31 research outputs found
PCV22: COST-EFFECTIVENESS OF HMG-CoA REDUCTASE INHIBITORS AND FIBRATES THERAPY IN ELDERLY WOMEN WITH CORONARY ARTERY DISEASE
No full textPCV70 A PHARMACOECONOMIC COMPARISON OF UNFRACTIONATED HEPARIN AND LOW MOLECULAR WEIGHT HEPARIN USAGE IN ACUTE CORONARY SYNDROME IN RUSSIA
No full textAdopting the two-branch network to video-text tasks
No full textThis Thesis was approved for publication on 2018-04-23 at 16:33.DSpace SAF Submission Ingestion Package generated from Vireo submission #12431 on 2018-08-31 at 17:21:14Made available in DSpace on 2018-09-04T20:36:51Z (GMT). No. of bitstreams: 2
CHANG-THESIS-2018.pdf: 15447494 bytes, checksum: 19c9cab37c0e29586fc0af1a3fd27846 (MD5)
LICENSE.txt: 4214 bytes, checksum: 7282ca76dd914b160456ecc3dc7e4409 (MD5)
Previous issue date: 2018-04-23Modeling visual context and its corresponding text description with a joint embedding network has been an effective way to enable cross-modal retrieval. However, while abundant work has been done for image-text tasks, not much exists with regards to the video domain. We hope to adopt a nonlinear embedding model, the two-branch network, to the video-text tasks in order to show its robustness. Two kinds of tasks are explored, bidirectional video-sentence retrieval and video description generation. For the retrieval task, we use nearest neighbor search to get the corresponding video or text with respect to the query. For video captioning, we incorporate the two-branch network in a traditional LSTM model with an additional embedding loss term in order to demonstrate its ability of preserving a semantic structure between video and text.Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-05-01The student, Hsiao-Ching Chang, accepted the attached license on 2018-04-23 at 16:08.The student, Hsiao-Ching Chang, submitted this Thesis for approval on 2018-04-23 at 16:14.Embargo set by: Seth Robbins for item 107294
Lift date: 2020-09-04T20:37:00Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemEmbargo set by: Seth Robbins for item 107294
Lift date: 2020-09-04T20:42:08Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemU of I Only Restriction Lifted for Item 107294 on 2020-09-05T09:15:20Z
The need to strengthen measures for the diagnosis and treatment of Helicobacter pylori infection in Russia. Memorandum
No full textLeonid B. Lazebnik, PhD, Doctor of Medical Scienses, Professor, Department of Polyclinic Therapy; President of Gastroenterological Scientific Society of Russia; Vise President of Russian Scientific Medical Society of Therapists; Scopus Author ID: 7005446863, ORCID: 0000-0001-8736-5851 Dmitry S. Bordin, MD, PhD, Head of the Department of Pancreatic, Biliary and upper digestive tract disorders; professor of the department of general practice (family medicine); professor of the department of propaedeutics of internal diseases and gastroenterology; ORCID: 0000-0003-2815-3992 Nataliya N. Dekhnich, Doctor of Medical Sciences, Associate Professor at the Department of Faculty Therapy; ORCID: 0000-0002-6144-3919 Roman S. Kozlov, Professor, Corresponding member of the Russian Academy of Science, Director, Institution of Antimicrobial Chemotherapy; chief freelance specialist-therapist of the Ministry of Health of Russia for the Siberian Federal District, professor Mariya A. Livzan, D. Sci. (Med.), Professor, Rector, Head of the Department of Faculty Therapy, Occupational Diseases; ORCID: 0000-0002-6581-7017, Scopus Author ID: 24341682600 Elena A. Lyalyukova, PhD, MD, Professor of the Department of additional postgraduate education in internal and family medicine, Associate Professor; WoS Research ID: AAB -5416-2021, Scopus Author ID: 56657486600, ORCID: 0000-0003-4878-0838 Svetlana V. Luzina, Deputy Chief physician for Medical Part Galina V. Belova, MD, PhD, Professor, Deputy chief physician; Scopus Author ID: 57198379175 Rustem A. Abdulkhakov, Doctor of Medicine, Professor of the Department of Hospital Therapy, Kazan State Medical University, Ministry of Health of Russia, Professor; ORCID: 0000-0002-1509-6776, Scopus Author ID: 6506615710 Sayyar R. Abdulkhakov, Candidate of Medical Sciences, Associate Professor, Head of the Department of Fundamental Foundations of Clinical Medicine; Institute of Fundamental Medicine and Biology; Associate Professor, Department of General Medical Practice and Polyclinic Therapy; assistant professor
