13], [C30], [C32] (physics based modeling), [J20] (good practices), [J27] (from single image) .Visual Place Categorization, mapping, and navigation: Papers [C9], [C29], my Ph.D. dissertation, [J16] .Find the appropriate level of sparsity: [C14] .Ensemble learning: [C1], [C2], [J2] (many could be better than all) .(Very) early work on faces: Papers [J1], [J3], [J18] Pages last modified since: Thur., Feb. 10, 2022.