Tuesday, October 4, 2016

Sketch Recognition Lab Summer Defense Follow-Ups

Over the summer of 2016, three Sketch Recognition Lab members, Siddartha Karthik, Swarna Keshavabhotla, and Stephanie Valentine, successfully defended their theses and dissertation in front of their committees and Director Tracy Hammond. The back-to-back-to-back defenses made for a long day on June 10th, but one that was well worth the work and the hours put in by everyone involved.

(Siddartha Karthik)

Siddartha Karthik, who is getting his MS in Computer Science and is set to graduate in August 2016, presented his thesis work on data mining and labeling in sketch recognition. His advisor was Dr. Hammond. Motivated by his want “to do some kind of data mining and machine learning” and a sketch recognition class, which he greatly enjoyed, that he took when he was in his first semester at Texas A&M University, Karthik focused his research on the recognition and labeling of images. 
As stated in his abstract:

“Recognizing sketches instantaneously is necessary to build beautiful interfaces with real time feedback. There are various techniques to quickly recognize sketches into ten or twenty classes. However for much larger datasets of sketches from a large number of classes, these existing techniques can take an extended period of time to accurately classify an incoming sketch and require significant computational overhead. Thus, to make classification of large datasets feasible, we propose using multiple stages of recognition… This process both significantly reduces the time taken to classify such huge datasets of sketches, and increases both the accuracy and precision of the recognition.”

Now that his thesis has been defended and he’s set to graduate at the end of the summer, Karthik is preparing to start working at Uber in San Francisco. When asked about where he saw his research going, he replied, “The first thing I have in my mind is to get it published. After that, there are a lot of ways in which others could expand on my work.”

Furthermore, if he could change one thing about his time in SRL, Karthik stated that he “Should have started working on [his] research a couple of semesters earlier” to make the process easier and less stressful.


(Stephanie Valentine defending her dissertation)
In a much different area of sketch recognition, Stephanie Valentine defended her dissertation and became Dr. Valentine with her research about children's social networking. Valentine has worked for years developing KidGab, a social media site designed for children under the age of 13, and promoting her nonprofit, Wired Youth.
As Valentine stated, "Lots of people have studied teens and adults, but children's social networking behaviors (from the perspective of the social network designer/admin) had never been published. I looked at questions like, What do pre-adolescents really talk about online? Are they likely to conform to one another? Which activities and affordances engage them most?"

When asked about her motivation for the research, Valentine responded that she wanted her work to be meaningful and good for humanity. Knowing the pain of cyberbullying, she saw plenty of research regarding cyberbully, but most was focused on reporting it or detecting it, rather than extinguishing it.

"I chose work which simultaneously prevents cyberbullying and is meaningful to the research world," she commented. "Kids are going to be online anyway, so why not give them a safe space to learn how to social network before they are expected to grasp the concepts and safety procedures of adult networks it at the level of an adult? My social network, KidGab; my nonprofit, Wired Youth; and now the iPhone and Android apps are all dedicated to that aim."

Valentine plans to stay in SRL as a research assistant and to continue her work on KidGab and has received a grant from the National Science Foundation which will fund her research for about a year. She plans to have a graduate assistant for research as she works to build her social network site even more, reaching more and more children every day.

"This lab has been amazing in so many ways," she reflected when asked about her takeaways. "When I arrived, the lab members nicknamed it the "rainbow lab" because we had people from such diverse origins working together in collective awesomeness. Dr. Hammond has a knack for recruiting very personable and energetic students, so the lab is frequently abuzz with some new exciting thing or another (be it technological, social, algorithmic, Pokemon-related, or anything else)."

Continuing by saying that Dr. Hammond has been supportive beyond the call of duty for an adviser, Valentine's "biggest takeway will be in [her] interactions and observations of [Dr. Hammond]." She continued, "I want to be her when I grow up: a scientist with a wide lens of knowledge, the life of every conversation and the brightest presence in any room. And now she's doing all that with a baby in her arms. It's unbelievable."

When asked about what direction her research is going, Valentine answered that it could go in so many ways that she often has to stop herself from asking more questions about it. Be it studying digital conformity found in children online or the creative processes of creation that children go through when allowed to draw and post their own sketches, the path which KidGab's research could go is endless and in an area of study that is relatively untapped. 
(Valentine explaining KidGab to her audience)
Upon reflecting on her time at SRL and her dissertation research, Valentine isn't sure if she would go back and change something, if she could, though she would love to go back and converse with her past-self.
"I would tell myself that the next few years are going to be hard. Your work won't always be respected because of its lack of theoretical algorithmic-ey-ness. Your thesis won't look like a Greek mathematician's notebook, and that's okay. People will reason that dealing with math and computers is much harder than dealing with humans, right? And you're not just dealing with humans, you're dealing with children. Piece of cake, they'll say. False. So false. They've clearly never tried to extract scientific meaning from a child's digital poetry. I would tell myself that you'll have to fight and fight some more for what you believe in, forging your own path when there isn't one before you. You'll find a way.
Not everyone will be happy, computer scientist reviewers can be mean and unreasonable, so take solace in those who do believe in your work. There are awesome people who will help and guide you. Pay attention to them. But in the end, you'll be so proud of your dissertation -- your legacy -- and the difference you made in the hearts of many a Girl Scout!"

Everyone in the Sketch Recognition Lab would like to congratulate Siddartha Karthik, Swarna Keshavabhotla, and Dr. Stephanie Valentine on all of their hard work. We are so proud of everything they have accomplished - and will accomplish in the future.

No comments:

Post a Comment