Current and future trends in object detection
No full textThe task of finding objects belonging to classes of interest in images has long been a focus of Computer Vision research. The ability to localize objects is useful in many applications: from self-driving cars, where it allows the car to detect pedestrians, bicyclists, road signs, and other vehicles, to security, where intruding persons can be detected. Though a lot of progress has been made since the conception of the field of Computer Vision more than five decades ago, as always, there is scope for further improvement. This is especially true in the case of object detection where a myriad of factors including variation in object instances through pose and appearance, along with other environmental factors such as the degree of occlusion, and lighting tend to cause failures.
In this work we focus on improving object detection through the use of more representative features and better models. We propose new features that are not only more powerful, but also more robust and capture more information than the currently popular features. Further, we propose scalable models which can leverage large amounts of training data to improve performance.Item withdrawn by Mark Zulauf ([email protected]) on 2014-07-14T15:22:14Z
Item was in collections:
University of Illinois Theses & Dissertations (ID: 1)
No. of bitstreams: 1
Mallya_Arun.pdf: 12895364 bytes, checksum: aeb50773df21ba9e5bedc343aa0568b3 (MD5)Made available in DSpace on 2014-09-16T17:12:20Z (GMT). No. of bitstreams: 2
Arun_Mallya.pdf: 12895364 bytes, checksum: aeb50773df21ba9e5bedc343aa0568b3 (MD5)
license.txt: 4061 bytes, checksum: 1fa7e8c5c6212b68bc954ab87bb5609f (MD5)Embargo set by: Seth Robbins for item 50491
Lift date: 2016-09-16T17:13:01Z
Reason: Author requested closed access (OA after 2yrs) in Vireo ETD systemLimited Restriction Lifted for Item 50491 on 2016-09-22T20:59:18Z
Multi-task semantic segmentation of damage and materials for visual inspection of civil infrastructure
No full textManual visual inspection is the most common means of assessing the condition of civil infrastructure in the United States but can be exceedingly laborious, time consuming, and dangerous. Research has focused on automating parts of the inspection process using unmanned aerial vehicles for image acquisition, followed by deep learning techniques for damage identification. Existing deep learning methods and datasets for inspections have typically been developed for a single damage type. However, most guidelines for inspections require the identification of multiple damage types and describe evaluating the significance of the damage based on the associated material type. Thus, the identification of material type is important in understanding the meaning of the identified damage. Training separate networks for the tasks of material and damage identification fails to incorporate this intrinsic interdependence between them. We hypothesize that a network that incorporates such interdependence directly will have a better accuracy in material and damage identification. To this end, a deep neural network, termed the Material-and-Damage-Network (MaDnet), is proposed to simultaneously identify material type (concrete, steel, asphalt), as well as fine (cracks, exposed rebar) and coarse (spalling, corrosion) structural damage. In this approach, semantic segmentation (i.e., assignment of each pixel in the image with a material and damage label) is employed, where the interdependence between material and damage is incorporated through shared filters learned through multi-objective optimization. A new dataset with pixel-level labels identifying the material and damage type is developed and made available to the research community. Finally, the dataset is used to evaluate MaDnet and demonstrate the improvement in pixel-accuracy over employing independent networks.Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2022-05-01The student, Vedhus Hoskere, accepted the attached license on 2020-05-12 at 13:50.The student, Vedhus Hoskere, submitted this Thesis for approval on 2020-05-12 at 13:55.This Thesis was approved for publication on 2020-05-12 at 21:30.DSpace SAF Submission Ingestion Package generated from Vireo submission #15358 on 2020-08-25 at 17:31:16Made available in DSpace on 2020-08-26T23:58:48Z (GMT). No. of bitstreams: 2
