好文作者面授招–20150506

【15-13期VALSE Webinar活动】

报告嘉宾1:王井东(微软亚洲研究院)
主持人:张兆翔(北京航天航空大学)
报告题目:Composite Quantization for Approximate Nearest Neighbor Search [Slides]
文章信息:Ting Zhang, Chao Du, Jingdong Wang, Composite Quantization for Approximate Nearest Neighbor Search, ICML2014.
报告时间:2015年5月6日晚20:00(北京时间)
报告摘要: In this talk, I will present our recent work on approximate nearest neighbor search: a compact coding approach, composite quantization . The idea is to use the composition of several elements selected from the dictionaries to accurately approximate a vector and to represent the vector by a short code composed of the indices of the selected elements. To efficiently compute the approximate distance of a query to a database vector using the short code, our approach introduces an extra constraint, constant inter-dictionary-element-product, resulting in that approximating the distance only using the distance of the query to each selected element is enough for nearest neighbor search.
报告人简介: Jingdong Wang is a Lead Researcher at the Visual Computing Group, Microsoft Research Asia. He received the M.Eng. and B.Eng. degrees in Automation from the Department of Automation, Tsinghua University, Beijing, China, in 2001 and 2004, respectively, and the PhD degree in Computer Science from the Department of Computer Science and Engineering, the Hong Kong University of Science and Technology, Hong Kong, in 2007. His areas of interest include computer vision, machine learning, pattern recognition, and multimedia computing. In particular, he has worked on kernel methods, semi-supervised learning, data clustering, image segmentation, and image and video presentation, management and search. At present, he is mainly working on the Big Media project, including large-scale indexing and clustering, Web image search and mining, and visual understanding such as salient object detection, image recognition, face alignment and recognition.

报告嘉宾2:贾奎(澳门大学)
主持人:董伟生(西安电子科技大学)
报告题目:Robust Object Matching using Low-rank constraint and its Applications [Slides]
报告时间:2015年5月6日晚21:00(北京时间)
文章信息:
[1] Kui Jia, Tsung-Han Chan, Zinan Zeng, Shenghua Gao, Gang Wang, Tianzhu Zhang, and Yi Ma, “ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images”, arXiv:1403.7877, 2014.
[2] Tianzhu Zhang*, Kui Jia*, Changsheng Xu, Yi Ma, and N. Ahuja, “Partial Occlusion Handling for Visual Tracking via Robust Part Matching”, IEEE Conference on Computer Vision and Pattern Recognition, 2014. (* indicates equal contributions)
[3] Zinan Zeng, Shijie Xiao, Kui Jia, Tsung-Han Chan, Shenghua Gao, Dong Xu, and Yi Ma, “Learning by Associating Ambiguously Labeled Images”, IEEE Conference on Computer Vision and Pattern Recognition, 2013.
[4] Zinan Zeng, Tsung-Han Chan, Kui Jia, and Dong Xu, “Finding Correspondence from Multiple Images via Sparse and Low-rank Decomposition”, European Conference on Computer Vision, 2012.
报告简介:Feature-based object matching is a fundamental problem in computer vision. In this talk, we present a new first-order object (inlier features) matching technique called ROML (Robust Object Matching using Low-rank constraint). Given a set of images with extracted inlier and outlier features, ROML aims to simultaneously identify the inlier features from each image, and establish their consistent correspondences across the image set. This is a challenging combinatorial problem. To achieve the goal, ROML leverages the underlying data low-rank property to simultaneously optimize a partial permutation matrix (PPM) for each image, and feature correspondences are established by the obtained PPMs. Extensive experiments on rigid/non-rigid object matching, matching instances of a common object category, and common object localization demonstrate ROML’s efficacy for feature-based object matching. A few more recent examples will also be presented in this talk to show how ROML can be used/adapted for a variety of computer vision applications.
报告人简介: Kui Jia received the B.Eng., M.Eng, and Ph.D. degrees respectively from Northwestern Polytechnic University, National University of Singapore, and Queen Mary, University of London. He is currently a Visiting Faculty with the Faculty of Science and Technology, University of Macau, Macau SAR, China. He is also holding a Research Scientist position at Advanced Digital Sciences Center, Singapore. His research interests are in computer vision, machine learning, and image processing.

(Visited 291 times, 1 visits today)