2026-09-18T19:38:27Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/89047 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Forsyth, David A Hoiem, Derek Ramanan, Deva Lazebnik, Svetlana Golparvar-fard, Mani Sadeghi, Mohammad Amin 2016-03-02T19:34:19Z 2016-03-02T19:34:19Z 2015-12-04 2015-12 The ultimate goal of computer vision is to understand images. We describe methods to understand images at two levels. One is at the level of description of images which we produce using sentences. These sentences talk about the things that are present in the image and about where they are and what they are doing. Then we ask in what ways should we describe images. We introduce visual phrases that are composite chunks of meaning. We show that object detectors could be better at detecting some visual phrases than detecting single objects. This process of image understanding needs to use a lot of detectors. Running conventional object detectors at the rate required for image understanding could be very slow. We study fast object detection from an engineering perspective. We argue that a desirable object detector must: (1) be able to work with legacy templates; (2) be random access; (3) be able to trade accuracy versus speed; (4) have any-time property. We describe a method to have all of these features together for a fast detector. We apply these techniques to deformable parts model object detectors and show two orders of magnitude speed-up while adding their desirable features. We finally investigate the consequences of this architecture with a view of improving convolutional neural networks. Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-03-02 without embargo terms The student, Mohammad Amin Sadeghi, accepted the attached license on 2015-12-03 at 19:25. The student, Mohammad Amin Sadeghi, submitted this Dissertation for approval on 2015-12-03 at 19:42. This Dissertation was approved for publication on 2015-12-04 at 15:49. DSpace SAF Submission Ingestion Package generated from Vireo submission #8930 on 2016-03-02 at 12:51:24 Made available in DSpace on 2016-03-02T19:34:19Z (GMT). No. of bitstreams: 2 SADEGHI-DISSERTATION-2015.pdf: 17726072 bytes, checksum: a9926b4b93154ebbd4c6cd886df92dbe (MD5) LICENSE.txt: 4218 bytes, checksum: a106486153c1ec5b3e0207c6ec0c9232 (MD5) Previous issue date: 2015-12-04 application/pdf http://hdl.handle.net/2142/89047 en Copyright 2015 Mohammad Amin Sadeghi Fast Object Detection Accurate Object Detection Visual Phrases Sentence Generation Vector Quantization. Fast object detection text text Computer Science Computer Science University of Illinois at Urbana-Champaign Dissertation Ph.D.