| University of Southern California | ||||||
| Ongoing | Prof. C. -C. Jay Kuo | Ying Li | ||||
| Joint work on multimedia content analysis and understanding | ||||||
| University of Washington | ||||||
| Ongoing | Prof. Ming-Ting Sun Xiaodan Song | Ching-Yung Lin | ||||
| As the amount of video data increases, organizing and retrieving video data based on their semantics is becoming more and more important. Traditionally, supervised learning is used to build models for detecting semantic concepts. However, in order to obtain a substantial amount of training data, extensive labeling work is needed with the supervised learning schemes. In this project, we propose a novel Autonomous Learning mechanism, in which imperfect labeling information extracted from cross-modality information is used for training. For instance, we can train visual models based on the automatic speech recognition results in videos. This shall, thus, not only reduce the number of examples needed for labeling, as active learning and transductive learning do, but also totally avoid the manual labeling process. First of all, imperfect labels without user involvement are obtained from cross-modality information. Then based on our proposed new schemes -- “Generalized Multiple-Instance Learning” and “Uncertain Labeling Density”-- the system conjectures relevance score of visual concepts. From these scores, Support Vector Regression is used to build generic visual models. Our proposed algorithm is tested on 150 hours of video databases. Preliminary experimental results show that this novel Autonomous Learning mechanism achieves promising performance comparing with supervised learning systems. · Project page | ||||||
| Haifa University | ||||||
| Ongoing | Sara Rosenblum | Dan Chevion | ||||
| Using data visualization and signal processing to characterize the handwriting process · Project page | ||||||
| Purdue University | ||||||
| Ongoing | Prof. Edward J. Delp | Arnon Amir | ||||
| Video analysis, indexing and retrieval, video summarization, video closed captions, video for remote education and distance learning | ||||||
| Technion, Israel Institute of Technology | ||||||
| Ongoing | Prof. Ehud Rivlin | Eugene Walach | ||||
| Medical Image Processing with particular focus on detection of nodules in CT lung scans. | ||||||