Oct 2022 - CrossA11y won a Best Paper Award!!
Stay tuned for more details! I will attend UIST 2022 in person. Let's chat in person. Shoot me an email!
April 2022 - Our work on Snooping neural network is featured in a CACM news article!
Our prototype shows it is possible to extract both the high-level network topology and detailed hyperparameters. Read the blog here.
March 2022 - Our Audio-driven Gesture Animation paper was accepted to CVPR 2022!
Synthesize high-quality videos via reenactment from novel video motion graph.
Feb 2022 — I am promoted to Senior Research Scientist!
This would not be possible without my interns, collaborators, and Adobe colleagues! Thank you all!
Jan 2022 - I hosted a panel discussion with Adobe Researchers on how to work with interns and what makes for a great internship.
Watch it here!
Oct 2021 - Our GPU Snooping paper was accepted to USENIX 2022! Congrats, Henrique!
Place a simple EM sensor next to your GPU and we can identify which pytorch model you are running!
Feb 2021 - I am invited to give a talk on audiovisual for accessibility at Dartmouth College.
Thanks Prof. Bo Zhu!
Dec 2020 - 🎉 Our latest work on making videos accessible has been conditionally accepted to CHI 2021! 🎉
Congrats to Yujia 👩🏻🎓 and my collaborators! More details coming soon!
Nov 2020 - I am invited as an panelist to discuss the future of audiovisual research at the VALSE webinar on Nov 25.
Other speakers and panelists include Di Hu, Chuang Gan, Yapeng Tian, Ruohan Gao, and Hang Zhou. 欢迎大家届时参加。
Oct 2020 - My two-time summer intern, Yang Zhou, did a fantastic job presenting our latest work -- Project On the Beat.
An AI-powered music video editing tool for synchronizing body movements to beats.
Sept 2020 - At Adobe Video World, I shared our latest public beta release of Speech-Aware Animation in Character Animator.
Check this release note for more details.
Aug 2020 - I give an invited talk at ECCV 2020 Multi-Modal Video Analysis Workshop
The talk covers our recent work on audio-driven animation from a single image and weakly supervised audiovisual video parsing. Watch the recording here.
Aug 2020 - MakeItTalk is conditionally accepted to SIGGRAPH Asia 2020!
In this work, we develop a method to generate talking head video with an audio clip and a single image. Watch the video in the publication list. Congrats, Yang!
July 2020 - Audio-Visual Video Parsing Accepted to ECCV 2020 Spotlight
Our work on using weak labels to parse audiovisual events from videos is accepted to ECCV 2020. More info to come. Congrats, Yapeng!
June 2020 - CVPR 2020 Sight and Sound Workshop
Yapeng presented his intern projects on Deep Audio Prior and Audio-Visual Video Parsing. See more details here.
April 2020 — Internship/Collaboration Going Virtual during COVID-19
Due to COVID-19, research internships and collaborations are either postponed or only happening virtually for 2019. Stay safe!
Feb 2020 - Eurographics 2020
I am serving on the International Program Committee (IPC) of the Eurographics 2020. This year the event will be held in Norrköping, Sweden virtually.
January 2020 — I am promoted to Research Scientist 2!
Thanks to my wonderful collaborators and colleagues!
Dec 2019 — 3D Physics Engine Shipped in Adobe Dimension CC!
Now you can drop 3D objects in Dimension and we use physics simulation to lay the object flat on the ground. The feature is named "Drop to Ground".
Nov 2019 — Project SweetTalk is selected as an Adobe MAX Sneaks in Los Angeles.
Project SweetTalk creates dynamic videos from static images. We can animate drawings from centuries ago, random sketches, 2D cartoon characters, Japanese mangas, stylized caricatures, and casual photos. See the demo here.
Oct 2019 — Our Scene-Aware Deep Acoustic Analysis Paper is Accepted to IEEE VR/TVCG!
June 2019 — Summer Intern Season Starts!
May 2019 — LayerCode is accepted to SIGGRAPH 2019!
Feb 2019 — Immersive Audio Talk @ Adobe Global Tech Summit
I present the latest progress from Adobe Research's audio team to the largest internal event.
Feb 2019 - Physical Hyperlinks Talk @ University of Washington
Invited by Prof. Adriana Schulz, I gave a talk on Physical Hyperlinks for Personalized Fabrication, a summary of my recent work on Acoustic Voxels, AirCode, and LayerCode.
Dec 2018 - Eurographics 2019 Short Paper Program Committee
Dec 2018 — First CHI Paper on Audible Panorama is Accepted!
Aug 2018 — Scene-Aware Audio in 360 Videos Presented at SIGGRAPH