2026-09-21T17:14:04Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/42242 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Moulin, Pierre Yu, Honghai 2013-02-03T19:29:00Z 2013-02-03T19:29:00Z 2012-12 2013-02-03T19:29:00Z 2012-12 This thesis presents three contributions. First, we provide an information theoretic analysis to a recently developed learning-based content identification (ID) algorithm, symmetric pairwise boosting (SPB). Second, we propose a regularized Adaboost algorithm, which tackles SPB’s implicit assumption that video segments are statistically independent. Finally, we develop the first hybrid content ID system for synchronized RGB and depth (RGBD) videos. Experimental results show the regularized Adaboost algorithm vastly outperforms SPB for all considered distortions, while the hybrid system further improves the content ID performance of regularized Adaboost relative to RGB-alone or depth-alone content ID systems. Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2012-12-05T16:43:41Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 YU_HONGHAI.pdf: 3725430 bytes, checksum: 5e0c46630ce7c4adeeb63b5354732782 (MD5) Made available in DSpace on 2013-02-03T19:29:00Z (GMT). No. of bitstreams: 2 Honghai_Yu.pdf: 3725430 bytes, checksum: 5e0c46630ce7c4adeeb63b5354732782 (MD5) license.txt: 4056 bytes, checksum: 5af3f5ebd18e83be652f22fbdcf24e46 (MD5) http://hdl.handle.net/2142/42242 en Copyright 2012 Honghai Yu Content identification fingerprinting learning theory mutual information Kinect camera depth video Regularized Adaboost for RGBD video content identification text Electrical & Computer Eng 1933 Electrical & Computer Engr 1200 University of Illinois at Urbana-Champaign Thesis M.S. MS:Electr & Computer Eng-UIUC 10KS1200MS