301 |
3D model reconstruction from silhouettesLiang, Chen, 梁晨 January 2008 (has links)
published_or_final_version / Computer Science / Doctoral / Doctor of Philosophy
|
302 |
Camera network calibrationZhang, Guoqiang, 張國強 January 2006 (has links)
published_or_final_version / abstract / Computer Science / Master / Master of Philosophy
|
303 |
A split-and-merge approach for quadrilateral-based image segmentationChen, Zhuo, 陳卓 January 2006 (has links)
published_or_final_version / abstract / Computer Science / Master / Master of Philosophy
|
304 |
3D reconstruction of lines, ellipses and curves from multiple imagesMai, Fei, 買斐 January 2008 (has links)
published_or_final_version / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy
|
305 |
An object-based approach to image-based renderingGan, Zhifeng., 甘智峰. January 2006 (has links)
published_or_final_version / abstract / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy
|
306 |
Temporal subtraction of chest radiograph using graph cuts and free-form deformationsZhang, Hui, 張暉 January 2007 (has links)
published_or_final_version / Computer Science / Master / Master of Philosophy
|
307 |
Mesh denoising and feature extraction from point cloud dataLee, Kai-wah, 李啟華 January 2009 (has links)
published_or_final_version / Computer Science / Doctoral / Doctor of Philosophy
|
308 |
Position and pose estimation for visual control of robot manipulators in planar tasksYung, Ho-lam., 容浩霖. January 2009 (has links)
published_or_final_version / Electrical and Electronic Engineering / Master / Master of Philosophy
|
309 |
A region merging methodology for color and texture image segmentationTan, Zhigang, 譚志剛 January 2009 (has links)
published_or_final_version / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy
|
310 |
Active learning of an action detector on untrimmed videosBandla, Sunil 22 July 2014 (has links)
Collecting and annotating videos of realistic human actions is tedious, yet critical for training action recognition systems. We propose a method to actively request the most useful video annotations among a large set of unlabeled videos. Predicting the utility of annotating unlabeled video is not trivial, since any given clip may contain multiple actions of interest, and it need not be trimmed to temporal regions of interest. To deal with this problem, we propose a detection-based active learner to train action category models. We develop a voting-based framework to localize likely intervals of interest in an unlabeled clip, and use them to estimate the total reduction in uncertainty that annotating that clip would yield. On three datasets, we show our approach can learn accurate action detectors more efficiently than alternative active learning strategies that fail to accommodate the "untrimmed" nature of real video data. / text
|
Page generated in 0.096 seconds