Adriana Ivanova Kovashka BACKGROUND

Transcription

1 Adriana Ivanova Kovashka Assistant Professor in Computer Science at University of Pittsburgh kovashka BACKGROUND EDUCATION The University of Texas at Austin (Austin, TX): 08/ /2014 PhD, M.S.Comp.Sci. Major: Computer Science, Concentration: Computer Vision / Artificial Intelligence Pomona College (Claremont, CA): 08/ /2008 Bachelor of Arts Majors: Computer Science and Media Studies, Minor: German APPOINTMENTS University of Pittsburgh, Computer Science Dept. Assistant Professor 01/ present. UT Austin, Computer Science Dept. Graduate Research Assistant 06/ /2014. Google Inc. Research, Mountain View Software Engineering Intern 06/ /2012. Princeton University, Distributed Mentor Project Research Assistant 05/ /2007. HONORS AND AWARDS NSF CISE Research Initiation Initiative (CRII) Award, May Outstanding Reviewer Award, CVPR 2017 and CVPR (Given to 6% of reviewers.) Doctoral Consortium Travel Grant, CVPR (Was accepted to participate in a mentoring program for senior PhD students, and received a $700 stipend.) Microelectronics and Computer Development (MCD) Fellowship. The University of Texas at Austin. September May (Awarded to about 10% of all admitted students.) CRA Distributed Mentor Project Award. March Adriana Kovashka: CV (07/2018) Page 1 of 8

2 RESEARCH citations h-index journals conference workshop chapters grants $802,428 JOURNAL PUBLICATIONS (PEER-REVIEWED) 1. Adriana Kovashka, Devi Parikh, and Kristen Grauman. WhittleSearch: Interactive Image Search with Relative Attribute Feedback. In International Journal of Computer Vision (IJCV), November 1, Volume 115, issue 2, pp Adriana Kovashka and Kristen Grauman. Discovering Attribute Shades of Meaning with the Crowd. In International Journal of Computer Vision (IJCV), August 1, Volume 114, issue 1, pp CONFERENCE PUBLICATIONS (PEER-REVIEWED) 1. Keren Ye and Adriana Kovashka. ADVISE: Symbolism and External Knowledge for Decoding Advertisements. To appear, Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, UK, September Acceptance rate: 30%. 2. Christopher Thomas and Adriana Kovashka. Persuasive Faces: Generating Faces in Advertisements. To appear, Proceedings of the British Machine Vision Conference (BMVC), Newcastle, UK, September Acceptance rate: 29.9%. 3. Mingda Zhang, Rebecca Hwa and Adriana Kovashka. Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Text. To appear, Proceedings of the British Machine Vision Conference (BMVC), Newcastle, UK, September (Spotlight.) Acceptance rate: 6.6% (spotlights). 4. Nils Murrugarra-Llerena and Adriana Kovashka. Image Retrieval with Mixed Initiative and Multimodal Feedback. To appear, Proceedings of the British Machine Vision Conference (BMVC), Newcastle, UK, September (Oral.) Acceptance rate: 4.3% (orals). 5. Keren Ye, Kyle Buettner and Adriana Kovashka. Story Understanding in Video Advertisements. To appear, Proceedings of the British Machine Vision Conference (BMVC), Newcastle, UK, September Acceptance rate: 29.9%. 6. Nils Murrugarra-Llerena and Adriana Kovashka. Asking Friendly Strangers: Non-Semantic Attribute Transfer. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), New Orleans, LA, February Acceptance rate: 24.6%. 7. Bhavin Modi and Adriana Kovashka. Confidence and Diversity for Active Selection of Feedback in Image Retrieval. In Proceedings of the British Machine Vision Conference (BMVC), London, UK, September Acceptance rate: 30%. Adriana Kovashka: CV (07/2018) Page 2 of 8

