Adriana Kovashka's guest appearances

Adriana Kovashka

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Humans of AI: Stories, Not Stats

Jeff Dean

Charles Isbell

Anima Anandkumar

Stefan Lee

Carlos Guestrin

Devi Parikh

Georgia Gkioxari

Ayanna Howard

Kate Darling

Jason Holmberg

Lotte Bransen

Christopher Berner

David Spiegelhalter

Kristen Grauman

Stephen Merity

OwlTail

Dhruv Batra

Adriana Kovashka is an Assistant Professor in Computer Science at the University of Pittsburgh. Find out more about her at her homepage. Humans of AI: Stories, Not Stats is an interview series with AI researchers to get to know them better as people. We don't talk about AI or their work or the stats of their life like what college they went to. They share what they think about, what they are insecure about, what they get excited about. They share the stories of their day-to-day life. Videos of these interviews are available at humanstories.ai. The host of this episode is Dhruv Batra, an Associate Professor in the School of Interactive Computing at Georgia Tech and a Research Scientist at Facebook AI Research (FAIR). Find out more about him at his homepage or follow him on Twitter. This interview was recorded on 8th April 2021.--- Send in a voice message: https://podcasters.spotify.com/pod/show/humanstoriesai/message

Adriana Kovashka is an Assistant Professor in Computer Science at the University of Pittsburgh. Find out more about her at <a href="https://people.cs.pitt.edu/~kovashka/" rel="nofollow" target="_blank">her homepage</a>. Humans of AI: Stories, Not Stats is an interview series with AI researchers to get to know them better as people. We don't talk about AI or their work or the stats of their life like what college they went to. They share what they think about, what they are insecure about, what they get excited about. They share the stories of their day-to-day life. Videos of these interviews are available at <a href="http://humanstories.ai/" rel="ugc noopener noreferrer nofollow" target="_blank">humanstories.ai</a>. The host of this episode is Dhruv Batra, an Associate Professor in the School of Interactive Computing at Georgia Tech and a Research Scientist at Facebook AI Research (FAIR). Find out more about him at <a href="https://www.cc.gatech.edu/~dbatra/" rel="ugc noopener noreferrer nofollow" target="_blank">his homepage</a> or follow him on <a href="https://twitter.com/DhruvBatraDB" rel="ugc noopener noreferrer nofollow" target="_blank">Twitter</a>. This interview was recorded on 8th April 2021.--- Send in a voice message: <a href="https://podcasters.spotify.com/pod/show/humanstoriesai/message" rel="nofollow" target="_blank">https://podcasters.spotify.com/pod/show/humanstoriesai/message</a>

S2E11: Adriana Kovashka with Dhruv Batra

Today we’re joined by Adriana Kovashka, an Assistant Professor at the University of Pittsburgh. In our conversation with Adriana, we explore her visual commonsense research, and how it intersects with her background in media studies. We discuss the idea of shortcuts, or faults in visual question answering data sets that appear in many SOTA results, as well as the concept of masking, a technique developed to assist in context prediction. Adriana then describes how these techniques fit into her broader goal of trying to understand the rhetoric of visual advertisements.  Finally, Adriana shares a bit about her work on robust visual reasoning, the parallels between this research and other work happening around explainability, and the vision for her work going forward.  The complete show notes for this episode can be found at twimlai.com/go/463.

Today we’re joined by Adriana Kovashka, an Assistant Professor at the University of Pittsburgh. In our conversation with Adriana, we explore her visual commonsense research, and how it intersects with her background in media studies. We discuss the idea of shortcuts, or faults in visual question answering data sets that appear in many SOTA results, as well as the concept of masking, a technique developed to assist in context prediction. Adriana then describes how these techniques fit into her broader goal of trying to understand the rhetoric of visual advertisements.  Finally, Adriana shares a bit about her work on robust visual reasoning, the parallels between this research and other work happening around explainability, and the vision for her work going forward.  The complete show notes for this episode can be found at <a href="http://twimlai.com/go/463" rel="nofollow" target="_blank">twimlai.com/go/463</a>.

Robust Visual Reasoning with Adriana Kovashka - #463