|
|
本帖最后由 wangjian4500 于 2014-9-17 11:41 編輯
時間：2014年9月20日，下午13:30-17:30
地點：清華大學FIT樓二樓多功能廳
Bridging CNN and Unmatched Visual Tasks
顏水城
新加坡國立大學副教授、博導
Abstract: In this talk, we shall introduce two recent works toapply deep learning for those tasks on which deep learning is not so natural.
1. In this work, we propose a flexible deepCNN infrastructure, called Hypotheses-CNN-Pooling (HCP), where an arbitrarynumber of object segment hypotheses are taken as the inputs, then a shared CNNis connected with each hypothesis, and finally the CNN output results fromdifferent hypotheses are aggregated with max pooling to produce the ultimatemulti-label predictions. Experimental results on Pascal VOC2007 and VOC2012multi-label image datasets well demonstrate the superiority of the proposed HCPinfrastructure over other state-of-the-arts. In particular, the mAP reaches84.2% by HCP only and 90.3% after the fusion with our complementary result in[47] based on hand-crafted features on the VOC2012 dataset, which significantlyoutperforms the state-of-the-arts with a large margin of more than 7%.
2. In this work, the human parsing task, namelydecomposing a human image into semantic fashion/body regions, is formulated asan Active Template Regression (ATR) problem, where the normalized mask of eachitem is expressed as the linear combination of the learned mask templates, andthen morphed to a more precise mask with the active shape parameters, includingposition, scale and visibility of each semantic region. More specifically, thestructure outputs are predicted by two separate networks. For a new image, thestructure outputs of the two networks are fused to generate the probability ofeach semantic label for each pixel, and super-pixel smoothing is finally used to fine-tune thehuman parsing result. Comprehensiveevaluations on a new large dataset well demonstrate the significant superiorityof the ATR framework over other state-of-the-arts for human parsing.
Bio: Dr. YanShuicheng is currently an Associate Professor at the Department of Electricaland Computer Engineering at National University of Singapore, and the foundinglead of the Learning and Vision Research Group (http ://w ww.lv-nus.org). Dr.Yan's research areas include machine learning, computer vision and multimedia,and he has authored/co-authored hundreds of technical papers over a wide rangeof research topics, with Google Scholar citation >13,000 times and H-index50. He has been serving as an associate editor of IEEE TKDE, TCSVT and ACMTransactions on Intelligent Systems and Technology (ACM TIST). He received theBest Paper Awards from ACM MM'13 (Best Paper and Best Student Paper), ACM MM’12(Best Demo), PCM'11, ACM MM’10, ICME’10 and ICIMCS'09, the runner-up prize ofILSVRC'13, the winner prize of ILSVRC’14 detection task, the winner prizes ofthe classification task in PASCAL VOC 2010-2012, the winner prize of thesegmentation task in PASCAL VOC 2012, the honorable mention prize of thedetection task in PASCAL VOC'10, 2010 TCSVT Best Associate Editor (BAE) Award,2010 Young Faculty Research Award, 2011 Singapore Young Scientist Award, and2012 NUS Young Researcher Award.
Learning with Parallel Vector Field
何曉飛
浙江大學教授、博導、國家杰青
Abstract: In this talk, I will introduce our recentwork on manifold learning from the perspective of vector field. Unlike graphbased techniques which try to preserve the distance, our approach tries to finda constant vector field on the manifold and then reconstruct the embeddingfunction via the obtained vector field. When we restrict the vector field tothe gradient field, our approach is equivalent to finding killing vector fieldon manifold. Our analysis of killing field on Euclidean space shows, when themanifold is locally isometric to a connected subset of Euclidean space, we canalways recover the manifold isometrically. I will also present someexperimental results on both synthetic and real data sets.
