• IVA 主页 /
• 所有成员

所有成员 - 研究人员

Jinqiao Wang, 王金桥 - 副研究员

Research Interests

• Multimedia analysis and processing
• Information Retrival
• Content based image retrieval
• Object detection and categorization
• Multimodel processing for multimedia

Research Experiences

• (2008.7 - Now) Assistant Professor in Institute of Automation, Chinese Academy of Sciences Multimedia Analysis, Object Detection and Tracking, Wireless Multimedia Retrieval, ....
• (2004.9 – 2008.6) Research Assistant in Chinese Academy of Sciences Structure analysis and semantic retrieval of broadcast video streams. I proposed a multi-model framework to structure broadcast video by fusing FMPI shot detection, audio scene change and text content change. Also a multi-model algorithm to classify commercial videos by video bag of words and text category.
• (2006.4 - 2006.10) Research Center of Intel, Beijing A research project of commercial video detection and segmentation in broadcast video streams with audio, visual and textual feature.
• (2005.6 - 2005.12) Institute of Infocomm Research, Singapore A research project of TRECVID 2005 for new video retrieval bench mark. We attend the task of low level feature extraction, camera motion estimation. We rank 2 in the final submission of all participants.
• (2004.4 - 2004.9) Chinese Offshore Oil Engineering Corporation Ltd (COOEC). Managed the commissioning in land and offshore commissioning of SPM system in BZ25-1 Oil Field Development Project Which was designed in a whole by APL Company in Norway and was inspected by DNV Company in Norway. Commissioning the systems of Lighting System, Distribution Board and Motor, UPS, Pumps (Open&Close Drain System), Pedestal Crane, Utility Winch, HPU&Accumulator Rack for ESD Valves, Heat Tracing System, Integrated Control System&S/D Valves, Fire&Gas System, Navigation Aids, Communication System, PIG Receivers&Launchers, Fire Fighting System&Life Saving System, All the equipments are imported from about 138 country.

Selected Publications [Full Publication Lists]

Demos

1. FMPI feature extraction program. [Zip] Frame Marked with Production Information(FMPI), POIM(Program Oriented Information Frame) is an extension of FMPI in TV broadcast streams. usage:

FMPI.exe imagename imagetype

The input image format can be JPG(ImageType=1), BMP(ImageType=2), TIF(ImageType=3) and PGM(ImageType=4). The filename of output feature is imagename.fea. The current version only support color images. The totol dimension of feature is 141, including color, texture, and edge features. The code can only be used for purpose of research, however please acknowledge its use with a citation PCM06 or MM06. If you feel interest for the sourcecode, email me jqwang@nlpr.ia.ac.cn.

2. Context Saliency based Image Summarization (Submitted to ICME09P).[Experimental Results]

Abstract:

The problem of image summarization is to determine a smaller representation but faithfully represent the original visual image appearance. In this paper, we propose a context saliency based image summarization approach in a supervised manner. Since merely visual saliency as importance measure is not enough, we incorporate redundancy-based contrast analysis and geometric segmentation into context saliency through naive Bayesian inference. Then we introduce a grid-based piecewise linear image warping scaleplate to maintain the proportion of salient objects. We argue that the image summaries should be appraised with target device specification under perception constrains, and we adopt the sweet spot evaluation to generate a flexible model that automatically combines cropping and warping methods. Additionally, we explore potential extension on multiple applications such as video retargeting, digital matting, image browsing etc. Experimental results show comparable performance compared to the state-of-art on common data sets.