HOSKERE-THESIS-2020.pdf: 6289823 bytes, checksum: a9866b789687dab4d9a7bcb8644712a5 (MD5)
LICENSE.txt: 4211 bytes, checksum: ac460472f6b71bd73314677859915fb9 (MD5)
Previous issue date: 2020-05-12Embargo set by: Seth Robbins for item 115804
Lift date: 2022-08-26T23:58:55Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemAuthor requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemU of I Onl
PCV52 ECONOMIC ANALYSIS OF THE USE OF CLOPIDOGREL IN PATIENTS WITH ACUTE CORONARY SYNDROME WITHOUT STSEGMENT ELEVATION (ACS) FROM THE RUSSIAN HEALTH CARE SYSTEM PERSPECTIVE
No full textUnderstanding scene structure from images
No full text"The task of recovering 3D information from 2D images has long been a focus of Computer Vision research. Such information is useful in many applications: from robot navigation, where it allows the robot to understand the physical constraints of the environment it is in, to augmented reality, where 3D information is used to alter images and videos in physically plausible ways. While much progress has been made in this line of research there is still scope for further improvement. This is especially true in the case of pictures taken ""in the wild"", where variables such as the presence of clutter, people, irregularly shaped buildings, unusual camera angles, etc tend to cause current techniques to fail.
In this work we focus on recovering 3D information from images in the presence of clutter and other such variables. We work on both indoor and outdoor scenes, utilizing different approaches in each case in order to make the 3D information recovery more robust.
Since this work focuses on expanding existing techniques to work well on more challenging datasets, we had to create new datasets for both indoor and outdoor scenes that could test the robustness of our methods. Details of these datasets are also provided in this work."Item withdrawn by Mark Zulauf ([email protected]) on 2014-05-01T18:50:10Z
Item was in collections:
University of Illinois Theses & Dissertations (ID: 1)
No. of bitstreams: 1
khalid_mariyam.pdf: 13631331 bytes, checksum: 1b82ffa95f7b89cce8a507fd8552fe6c (MD5)Made available in DSpace on 2014-05-30T17:06:32Z (GMT). No. of bitstreams: 2
Mariyam_Khalid.pdf: 13631130 bytes, checksum: bbabefb4c682d6d19d437144bd4a929d (MD5)
license.txt: 4064 bytes, checksum: 5377323b0625637a6e5f02a5c0b7b118 (MD5)Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by Seth Robbins ([email protected]) on 2014-05-30T17:09:51Z
Item is restricted until 2016-05-30T17:09:03ZRestriction data tranferred 2014-07-01T11:39:03-05:00
Original Data
Group with Access UIUC Users [automated]
Release Date: 2016-05-30 12:09:03 UTC
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemU of I Only Restriction Lifted for Item 49774 on 2016-09-22T20:59:05Z
Methods to improve quality and diversity of language-vision models
No full textSubmission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-12-01The student, Jyoti Aneja, accepted the attached license on 2021-12-03 at 00:27.The student, Jyoti Aneja, submitted this Dissertation for approval on 2021-12-03 at 00:36.This Dissertation was approved for publication on 2021-12-03 at 13:22.DSpace SAF Submission Ingestion Package generated from Vireo submission #17379 on 2022-04-06 at 17:17:47Made available in DSpace on 2022-04-29T21:46:17Z (GMT). No. of bitstreams: 3
ANEJA-DISSERTATION-2021.pdf: 23857233 bytes, checksum: f1cb5a16a8c37da8e3d88ac42d339542 (MD5)
LICENSE.txt: 4208 bytes, checksum: 70bf9b59c99402d28a6f259391c734e8 (MD5)
PROQUEST_LICENSE.txt: 4554 bytes, checksum: 82134db12f8ad8e83aa8d6184b89eae6 (MD5)
Previous issue date: 2021-12-03Embargo set by: Seth Robbins for item 123370
Lift date: 2024-04-29T21:46:25Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemEmbargo set by: Seth Robbins for item 123370
