Page 57 - profile2014.indd
P. 57
Video Inpainting ed several important advancements. First, since human motion
is articulated by nature, we proposed to solve this problem by
My group started this topic in 2009 when engaged in the Tai- manifold learning-based posture sequence estimation. In this
wan e-Learning and Digital Archives Project (2008-12). In recent way, we are able to deal with any changes caused by rotation,
years, transforming cultural and historical artifacts, such as pho-
tographs and vintage lms/videos, into digital format has be- translation, and scaling in the spatial domain. We transferred our
come an important trend. However, because of their age, the vis- video inpainting techniques to The National Bureau of Archives
ual quality of such images and videos after digitization is usually in December 2011. During 2011-2013, we further developed
techniques to deal with motion extrapolation issues. These tech-
very poor, and often contains unstable luminance and damaged niques were published in IEEE Transactions on Image Processing
content. Video inpainting, a considerably challenging technique,
helps users remove undesirable objects, and repair areas where (2011), Multimedia (2014), and PAMI (2014).
content is missing or damaged. In this eld, we have contribut-
Publications
1. Y. L. Chen, C. T. Hsu, and H. Y. Mark Liao, “Simultaneous 7. Hsueh-Yi Sean Lin, Hong-Yuan Mark Liao, and Ja-Chen Lin,
Tensor Decomposition and Completion Using Factor Priors,” “Visual Salience-Guided Mesh Decomposition,” IEEE Trans-
IEEE Transactions on Pattern Analysis and Machine Intelli- actions on Multimedia, volume 9, number 1, pages P46~P57,
gence, volume 36, number 3, pages 577-591, March 2014. January 2007.
2. Nick C. Tang, C. T. Hsu, M. F. Weng, T. Y. Lin, and H. Y. Mark 8. Y.H. Ho,C.W.Lin, J.F. Chen and H.Y. Mark Liao, “Fast Coarse-
Liao, “Example-based Human Motion Extrapolation and Mo- to-Fine Video Retrieval Using shot-level Spatio-temporal Sta-
tion Repairing Using Contour Manifold,” IEEE Transactions tistics,” IEEE Transactions on Circuits and Systems for Video
on Multimedia, volume 16, number 1, pages 47-59, January Technology, volume 16, number 5, pages 642-648, May 2006.
2014.
9. C.-W Su, H.-Y. Mark Liao, H.-R. Tyan, K.-C. Fan, and L.-H
3. Yan-Ying Chen, Winston Hsu, and H. Y. Mark Liao, “Auto- Chen, “A Motion-Tolerant Dissolve Detection Algorithm,”
matic Training Image Acquisition and Effective Feature Selec- IEEE Transactions on Multimedia, volume 7, number 6, pages
tion from Community-Contributed Photos for Facial Attribute 1106-1113, December 2005.
Detection,” IEEE Transactions on Multimedia, volume 15,
number 6, pages 1388-1399, October 2013. 10. C. -C Shih, H.-Y. Mark Liao, and C.-S Lu, “A New Iterated
Two-band Diffusion Equation :Theory and Its Application,”
4. C. H. Ling, Y. M. Liang, C. W. Lin, Y. S. Chen, and H. Y. IEEE Trans. on Image Processing, volume 12, number 4, pag-
Mark Liao, “Human Object Inpainting Using Manifold Learn- es 466-476, January 2003.
ingbased Posture Sequence Estimation,” IEEE Trans. on Im-
11. C.-S Lu, and H.-Y. Mark Liao, “Multipurpose Watermarking
age Processing, volume 20, number 11, pages 3124-3135,
for Image Authentication and Protection,” IEEE Trans. on
November 2011.
Image Processing, volume 10, number 10, pages 1579-1592,
5. Yu-Ming Liang, Sheng-Wen Shih, Arthur C.-C. Shih, H.-Y. October 2001.
Mark Liao, and Chen-Chung Lin, “Learning Atomic Human
Actions Using Variable-Length Markov Models,” IEEE Trans- 12. C.-S. Lu, , S.-K. Huang, C.-J. Sze, H.-Y. Mark Liao, “Cock-
actions on Systems, Man, and Cybernetics, Part B: Cybernet- tail watermarking for digital image protection,” IEEE Trans-
ics, volume 39, number 1, pages 268-280, February 2009. actions on Multimedia, volume 2, number 4, pages 209-224,
December 2000.
6. C.-W. Su, H.-Y. Mark Liao, H.-R. Tyan, C.-W. Lin, D.-Y.
Chen, and K.-C. Fan, “Motion Flow-based Video Retrieval,”
IEEE Transactions on Multimedia, volume 9, number 6, pages
1193-1201, October 2007.
57