Devi Parikh

Devi Parikh
Devi Parikh
Alma mater	Carnegie Mellon University
Known for	Visual Question Answering (VQA), AI research
	Scientific career
Fields	Computer vision, Natural language processing
Institutions	Meta, Georgia Tech, Virginia Tech

Devi Parikh is an American computer scientist.

Career

Parikh earned her PhD in Electrical and Computer Engineering at Carnegie Mellon University. She has served as a professor at Virginia Tech and Georgia Tech, and as of 2022 she is a research director at Meta.^[1]

Research

Parikh's research focuses on computer vision and natural language processing.

In 2015, Parikh and her students at Virginia Tech worked on AI for Visual Question Answering (VQA). This technology allows users to ask questions about pictures, e.g. "Is this a vegetarian pizza?"^[2]^[3] Parikh's VQA dataset has been used to evaluate over 30 AI models.^[4]

In 2017, Parikh published a conversational agent called ParlAI.^[5] In 2020, she developed an AI system that generates dance moves in sync with songs.^[6]^[7] In 2022, Parikh and a team at Meta developed Make-a-Video, a text-to-video AI model that is based on the diffusion algorithm.^[8]^[9]

Awards

2017 IJCAI Computers and Thought Award
2011 ICCV Best-Paper Award ("Marr Prize")

References

^ Parikh, Devi (2022-12-28). "Curriculum Vitae" (PDF). Retrieved 2022-12-28.
^ Agrawal, Aishwarya; Lu, Jiasen; Antol, Stanislaw; Mitchell, Margaret; Zitnick, C. Lawrence; Batra, Dhruv; Parikh, Devi (2016-10-26). "VQA: Visual Question Answering". arXiv:1505.00468 [cs.CL].
^ Yao, Mariya. "Meet These Incredible Women Advancing A.I. Research". Forbes. Retrieved 2022-12-28.
^ "Papers with Code - VQA v2 test-dev Benchmark (Visual Question Answering)". paperswithcode.com. Retrieved 2022-12-28.
^ Mannes, John (2017-05-15). "Facebook's ParlAI is where researchers will push the boundaries of conversational AI". TechCrunch. Retrieved 2022-12-28.
^ Tendulkar, Purva; Das, Abhishek; Kembhavi, Aniruddha; Parikh, Devi (2020-06-23). "Feel The Music: Automatically Generating A Dance For An Input Song". arXiv:2006.11905 [cs.AI].
^ "Facebook's new choreography AI is a dancing queen". Engadget. 23 June 2020. Retrieved 2022-12-28.
^ Edwards, Benj (2022-09-29). "Meta announces Make-A-Video, which generates video from text [Updated]". Ars Technica. Retrieved 2022-12-28.
^ Singer, Uriel; Polyak, Adam; Hayes, Thomas; Yin, Xi; An, Jie; Zhang, Songyang; Hu, Qiyuan; Yang, Harry; Ashual, Oron; Gafni, Oran; Parikh, Devi; Gupta, Sonal; Taigman, Yaniv (2022-09-29). "Make-A-Video: Text-to-Video Generation without Text-Video Data". arXiv:2209.14792 [cs.CV].

[1] Parikh, Devi (2022-12-28). "Curriculum Vitae" (PDF). Retrieved 2022-12-28.

[2] Agrawal, Aishwarya; Lu, Jiasen; Antol, Stanislaw; Mitchell, Margaret; Zitnick, C. Lawrence; Batra, Dhruv; Parikh, Devi (2016-10-26). "VQA: Visual Question Answering". arXiv:1505.00468 [cs.CL].

[3] Yao, Mariya. "Meet These Incredible Women Advancing A.I. Research". Forbes. Retrieved 2022-12-28.

[4] "Papers with Code - VQA v2 test-dev Benchmark (Visual Question Answering)". paperswithcode.com. Retrieved 2022-12-28.

[5] Mannes, John (2017-05-15). "Facebook's ParlAI is where researchers will push the boundaries of conversational AI". TechCrunch. Retrieved 2022-12-28.

[6] Tendulkar, Purva; Das, Abhishek; Kembhavi, Aniruddha; Parikh, Devi (2020-06-23). "Feel The Music: Automatically Generating A Dance For An Input Song". arXiv:2006.11905 [cs.AI].

[7] "Facebook's new choreography AI is a dancing queen". Engadget. 23 June 2020. Retrieved 2022-12-28.

[8] Edwards, Benj (2022-09-29). "Meta announces Make-A-Video, which generates video from text [Updated]". Ars Technica. Retrieved 2022-12-28.

[9] Singer, Uriel; Polyak, Adam; Hayes, Thomas; Yin, Xi; An, Jie; Zhang, Songyang; Hu, Qiyuan; Yang, Harry; Ashual, Oron; Gafni, Oran; Parikh, Devi; Gupta, Sonal; Taigman, Yaniv (2022-09-29). "Make-A-Video: Text-to-Video Generation without Text-Video Data". arXiv:2209.14792 [cs.CV].

[1]

[2]

[3]

[4]

[5]

[6]

[7]

[8]

[9]