3 8. Zaeem Hussain, Xiaozhong Zhang, Mingda Zhang, Keren Ye, Christopher Thomas, Zuha Agha, Nathan Ong, and Adriana Kovashka. Automatic Understanding of Image and Video Advertisements. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, July (Spotlight.) Acceptance rate: 8% (spotlights). 9. Nils Murrugarra-Llerena and Adriana Kovashka. Learning Attributes from Human Gaze. In Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, March (Oral.) Acceptance rate: 45%. 10. Debashis Ganguly, Mohammad H. Mofrad, and Adriana Kovashka. Detecting Sexually Provocative Images. In Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, March (Oral.) Acceptance rate: 45%. 11. Christopher Thomas and Adriana Kovashka. Seeing Behind the Camera: Identifying the Authorship of a Photograph. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, June Acceptance rate: 29.9%. 12. Siqi Liu and Adriana Kovashka. Adapting Attributes by Selecting Features Similar across Domains. In IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, March Acceptance rate (first round): 34%. 13. Adriana Kovashka and Kristen Grauman. Attribute Adaptation for Personalized Image Search. In Proceedings of the International Conference on Computer Vision (ICCV), Sydney, Australia, December Acceptance rate: 27.9%. 14. Adriana Kovashka and Kristen Grauman. Attribute Pivots for Guiding Relevance Feedback in Image Search. In Proceedings of the International Conference on Computer Vision (ICCV), Sydney, Australia, December Acceptance rate: 27.9%. 15. Adriana Kovashka, Devi Parikh, and Kristen Grauman. WhittleSearch: Image Search with Relative Attribute Feedback. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, June Acceptance rate: 24.1%. 16. Devi Parikh, Adriana Kovashka, Amar Parkash, and Kristen Grauman. Relative Attributes for Enhanced Human-Machine Communication (Invited paper). In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Toronto, Ontario, Canada, July Adriana Kovashka, Sudheendra Vijayanarasimhan, and Kristen Grauman. Actively Selecting Annotations Among Objects and Attributes. In Proceedings of the International Conference on Computer Vision (ICCV), Barcelona, Spain, November Acceptance rate: 23.7%. 18. Adriana Kovashka and Kristen Grauman. Learning a Hierarchy of Discriminative Space- Time Neighborhood Features for Human Action Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June Acceptance rate: 26.7%. 19. Sindhu Raghavan, Adriana Kovashka, and Raymond Mooney. Authorship Attribution Using Probabilistic Context-Free Grammars. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL), Short Papers, Uppsala, Sweden, July Acceptance rate: 22%. Adriana Kovashka: CV (07/2018) Page 3 of 8

4 20. Adriana Kovashka and Matthew Lease. Human and Machine Detection of Stylistic Similarity in Art. In Proceedings of the 1st Annual Conference on the Future of Distributed Work (CrowdConf), San Francisco, CA, October WORKSHOP PUBLICATIONS (PEER-REVIEWED) 1. Christopher Thomas, Adriana Kovashka, Donald Chiarulli and Steven Levitan. A Visual Attention Algorithm Designed for Coupled Oscillator Acceleration. In The Twelfth IEEE Embedded Vision Workshop, held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, June (Oral) 2. Xinyue Huang and Adriana Kovashka. Inferring Visual Persuasion via Body Language, Setting, and Deep Features. In ChaLearn Looking at People and Faces of the World Challenge and Workshop, held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, June (Oral) 3. Adriana Kovashka and Kristen Grauman. Discovering Shades of Attribute Meaning with the Crowd. In Third International Workshop on Parts and Attributes, held in conjunction with the European Conference on Computer Vision (ECCV), Zurich, Switzerland, September Adriana Kovashka and Kristen Grauman. Interactive Image Search with Attribute-based Guidance and Personalization. In Workshop on Computer Vision and Human Computation, in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, June BOOK CHAPTERS AND SURVEYS (INVITED) 1. Adriana Kovashka and Kristen Grauman, Attributes for Image Retrieval, In Visual Attributes (Advances in Computer Vision and Pattern Recognition), Springer, Adriana Kovashka, Olga Russakovsky, Kristen Grauman, Fei-Fei Li, Crowdsourcing in Computer Vision. In Foundations and Trends in Computer Graphics and Vision, NOW Publishers, THESES 1. Interactive Image Search with Attributes. PhD Thesis. University of Texas at Austin. August Dorian: Music Recommendation Strategies using Social Network Mining. Bachelor s Thesis. Pomona College. May Adriana Kovashka: CV (07/2018) Page 4 of 8