Lift date: 2024-04-29T21:47:53Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemAuthor requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemU of I OnlyHumans can describe images and, more generally, the world around them in an evocative manner using vivid language constructs. Designing neural network models that can attain results similar to those of humans on tasks like image-captioning and image-generation is a worthy goal in the overall pursuit of artificial general intelligence. Notwithstanding the tremendous recent progress in this area, current systems still cannot describe objects and scenes as creatively and accurately as humans. As a step in the direction of bridging this gap, this thesis proposes architectures and algorithms for generating high-quality, diverse outputs for the tasks of image-captioning and image-generation
Image recognition, semantic segmentation and photo adjustment using deep neural networks
No full textSubmission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2018-05-01The student, Zhicheng Yan, accepted the attached license on 2016-03-08 at 16:12.The student, Zhicheng Yan, submitted this Dissertation for approval on 2016-03-08 at 16:21.This Dissertation was approved for publication on 2016-03-09 at 13:30.DSpace SAF Submission Ingestion Package generated from Vireo submission #9097 on 2016-07-07 at 13:48:30Made available in DSpace on 2016-07-07T20:26:56Z (GMT). No. of bitstreams: 3
YAN-DISSERTATION-2016.pdf: 35628927 bytes, checksum: ea3af13a8083286c039c5aa9faaa3eee (MD5)
LICENSE.txt: 4209 bytes, checksum: d98d954930bc9efae7b6bec2f9be29c2 (MD5)
PROQUEST_LICENSE.txt: 4555 bytes, checksum: 7f200197b6b7e731b1648ebc99d25a96 (MD5)
Previous issue date: 2016-03-09Embargo set by: Seth Robbins for item 93076
Lift date: 2018-07-07T20:28:14Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemEmbargo set by: Seth Robbins for item 93076
Lift date: 2018-07-07T20:35:34Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemU of I Only Restriction Lifted for Item 93076 on 2018-07-08T09:15:20Z.Deep Neural Networks (DNNs) have proven to be effective models for solving various problems in computer vision. Multi-Layer Perceptron Networks, Convolutional Neural Networks and Recurrent Neural Networks are representative examples of DNNs in the setting of supervised learning. The key ingredients in the successful development of DNN-based models include but not limited to task-specific designs of network architecture, discriminative feature representation learning and scalable training algorithms.
In this thesis, we describe a collection of DNN-based models to address three challenging computer vision tasks, namely large-scale visual recognition, image semantic segmentation and automatic photo adjustment. For each task, the network architecture is carefully designed on the basis of the nature of the task. For large-scale visual recognition, we design a hierarchical Convolutional Neural Network to fully exploit a semantic hierarchy among visual categories. The resulting model can be deemed as an ensemble of specialized classifiers. We improve state-of-the-art results at an affordable increase of the computational cost. For image semantic segmentation, we integrate convolutional layers with novel spatially recurrent layers for incorporating global contexts into the prediction process. The resulting hybrid network is capable of learning improved feature representations, which lead to more accurate region recognition and boundary localization. Combined with a post-processing step involving a fully-connected conditional random field, our hybrid network achieves new state-of-the-art results on a large benchmark dataset. For automatic photo adjustment, we take a data-driven approach to learn the underlying color transforms from manually enhanced examples. We formulate the learning problem as a regression task, which can be approached with a Multi-Layer Perceptron network. We concatenate global contextual features, local contextual features as well as pixel-wise features and feed them into the deep network. State-of-the-art results are achieved on datasets with both global and local stylized adjustments
