User Tools

Site Tools



This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
projects:year4:15.8 [2019/08/21 12:30]
sally.johnson [Table]
projects:year4:15.8 [2021/06/02 15:38] (current)
sally.johnson [Table]
Line 2: Line 2:
 ===== Project - Summary ===== ===== Project - Summary =====
 <WRAP leftalign box > <WRAP leftalign box >
-**Objectives:** +Automatic image content description is vital problems in computer vision that artificial intelligence and natural language processing. The primary challenge towards this goal is in the design of a multi-model approach that is rich enough to aim simultaneously about contents of images and their representation in terms of words or sentences. We present multi-model approach based on a deep learning architecture that combines recent advances in computer vision such as; salient object proposal prediction, and object detection to generate natural sentences describing an image. Leveraging recent advances in recognition of objects, their attributes and locations, however they are limited in their expressivity. Moreover, current object detection methods still suffer various problems in localization and processing time that render them unreliable and inadequate as they are still slow at test timeWe target the high-level goal of annotating the contents of images based salient regions or segments of images and study the multimodal correspondence between words and imagesThe idea is to correctly labeling scenes, objects and regions with a fixed set of categorieswhile our focus is on richer and higher-level descriptions of regions. The proposed approaches can also be used in text to image search in large scale image retrieval systems.
- +
-The objectives of our CVDI project were to develop: +
-  * A prototype visual ontology application for capturing software reuse and adaptation in a target test domain. +
-  * A platform for modeling adaptation science and service. +
-  * An approach for CVDI partners to determine and strategically plan for greater impact of data, application, and algorithm outputs. +
- +
 </WRAP> </WRAP>
 ===== Project - Team ===== ===== Project - Team =====
-^ Team Member           ^ Role         ^ Email          ^ Phone Number   ^ Academic Site/IAB   ^ +^ Team Member           ^ Role         ^ Email                    ^ Phone Number     ^ Academic Site/IAB   ^ 
-| Moncef Gabbouj        | PI           Not available  Not available  | Tampere University +| Moncef Gabbouj        | PI    +358 400 736613  | Tampere University 
-| Serkan Kiranyaz       | PI           Not available  Not available  | Tampere University +| Serkan Kiranyaz       | PI   97 43 063 5600   | Tampere University 
-| Iftikhar Ahmad        | PI           | Not available  | Not available  | Tampere University +| Iftikhar Ahmad        | PI           | Not available            | Not available    | Tampere University 
-| Alexandros Iosifidis  | PI           Not available  Not available  | Tampere University +| Alexandros Iosifidis  | PI              +45 9350 8875    | Tampere University 
-| Muhammad Adeel Waris  | PhD Student  | Not available  | Not available  | Tampere University  |+| Muhammad Adeel Waris  | PhD Student  | Not available            | Not available    | Tampere University  |
Line 23: Line 16:
 ===== Project - Impact and Uses/Benefits ===== ===== Project - Impact and Uses/Benefits =====
 <WRAP leftalign box > <WRAP leftalign box >
-The impact and benefits of our work include the following: +Industrial partner can train this system for any object classification task that it desiresSuch systems can serve the companies that are dealing with computer vision problems such as camera smart object auto-focusingadvertisement assessmentface detection, and many other applications basically including any object/region detection task.
-  * A more accurate view of data and algorithm reuse. +
-  * Platform to enable radical, new adaptation combinations, documenting reuse of data and algorithms. +
- +
-Specific to industry, our work can help industry provide services that support better science and informed decision makingThe actual impact on better science is hard to measure, although the growth in digital data and data intensive research provides opportunities to address society's grand challenges in ways that have been previously unimaginable. The cost of data gathering and software development is not trivial, and the reuse of these resources is being mandated and encouraged by federal agencies. Industry also recognizes the value of these approaches in efforts such as the recent launch of the NSF Big Data Regional Hubs. The work pursued and achieved in our CVDI project leads to a better return on investment (ROI) of resources allocated to data and software creationusearchivingby enabling reuse that is accurate and resourceful. The work may also procure deeper understanding sustainable knowledge of ontological connections among knowledge assets. Finally, we believe the work can lead to better effort to explore predictive capabilities in the future, although more research is needed in this area. +
 </WRAP> </WRAP>
Line 36: Line 24:
 ===== Project - Documents ===== ===== Project - Documents =====
projects/year4/15.8.1566408619.txt.gz · Last modified: 2019/08/21 12:30 by sally.johnson