2026-09-22T07:02:20Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/32060 2023-07-10 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Made available in DSpace on 2012-06-27T21:31:00Z (GMT). No. of bitstreams: 2 Sadeghi_Mohammad_Amin.pdf: 12334753 bytes, checksum: 738a2c76fd1c4928e84a9747bcd9b451 (MD5) license.txt: 4066 bytes, checksum: e11c5bd6828b3d05964feec70e3062c8 (MD5) Item marked as restricted to the 'Administrator' Group (id=1) by William Ingram (wingram2@illinois.edu) on 2012-06-27T21:32:46Z Item is restricted until 2014-06-27T21:32:23Z Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2014-06-28T10:00:28Z Item was in collections: Graduate Theses and Dissertations at Illinois (ID: 204) Dissertations and Theses - Computer Science (ID: 587) No. of bitstreams: 2 Sadeghi_Mohammad_Amin.pdf: 12334753 bytes, checksum: 738a2c76fd1c4928e84a9747bcd9b451 (MD5) license.txt: 4066 bytes, checksum: e11c5bd6828b3d05964feec70e3062c8 (MD5) Item released from any restrictions by Sarah Shreeves (sshreeve@illinois.edu) on 2014-06-28T10:00:28Z http://hdl.handle.net/2142/32060 en Copyright 2012 Mohammad Amin Sadeghi and Ali Farhadi under Creative Commons Visual Phrase Phrasal Recognition Visual Composites Object Recognition Recognition using visual phrases text Forsyth, David A. Sadeghi, Mohammad Amin 2012-06-27T21:31:00Z 2014-06-28T10:00:28Z 2012-05 2012-06-27T21:31:00Z 2012-05 In this thesis I introduce visual phrases, complex visual composites like ``a person riding a horse''. Visual phrases often display significantly reduced visual complexity compared to their component objects, because the appearance of those objects can change profoundly when they participate in relations. I introduce a dataset suitable for phrasal recognition that uses familiar PASCAL object categories, and demonstrate significant experimental gains resulting from exploiting visual phrases. I show that a visual phrase detector significantly outperforms a baseline which detects component objects and reasons about relations, even though visual phrase training sets tend to be smaller than those for objects. I argue that any multi-class detection system must decode detector outputs to produce final results; this is usually done with non-maximum suppression. I describe a novel decoding procedure that can account accurately for local context without solving difficult inference problems. I show this decoding procedure outperforms the state of the art. Finally, I show that decoding a combination of phrasal and object detectors produces real improvements in detector results. Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2012-04-25T20:23:32Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Sadeghi_Mohammad_Amin.pdf: 12334753 bytes, checksum: 738a2c76fd1c4928e84a9747bcd9b451 (MD5) Computer Science 1434 Computer Science 0112 University of Illinois at Urbana-Champaign Thesis M.S. PHD:Computer Science -UIUC 10KS0112PHD