| NSF Org: |
CNS Division Of Computer and Network Systems |
| Recipient: |
|
| Initial Amendment Date: | September 17, 2014 |
| Latest Amendment Date: | September 17, 2014 |
| Award Number: | 1463102 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Jie Yang
jyang@nsf.gov (703)292-4768 CNS Division Of Computer and Network Systems CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | October 1, 2014 |
| End Date: | September 30, 2017 (Estimated) |
| Total Intended Award Amount: | $150,000.00 |
| Total Awarded Amount to Date: | $150,000.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
1109 GEDDES AVE STE 3300 ANN ARBOR MI US 48109-1015 (734)763-6438 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
MI US 48109-1274 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | CCRI-CISE Cmnty Rsrch Infrstrc |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
Broad access to image and video datasets has been responsible for much of the progress in computer vision recognition problems over the last decade. These common benchmarks have played a leading role in transforming recognition research from a black art into an experimental science. Progress, however, has stagnated; although datasets continue to grow, they are developed and annotated in isolation: e.g., a collection of sporting activities, a set of objects in images, etc. These isolated datasets suffer from task and domain-specific bias, and knowledge transfer across them is extremely limited. This project is investigating and establishing a prototype architecture that federates across various recognition problems and modalities, by establishing a common namespace for entities, events and annotations across the datasets. The project is also establishing a web-portal for the prototype federated dataset architecture and linking two existing recognition datasets into the prototype architecture. The resulting federated structure is truly greater than the sum of its parts, and can support new research that was not previously possible for the computer vision community and other related fields.
As a first test scenario for this federated architecture, this project is investigating and constructing a new federated dataset of images and video annotated with various forms of associated text. Image and video content annotations span both the spatial and temporal dimensions while textual annotations reflecting depicted content range from complete free-form natural language descriptions, to more targeted phrases and referring expressions, to individual keyword lists. This dataset is being constructed to promote and enhance collaboration efforts between the vision and language communities by providing a new multi-modal annotated dataset with associated research competitions.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
The Federated Data Set Infrastructure for Recognition Problems in Computer Vision was a seed project in the CRI program that led to two significant outcomes. First, the investigators of the workshop held a widely attended information-gathering workshop at CVPR 2015: The Future of Datasets in Vision. The workshop hosted four invited speakers, twenty posters from twenty-six institutions, ten countries and eighty-four individual speakers. During and after the workshop, the investigators gathered and analyzed feedback and interests from the computer vision community to help craft a subsequent full-sized proposal to the CRI program. Significant lessons learned from the community were that a common infrastructure to store and provide access to the large and growing number of datasets in the community would provide the most utility to the community while the alternative potential of establishing a common namespace was not seen as likely to the fruitful for the community.
This full-sized proposal was funded and is the second outcome of the seed project. COVE -- Computer Vision Exchange for Data, Annotation and Tools -- is the resulting full-size project that integrates the lessons learned from this seed and from the workshop. COVE will provide a common index for data sets in the computer vision community, with an index and archive coinciding with the Computer Vision Foundation's open access archive. The COVE project is ongoing and will reside at http://cove.thecvf.com.
Last Modified: 02/12/2018
Modified by: Jason J Corso
Please report errors in award information by writing to: awardsearch@nsf.gov.
