Search For:

Displaying 1-11 out of 11 total
Live Semantic Sport Highlight Detection Based on Analyzing Tweets of Twitter
Found in: 2012 IEEE International Conference on Multimedia and Expo (ICME)
By Liang-Chi Hsieh,Ching-Wei Lee,Tzu-Hsuan Chiu,Winston Hsu
Issue Date:July 2012
pp. 949-954
Microblogging as a new form of communication on Internet, has attracted the attention from researchers recently. Relying the real-time and conversational properties of microblogging, its users update their statuses and share experience within their the soc...
Coarse-to-fine temporal optimization for video retargeting based on seam carving
Found in: Multimedia and Expo, IEEE International Conference on
By Wei-Lun Chao, Hsiao-Hang Su, Shao-Yi Chien, Winston Hsu, Jian-Jiun Ding
Issue Date:July 2011
pp. 1-6
In this paper, a new video retargeting method based on temporal information and seam carving is presented. Two video energy functions, motion weight prediction and pixel-based optimization, are proposed to take the temporal information into account and mak...
3D Sub-query Expansion for Improving Sketch-Based Multi-view Image Retrieval
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Yen-Liang Lin,Cheng-Yu Huang,Hao-Jeng Wang,Winston Hsu
Issue Date:December 2013
pp. 3495-3502
We propose a 3D sub-query expansion approach for boosting sketch-based multi-view image retrieval. The core idea of our method is to automatically convert two (guided) 2D sketches into an approximated 3D sketch model, and then generate multi-view sketches ...
Large-Scale Concept Ontology for Multimedia
Found in: IEEE Multimedia
By Milind Naphade, John R. Smith, Jelena Tesic, Shih-Fu Chang, Winston Hsu, Lyndon Kennedy, Alexander Hauptmann, Jon Curtis
Issue Date:July 2006
pp. 86-91
As increasingly powerful techniques emerge for machine tagging multimedia content, it becomes ever more important to standardize the underlying vocabularies. Doing so provides interoperability and lets the multimedia community focus ongoing research on a w...
Full body human attribute detection in indoor surveillance environment using color-depth information
Found in: 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
By Hao-Jen Wang,Yen-Liang Lin,Cheng-Yu Huang,Yu-Lin Hou,Winston Hsu
Issue Date:August 2013
pp. 383-388
With the advent of depth enabled sensors and increasing needs in surveillance systems, we propose a novel framework to detect fine-grained human attributes (e.g., having backpack, talking on cell phone, wearing glasses) in the surveillance environments. Tr...
Flickr-tag prediction using multi-modal fusion and meta information
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Tzu-Hsuan Chiu, Chun-Yen Yeh, Felix Wu, Guan-Long Wu, Winston Hsu, Yu-Chuan Su
Issue Date:October 2013
pp. 353-356
We present our evaluation and analysis on Yahoo! Large-scale Flickr-tag Image Classification dataset. Our evaluations show that combining multi-features and different classification models, the MAP of tag prediction can be significantly improve over ordina...
Semi-supervised face image retrieval using sparse coding with identity constraint
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Bor-Chun Chen, Kuan-Yu Chu, Winston Hsu, Yan-Ying Chen, Yin-Hsi Kuo
Issue Date:November 2011
pp. 1369-1372
We aim to develop a scalable face image retrieval system which can integrate with partial identity information to improve the retrieval result. To achieve this goal, we first apply sparse coding on local features extracted from face images combining with i...
Region-based landmark discovery by crowdsourcing geo-referenced photos
Found in: Proceedings of the 34th international ACM SIGIR conference on Research and development in Information (SIGIR '11)
By An-Jung Cheng, Kuo-Wei Chang, Liang-Chi Hsieh, Winston Hsu, Yen-Ta Huang
Issue Date:July 2011
pp. 1141-1142
We propose a novel model for landmark discovery that locates region-based landmarks on map in contrast to the traditional point-based landmarks. The proposed method preserves more information and automatically identifies candidate regions on map by crowdso...
Multi-layer graph-based semi-supervised learning for large-scale image datasets using mapreduce
Found in: Proceedings of the 34th international ACM SIGIR conference on Research and development in Information (SIGIR '11)
By Guan-Long Wu, Liang-Chi Hsieh, Wen-Yu Lee, Winston Hsu, Ya-Fan Su
Issue Date:July 2011
pp. 1121-1122
Semi-supervised learning is to exploit the vast amount of unlabeled data in the world. This paper proposes a scalable graph-based technique leveraging the distributed computing power of the MapReduce programming model. For a higher quality of learning, the...
Recent developments in content-based and concept-based image/video retrieval
Found in: Proceeding of the 16th ACM international conference on Multimedia (MM '08)
By Rong Yan, Winston Hsu
Issue Date:October 2008
pp. 40-42
Devising effective Content Protection mechanisms and building satisfactory Digital Rights Management systems have been top priorities for the Publishing and Entertainment Industries in recent years. In this tutorial, we focus on protection tools and standa...
Story boundary detection in large broadcast news video archives: techniques, experience and trends
Found in: Proceedings of the 12th annual ACM international conference on Multimedia (MULTIMEDIA '04)
By Lekha Chaisorn, Shih-Fu Chang, Tat-Seng Chua, Winston Hsu
Issue Date:October 2004
pp. 656-659
The segmentation of news video into story units is an important step towards effective processing and management of large news video archives. In the story segmentation task in TRECVID 2003, a wide variety of techniques were employed by many research group...