時間：2011年10月20日上午10:00（周四）
地點：學(xué)術(shù)會議中心二樓報告廳
報告人：田奇 教授
單 位：美國德州大學(xué)圣安東尼奧分校
題 目：Coding for Large-scale Partial-duplicate Image Search
摘 要：Bag-of-visual-words model is widely used in the state-of-the-art large-scale image retrieval system. It represents each image as a bag of visual words by quantizing local image descriptors to the closest visual words. However, feature quantization reduces the discriminative power of local features, which causes many false visual word matches. Recently, some geometric verification methods are proposed to check the geometric consistency of matched features in a post-processing step. Although retrieval precision is improved, either the computational cost is too expensive to ensure real-time response, or they are limited to local verification. To address this dilemma, we propose a novel scheme, Spatial Coding and its variant Neighborhood Coding, designed for large scale partial-duplicate image retrieval. The spatial relationships among visual words are encoded in global region maps. Based on the region maps, a spatial verification approach is developed, which can detect false matches of local features efficiently, and consequently improve retrieval performance greatly.
Experiments in partial-duplicate image retrieval, using a database of one million images from Image-Net, reveal that our approach can effectively detect duplicate images with rotation, scale changes, occlusion, and background clutter with very low computational cost. The spatial coding and neighborhood coding achieve an 53% and 29.6% improvement in mean average precision and 46% and 67.6% reduction in time cost over the baseline Bag-of-Visual-Words approach, respectively. They perform even better than full geometric verification while being much less computationally expensive. Our demo on 10-million dataset further reveals the scalability of our approach.
報告人簡介：田奇教授于1992年在清華大學(xué)電子工程系獲得學(xué)士學(xué)位，2002在美國伊利諾伊州厄巴納-香檳大學(xué)電子與計算機工程系獲得博士學(xué)位。田奇教授現(xiàn)擔任美國德州大學(xué)圣安東尼奧分校計算機科學(xué)系副教授、博士生導(dǎo)師。他還曾兼任微軟亞洲研究院媒體計算組主任研究員以及資訊顧問、美國伊利諾伊大學(xué)訪問學(xué)者、美國NEC研究院訪問教授、美國三菱劍橋研究院訪問研究員等職。田奇教授也是2010年國家自然科學(xué)基金委國際合作基金獲得者。
田奇教授在多媒體領(lǐng)域進行了多年的研究有豐富的研究經(jīng)驗和重要的研究成果。其提出的創(chuàng)新學(xué)術(shù)思想推動了多媒體研究的發(fā)展，并已經(jīng)被學(xué)術(shù)界大量引用。他在國際期刊/中文期刊和國際會議上已發(fā)表論文100余篇，其中40余篇發(fā)表在國際一流學(xué)術(shù)期刊如：IEEE TPAMI, IEEE TCSVT, IEEE Signal Processing Magazine, ACM Transactions on Knowledge Discovery from Data, IEEE Transactions on Computational Biology and Bioinformatics，IEEE Transactions on Multimedia, Pattern Recognition, IJCV等。90余篇發(fā)表在國際一流學(xué)術(shù)會議如ACM Multimedia，IEEE CVPR，ACM CIKM等。他的工作曾在2006年ICASSP會議上獲得最佳論文獎，在2007年 PCM會議中獲得最佳論文獎提名，其提出的判別式EM算法(DEM) 以及核判別EM算法(KDEM)已經(jīng)被引用200余（Google Citations）次。田奇教授在國際學(xué)術(shù)界具有重要的影響力。他在很多國際期刊中擔任重要職務(wù)，其中包括IEEE CSVT 副主編，IEEE TMM客座編輯， ACM TIST客座編輯和Elsevier CVIU雜志客座編輯等職務(wù)等。田奇教授還在很多頂級國際會議中擔任主席和會議組織者，其中包括ACM Multimedia 2009 2010，ICPR 2010， CIVR2010，ICME 2010 等。
TOP