5 INVITED TALKS 1. Computer Vision and Pattern Recognition (CVPR) Visual Question Answering Workshop, June How to be a Good Citizen of CVPR Workshop, June CVPR Area Chair Workshop, February University of Rochester, Computer Science Colloquium, December University of Pittsburgh, Advancing Research through Computing Symposium, March Google Pittsburgh, May University of Pittsburgh, Intelligent Systems Program, March University of Pittsburgh, Computational Aesthetics Workshop, November European Conference on Computer Vision (ECCV) Workshop on Parts and Attributes, September Army Research Laboratory CARS Workshop, July University of North Carolina, April Carnegie Mellon University, VASC Seminar, April University of Pittsburgh, Computer Science Colloquium, March ebay Research Labs, March Oregon State University, EECS Colloquium, March Stony Brook University, Computer Science Colloquium, February Lafayette College, Computer Science Colloquium, February NAACL-HLT 2013 Workshop on Vision and Language, June FUNDING 1. Title: Mixed-Initiative Image Retrieval, Role: Sole PI, Funding agency: University of Pittsburgh Central Research Development Fund (CRDF), Amount: $17,750, Duration: August 1, 2018 to June 30, 2020, Date awarded: July 5, Title: Modeling Narrative Structure in Advertisement Videos, Role: Sole PI, Funding agency: Google Faculty Research Awards, Amount: $42,900, Date awarded: February 21, Title: RI: Small: Modeling Vividness and Symbolism for Decoding Visual Rhetoric, Role: PI, Co-PI: Rebecca Hwa, Funding agency: NSF, Amount: $449,978, Duration: August 1, 2017 to July 31, 2020, Date awarded: July 27, 2017 Adriana Kovashka: CV (07/2018) Page 5 of 8

6 4. Title: Deeply Interactive Image Search: Learning Attribute Vocabularies and Spatial Support from People, Role: Sole PI, Funding agency: University of Pittsburgh Central Research Development Fund (CRDF), Amount: $15,749, Duration: July 31, 2016 to June 30, 2018, Date awarded: June 24, Title: CRII: RI: Automatically Understanding the Messages and Goals of Visual Media, Role: Sole PI, Funding agency: NSF, Amount: $182,590 (incl. REU supplement), Duration: June 1, 2016 to May 31, 2018, Date awarded: May 27, Title: Decoding Video Advertisements, Role: Sole PI, Funding agency: Google Faculty Research Awards, Amount: $41,361, Date awarded: February 8, Title: Group Travel Grant for the Doctoral Consortium of the IEEE Conference on Computer Vision and Pattern Recognition, Role: Sole PI, Funding agency: NSF, Amount: $20,000, Duration: June 1, 2017 to May 31, 2018, Date awarded: May 9, Title: Group Travel Grant for the Doctoral Consortium of the IEEE Conference on Computer Vision and Pattern Recognition, Role: Sole PI, Funding agency: NSF, Amount: $17,050, Duration: June 1, 2016 to May 31, 2017, Date awarded: March 23, Title: Group Travel Grant for the Doctoral Consortium of the IEEE Conference on Computer Vision and Pattern Recognition, Role: Sole PI, Funding agency: NSF, Amount: $15,050, Duration: June 1, 2015 to May 31, 2016, Date awarded: April 23, 2015 PATENTS 1. Efficiently identifying images, videos, songs or documents most relevant to the user using binary search trees on attributes for guiding relevance feedback, Inventors: Kristen Grauman, Adriana Kovashka, Owner: Board of Regents, The University of Texas System, Issued: November 3, Efficiently identifying images, videos, songs or documents most relevant to the user based on attribute feedback, Inventors: Kristen Grauman, Adriana Kovashka, Devi Parikh, Owner: Board of Regents, The University of Texas System, Issued: March 22, 2016 DATASETS Automatic Understanding of Image and Video Advertisements. Images: 64,832. Videos: 3,477. Annotations: 700,000. Number of times accessed: 1,780. Accessed: 954 times from the United States (28 different states), 187 from India, 145 from Japan, 113 from China, and more from 50 other countries. PRESS TheStack.com. New photographs from dead photographers with convolutional neural networks. November 12, Adriana Kovashka: CV (07/2018) Page 6 of 8

