The 11th International Conference on Image and Graphics (ICIG) will be held in Haikou, China, on 26 – 28, November, 2021. We sincerely invite the researches over the world in this area to join us.
ICIG 2021 Symposium:
Image Representation and Understanding
Image-related researches have attracted significant attentions in the past decades. There have been great efforts to process and analyze the massive image data including both images and videos. Undoubtably, the processing of images, from bottom-level representation to high-level understanding, will still be a popular topic in the foreseeable future. This workshop invites four speakers to share their recent contributions and novel ideas in image representation and understanding.
Tiesong Zhao (Fuzhou University)
Xu Wang
(Shenzhen University)
![]()
Hanli Wang
Tit
le: Bridging Vision and Language: Recent Advances in Visual Translation
Abstract: Translating an image or a video automatically into natural language is interesting,promising, but challenging. The task is to summarize the visual content ofimage or video and re-express it with decent words, suitable grammars, sentencepatterns and human habits. Nowadays, the encoding-decoding pipeline is the mostcommonly used framework to achieve this goal. In particular, the convolutionalneural network is used as the encoder to extract semantics of images or videos,while the recurrent neural network is employed as the decoder to generate wordsequence. In this talk, the literature on image and video description isfirstly reviewed, then the preliminary research advances are introduced,including visual captioning, visual storytelling, visual dense captioning,visual sentiment captioning, and the more complex visual paragraph description.
Biography: Hanli Wang received the B.S. and M.S. degrees in Electrical Engineering from ZhejiangUniversity, Hangzhou, China, in 2001 and 2004, respectively, and the Ph.D.degree in Computer Science from City University of Hong Kong, Kowloon, HongKong, in 2007. From 2007 to 2008, he was a Research Fellow with the Departmentof Computer Science, City University of Hong Kong. From 2007 to 2008, he wasalso a Visiting Scholar with Stanford University, Palo Alto, CA. From 2008 to2009, he was a Research Engineer with Precoad, Inc., Menlo Park, CA. From 2009to 2010, he was an Alexander von Humboldt Research Fellow in University ofHagen, Hagen, Germany. Since 2010, he has been a full Professor with theDepartment of Computer Science and Technology, Tongji University, Shanghai,China. His research interests include multimedia signal processing, computervision, and machine learning. He has published more than 160 research papers inthese research fields. His personal website is at https://mic.tongji.edu.cn.
![]()
Long Xu
Titl
e: Mask-convolution for restoring over-exposure of solar image
Abstract: Over-exposuremay happen for imaging of solar observation in case extremely violet solarbursts occur, which means that signal intensity goes beyond the dynamic rangeof an imaging system, resulting in information loss. Although over-exposure canbe alleviated a little by reducing exposure time in case of flares, it cannotbe solved completely. Recently, thanks to deep learning, lots of traditionalimage processing / reconstruction problems got breakthroughs, including imageinpainting. Over-exposure recovery is like image inpainting. In this talk, wepresent a learning-based model, namely mask-pix2pix network forrecovering/completing over-exposure regions of solar images. The proposed modelis established over the pix2pix GAN, so it has the form of a GAN, where thegenerator and discriminator are a U-net and a PatchGAN, respectively. Beyondconventional pix2pix, it introduces a new convolution operator, namelymask-convolution, which is specially designed for inpainting tasks. To providea convolution operator which could both fulfill block-wise convolution andeliminate interference of invalid pixels in mased region, we designed a maskconvolution operator, which highlight the mask regions during repairing damagedimage. Experimental results validate the advantage of the proposed model in therecovery of exposure solar images.
Biography: Long Xu received his M.S. degree in applied mathematics from Xidian University,Xi'an, China, in 2002, and the Ph.D. degree from the Institute of ComputingTechnology, Chinese Academy of Sciences, Beijing, China. He was a Postdoc withthe Department of Computer Science, City University of Hong Kong, theDepartment of Electronic Engineering, Chinese University of Hong Kong, fromJuly Aug. 2009 to Dec. 2012. From Jan. 2013 to March 2014, he was a Postdocwith the School of Computer Engineering, Nanyang Technological University,Singapore. Currently, he is with the Key Laboratory of Solar Activity, NationalAstronomical Observatories, Chinese Academy of Sciences. His research interestsinclude image/video processing, wavelet, machine learning, and computer vision.He was selected into the 100-Talents Plan, Chinese Academy of Sciences, 2014.