Bio:何曉飛，博士，浙江大學教授、博導，國家杰出青年基金獲得者，IEEE高級會員。2000年畢業(yè)于浙江大學，獲計算機學士學位；2005年畢業(yè)于美國芝加哥大學，獲計算機博士學位；之后加入美國雅虎公司，任職研究科學家；2007年作為人才引進加入浙江大學，任職教授；曾獲1999年國際大學生數(shù)學建模競賽特等獎。近年來主要從事人工智能、互聯(lián)網(wǎng)數(shù)據(jù)挖掘及計算機視覺等方面的研究。論文共被他人引用8000余次，其中兩篇代表性論文分別被他人引用上千次。現(xiàn)/曾任7個國際SCI學術(shù)刊物的編委，包括IEEE TKDE、IEEE TCYB、CVIU等。曾近30次擔任國際會議的大會主席、副主席及程序委員會委員。獲得2012年人工智能頂級國際會議AAAI的最佳論文獎，以及2010年多媒體領(lǐng)域國際頂級會議ACM Multimedia的最佳論文提名獎。
Regressionbased Robust Classification
楊健
南京理工大學教授、博導、國家杰青
Bio：楊健，2002年7月博士畢業(yè)于南京理工大學計算機學院模式識別專業(yè)。自2003年起，先后在西班牙薩拉戈薩大學、香港理工大學、美國新澤西理工學院、加州理工學院從事博士后或訪問研究。2007年9月起任南京理工大學計算機學院教授，2014年3月起任南京理工大學計算機科學與工程學院副院長。
長期從事模式識別理論與應(yīng)用方面的研究，先后主持了國家自然科學基金面上項目，國家杰出青年科學基金項目，教育部科學技術(shù)研究重大項目，國家973課題等項目。在模式識別和機器智能領(lǐng)域的頂級國際期刊 IEEE Trans. on PAMI上發(fā)表論文3篇，在其他IEEE Transactions及Pattern Recognition等國際SCI源期刊上發(fā)表論文70余篇。SCI被引用3000余次，Google Scholar被引用6000余次�，F(xiàn)擔任國際SCI源學術(shù)期刊的IEEE Trans. on Neural Networks andLearning Systems和Pattern Recognition Letters的編委。
曾獲國家自然科學二等獎（第二完成人）；江蘇省科技進步一等獎（第二完成人）；教育部科技進步獎(推廣類) 二等獎（第二完成人）；第十一屆中國青年科技獎；第二屆“SCOPUS尋找青年科學之星”成長獎；國務(wù)院政府特殊津貼；入選國家百千萬人才工程，被授予“有突出貢獻中青年專家”稱號。
AnIntroduction of Micro-expression Recognition
王甦菁
中國科學院心理研究所 博士后
Abstract: 在這個報告中，我將給大家簡單介紹一下微表情識別的一些進展。微表情指人們在試圖隱藏自己的情緒時所泄露快速表情。這樣微表情就可以一條很重要的測謊線索用于測謊，并有可能被廣泛地應(yīng)用于安全、司法臨床等領(lǐng)域。在本報告中，列舉了當前微表情識別幾個公開的數(shù)據(jù)庫，并介紹了幾種微表情識別的新的算法，最后了微表情識別中所面臨的問題。
Bio：王甦菁，2012年7月博士畢業(yè)于吉林大學計算機科學與技術(shù)學院，同年8月進入中國科學院心理研究所從事博士后研究，長期從事特征抽取在人臉識別上應(yīng)用基礎(chǔ)研究，在流形學習，張量分析，彩色空間理論等方面有著深入的研究，并與國內(nèi)外人臉識別專家有著長期密切合作。其成果發(fā)表在本領(lǐng)域國際權(quán)威期刊IEEE Transactions 系列期刊上發(fā)表多篇論文。擔任國際學術(shù)期刊Neurocomputing的編委。承擔1項國家自然科學基金面上項目“基于稀疏張量的微表情識別研究”項目，發(fā)表30余篇論文。 |
|
發(fā)表于 2014-9-18 18:26:07
收藏