7 COURSES TAUGHT TEACHING AND MENTORING CS2770: Computer Vision (Spring 2017, Spring 2018; graduate; OMET 4.47/5) developed new course CS2750: Machine Learning (Spring 2016, Spring 2017; graduate; OMET 3.72/5, 3.95/5) CS1674: Introduction to Computer Vision (Fall 2016, Spring 2018; undergraduate; OMET 3.89/5) developed new course CS1699: Introduction to Computer Vision (Fall 2015; undergraduate; OMET 3.39/5) CS3710: Visual Recognition (Spring 2015; graduate; OMET 3.88/5) STUDENTS SUPERVISED Nils Murrugarra-Llerena (PhD; dissertation proposal passed; supervised 2015-present; expected graduation 2018) Christopher Thomas (PhD; comprehensive exam passed; supervised 2015-present; expected graduation 2019) Keren Ye (PhD; supervised 2016-present) Mingda Zhang (PhD; supervised 2016-present) Wei Guo (PhD; jointly supervised by Jingtao Wang) PHD STUDENT COMMITTEE MEMBERSHIP Huy Nguyen Fan Zhang Charmgil Hong ChangSheng Liu Patrick Luo Siqi Liu Yanbing Xue Jeongmin Lee Omid Kashefi (ISP) Rui Meng (IS) Adriana Kovashka: CV (07/2018) Page 7 of 8

8 SERVICE PROFESSIONAL SERVICE 1. Chairing Duties at Conferences (by Invitation): Area Chair: CVPR 2019, CVPR 2018, WACV 2017, WACV 2016, ICVGIP Tutorials Chair: WACV Chair / co-chair: CVPR 2015, 2016, 2017 Doctoral Consortium. Session Chair: CVPR 2018, 2016, WACV Workshop Organization: Sole Organizer: CVPR 2016 Workshop Towards Automatic Understanding of Visual Advertisements. Organizer: CVPR 2016 Workshop Visual Understanding of Subjective Attributes of Data. Organizer: CVPR 2015 Workshop Women in Computer Vision. Organizer: ECCV 2014 Workshop Human-Machine Communication for Visual Recognition and Search. 3. Reviewing and Judging: Panelist: National Science Foundation (NSF), 2015, Senior Program Committee Member: IJCAI Program Committee: CVPR 2013, 2015 (Outstanding Reviewer), 2016, 2017 (Outstanding Reviewer); ICCV 2013, 2015, 2017; ECCV 2012, 2014, 2016; NIPS 2014, 2015, 2016, 2018; ICLR 2018; AAAI 2014; HCOMP 2012; UIST 2015; EGOCV (CVPRW) 2014, 2016; BigVision (CVPRW) Journal Reviewer: IJCV 2013; TPAMI 2014, 2015, 2017, 2018; CVIU 2014; TKDE Judge: LDV Vision Summit 2016 Computer Vision Challenge. Adriana Kovashka: CV (07/2018) Page 8 of 8