🎥 New Talk: “Generative, Malleable, and Personal User Interfaces”. This talk describes our work toward the long-held vision in the field of human-computer interaction. Talk Link: https://t.co/uotMwQnLIZ We are committed to making it as real as we can.

I will be presenting DataParticles today at the "Visualization Grammars and Design" session (12:06 - 12:20, X11+12) #CHI2023 Welcome to my talk and let's chat 😊

The Motion feature in #AdobeFresco empowers artists and creators to add motion to individual elements in their artwork. @AdobeResearch’s @liyiwei and @rubaiat share the “behind the scenes” of this impactful research work! https://t.co/ewlmCVlmF5

Stop reading the text !!! Have a graphic dialogue with OpenAI’s #GPT4 with #Graphologue. It turns GPT4-generated text into interactive node-link diagrams in real-time. New Human-Computer Interaction #HCI research makes #AI easier to use. More at https://t.co/2M90KhqNar

What if #ChatGPT were 3D? Structure #GPT4's responses in 3D with #Sensecape to better understand large amounts of text. New Human-Computer Interaction #HCI research makes #AI easier to use. More at https://t.co/2M90KhqNar.

Our paper was awarded Best Paper #CHI2023! Looking back, I am so grateful for this journey with @HaijunXia @janee424 @ZhutianChen. From the fuzzy idea we began with to the final project, I’m thankful for all the support, guidance, and inspiration that helped shape it (and me🐣

How can Curry outshine LeBron? Check out our #CHI2023 paper on iBall🏀 - A next-gen interactive game watching system with AR Vis + gaze/touch/text interactions! w/ @ticahere J.Shan @QisenY J.Beyer @HaijunXia @hpfister Live Demo,Code,Paper: https://t.co/4xD4jVzOBM #NBA #sports

😆 Welcome to check out our video and full paper: 📽️ https://t.co/kSmF81sGdT 📰 https://t.co/vpkmiqrUc5

From evaluation with experts we found that modularized planning with natural language allows creators to be story-focused and exploratory. Interestingly, we observed creators tend to reason on their story narratives with generated animations rather than the text itself!

To leverage the latent connections between text, data and visualizations, our system used constituency parsing to understand the pragmatic structure that informs data selection, encoding, multiple data operations, and animation effects.

We studied 44 popular animated data stories and also found a strong correspondence between the segments of an informative story and their desired visualizations. Moreover, we observed that the narrations are usually descriptive for desired visual effects.

Creating an animated data story is tedious and fragmented. Our #CHI2023 paper presents DataParticles - a language-driven system for visually exploring, reasoning and communicating data insights. Shout out to my collaborators @HaijunXia @janee424 @ZhutianChen.

Console logs are handy for debugging and inspecting code. However, it’s hard for programmers to track and make sense of them - long interleaved stream, deep data structures, numbers without context… Log-it #CHI2023 is to help! w/ interactive, structured, and visualized logs 🧵

Excited to be at #CHI2022 in person! 🌼🫶

VideoSticker supports a variety of interactive experiences with video content including learning a new skill, sports analytics, and integrating concepts from multiple videos.

Our system implements automated object extraction, tracking, and text detection, which are built on top of state-of-art deep learning models.

Instead of passive viewing , viewers can actively engage with educational videos and create semi-animated notes in just a few clicks.

VideoSticker supports 2 types of stickers ‘Frame Sticker’ and ‘Object Sticker’ to capture animated visual and text content from videos. Website: https://t.co/ZIwxIprKQp

🎥 -- 📔 I will present our paper *VideoSticker* tomorrow at #IUI2022 at 2:30 PM (Applications and Tools Session). We propose an AI-powered approach to take notes from videos. cc: @HariSubramonyam @eytanadar @DesignLabUCSD @UMSI @StanfordHCI @StanfordEd @StanfordHAI

Super excited to share our work "VideoSticker" - a tool for taking notes from videos in a semi-automated manner. This work started during my master's @UMich with amazing @HariSubramonyam @eytanadar. #IUI2022 📎Paper: https://t.co/OTCkBxdhrv 📽️Video: https://t.co/BnMMqriP03