![]()
You Yang
Tit
le: Recent researches in Interactive Video
Abstract: Video service accounts for more than 80% amount of data transmission over internet,and how can we bring more immersive experiences to audience becomes a challengetask to both academia and industries. People tend to be involved into thevideo, just like the visual experience in their daily life. In this case, moredimensions of interaction should be considered, including viewing angles,illumination conditions, focal length, etc. So far, only limited dimensions ofinteractions have been taken into application by industrials, and considerationby MPEG. In this talk, we present the recent research progress of theprocessing chain from data capture in source part to interaction in terminalpart. Subtopics include multiview video capture and calibration, illuminationcoding and capture, focal stack images and their coding schemes.
Biography: You Yang received the Ph.D. degree in computer science from the Institute ofComputing Technology, Chinese Academy of Sciences, Beijing, China, in 2009.Since 2013, he has been with the School of Electronic Information andCommunications, Huazhong University of Science and Technology, Wuhan, China,and also with the Division of Intelligent Media and Fiber Communications, WuhanNational Laboratory for Opto-Electronics, Wuhan, where he is currently aProfessor and the Head of Information Engineering Department. Before that, Hehas worked as a Postdoctoral Fellow with the Automation Department, TsinghuaUniversity, from 2009 to 2011, and a Senior Research Scientist with SumavisionResearch, from 2011 to 2013. He has authored or coauthored over 90peer-reviewed articles and authorized 26 patents. His research interestincludes three-dimensional (3D) vision system and its applications, includingmultiview imaging systems, 3D/VR/AR content processing and visualcommunications, human-machine interaction techniques, and interactive visualapplications. Dr. Yang is a Fellow of the Institute of Engineering andTechnology of United Kingdom. He has been awarded the High Commended in 2020E&T Innovation Award of Outstanding Innovation in Communication & IT.He has been a Committee/TPC Member or the Session Chair of over 30international conferences, including ICME, ICASSP, VCIP, ICIMCS, MMM, andothers, and a Reviewer of 33 prestigious international journals from IEEE, ACM,OSA, and other associations. He has served as the General Secretary of Imageand Video Communication Technical Committee in CSIG since 2020. He was invitedto be the Judge of IET Innovation Award, in 2019. He was a Guest Editor ofNeurocomputing, from 2014 to 2016. He has been an Associate Editor of Journal ofElectronic Imaging since 2021, IEEE Access since 2018, IET Image Processingsince 2018, and PLoS ONE since 2015.
![]()
Yun Zhang
Tit
le: Deep Learning based Video Coding: Challenges and Opportunities
Abstr
act: Due to the rapid growth of video applications and boosting demands for higherquality video services, such as UHD/HDR, 3D and VR, video data volume has beenincreasing explosively worldwide, which has been the most severe challenge formultimedia computing, transmission and storage. Video coding, such as HEVC andVVC, by compressing videos into a much smaller size for transmission or storageis one of the key solutions; however, its development has become saturated tosome extent while the compression ratio continuously grows in the last threedecades. Deep leaning algorithms provide new opportunities for furtherupgrading video coding algorithms. In this talk, our recent progress on deep learning-basedvideo coding will be introduced. Firstly, intra prediction in video coding isformulated as an inpainting task, and Generative Adversarial Network (GAN)based intra video coding is developed to achieve higher coding efficiency.Secondly, chroma prediction in video coding is formulated as image colorizationtask, and deep learning based chroma predictive coding is proposed.Experimental results on HEVC and VVC are given to validate the effectiveness ofthe proposed deep learning-based coding optimizations. Finally, challengingissues and opportunities will be identified.
Biography: Yun Zhang received the Ph.D. degree in Computer Science from Institute of ComputingTechnology (ICT), Chinese Academy of Sciences (CAS), Beijing, China, in 2010.From 2010 to 2017, he was an Assistant Professor and an Associate Professor inShenzhen Institute of Advanced Technology (SIAT), CAS, Shenzhen, China, wherehe is currently a professor. His research interests are in the field ofmultimedia communications and visual signal processing, including videocompression, computational visual perception, VR/AR, and machine learning.Prof. Zhang has published 1 book and over 100 high quality scientific researchpapers, more than 40 of them are published on Top IEEE/ACM Transactions, suchas IEEE Trans. Image Process., IEEE Trans. Broadcast., IEEE Trans. CircuitsSyst. Video Technol., IEEE Trans. Indust. Electronics, IEEE Trans. Indust.Informatics. In addition, he has filed over 40 CN/US/PCT patents on visualsignal processing and more than 20 of them are granted. He is a Senior Memberof IEEE, and serves as Associate Editor of IEEE Access, Electronic Letters,Topic Editor of Sensors and Guest Editor on Special issue “Advances inDeep-Learning-Based Sensing, Imaging, and Video Processing” in Sensors.
http://icig2021.csig.org.cn/
To visit the conference website, please scan the following QR code:
![]()
http://conf.csig.org.cn/fair/394
To register on the microsite, please scan the following QR code:
![]()
![]()
微信扫码咨询专知VIP会员