글번호
6532114
일 자
17.04.20
조회수
243
글쓴이
학과사무실
제목 : 4월21일(금) 한국컴퓨터비전연구회 신진연구자 발표회
*관심있으신 분들의 많은 참석 바랍니다*


이번주 금요일에 한국컴퓨터비전연구회(Korean Computer Vision Society) 신진연구자 발표회가 포스텍에서 열립니다. 한국컴퓨터비전연구회가 상하반기 각각 한번씩 개최하는 이 발표회는 최근 대학또는 연구소에 새로 부임하신 연구자분들을 소개하고 연구에 관해 듣는 자리입니다. 올해는 DGIST 곽수하 교수, 연세대 함범섭 교수의 발표가 있을 예정이니 관심있는 분들의 많은 참석바랍니다. 더 자세한 사항은 아래 덧붙입니다.

일시: 4월 21일 금요일 16:30 (오후 4시 30분)
장소: POSTECH 박태준학술정보관 502호

16:30 - 17:15   연구발표 DGIST 곽수하 교수: Towards learning with minimum supervision for semantic segmentation
17:15 - 18:00   연구발표 연세대 함범섭 교수: 시멘틱 영상 정합


* 발표자: 곽수하 교수 (16:30 - 17:15)

제목: Towards learning with minimum supervision for semantic segmentation

초록: Semantic segmentation is a visual recognition task aiming to estimate pixel-level class labels in images. This problem has been recently handled by Deep Convolutional Neural Networks (DCNNs), and the state of the art based on DCNN achieve impressive records on public benchmarks. However, learning DCNN demands a large number of annotated training data while segmentation annotations in existing datasets are significantly limited in terms of both quantity and diversity due to the heavy annotation cost. Weakly supervised approaches tackle this issue by leveraging weak annotations such as bounding boxes and scribbles, which are either readily available in existing large-scale datasets or easily obtained thanks to their low annotation costs. In this talk, I will introduce our recent approaches to weakly supervised semantic segmentation based on image-level class label, which is the form of minimum supervision indicating only presence or absence of a semantic entity in an image. Learning semantic segmentation with image-level class label is a significantly ill-posed problem since neither object location nor shape is informed by the label. We tackled this challenging problem by employing (1) unsupervised techniques revealing low-level image structures, (2) web-crawled videos as additional data sources, and (3) DCNN architectures appropriate for learning segmentation with incomplete pixel-level annotations. I will conclude this talk with a few suggestions for future research directions worth to investigate for further improvement.

소개: Suha Kwak is an assistant professor in the Department of Information and Communication Engineering at Daegu Gyeongbuk Institute of Science and Technology (DGIST), Korea. He received his B.S. and Ph.D. degrees in computer science and engineering from Pohang University of Science and Technology (POSTECH), Korea, in 2007 and 2014, respectively. Before joining DGIST, he was a postdoctoral researcher at Inria / Ecole Normale Superieure in Paris, France, and a member of WILLOW project team. He has been working on various topics in the areas of computer vision and machine learning. He is primarily interested in problems related to video understanding such as object detection, tracking, and human behavior analysis. He is also interested in deep learning, structured prediction, and weakly supervised learning.

* 발표자: 함범섭 교수 (17:15 - 18:00)

제목: 시멘틱 영상 정합 

초록기존 영상 정합 기술은 스테레오 정합 (stereo matching), 움직임 추청 (optical flow) 같이 동일한 장면  물체를 촬영한 영상에 국한되어 있었다시멘틱 정합 (semantic matching) 같은 카테고리에 속해 있지만 서로 다른 형태를 띄고 있는 물체 영상에 대한 정합을지칭하며이를 이용하면 영상 간의 의미론적 연관성을 모델링   있다시멘틱 정합은 물체인식 (object recognition), 시멘틱세그멘테이션 (semantic segmentation), 영상 에디팅 (editing)  합성 (synthesis)  많은 컴퓨터 비전 분야에 사용되는 핵심 기술이다세미나에서는 시멘틱 정합 기술 관련 최근 연구결과를 소개한다. 이와 더불어 영상 필터링비지도 학습에 대한 최근 연구결과를 소개한다.

소개: 함범섭 교수는 2016 8월부터 현재 연세대학교 전기전자공학부 조교수로 재직 중이다부임전에는  대학에 학사박사 학위를 받은 프랑스 INIRA Paris 연구소에서 박사  연구원으로 재직하였다관심 연구 분야는 컴퓨터 비전영상처리기계학습 야이며특히정합과 평활화에 관한 이론  적용 분야 연구를 주로 수행하였다

첨부파일 첨부파일:
첨부파일이 없습니다.
목록으로
다음글 2017 삼성 투모로우 솔루션 홍보 (~5/25)
이전글 [삼성전자 DS부문]포항공과대학교 SW알고리즘 대회