Computer Vision and Multimodal Computing Reading Group

We read and discuss papers in the areas of (1) diffusion models (2) digatal avatars (3) multimodal perception+robotics (4) computer vision for social interaction (5) implicit neural representations (6) other areas related to our research. If you would like to join this group, please send email to: yapeng dot tian at utdallas dot edu.

Regular Meeting Time & Place

• The Computer Vision and Multimodal Computing Reading Group will meet in ECSS 4.910 Alan Turing conference room, 15:00-17:00 on every Thursday.  

Scheduled Meetings

Date	Agenda
03/23/2023	Shijian Deng: PaLM-E: An embodied multimodal language model
03/30/2023	Yulang Wu: What are Diffusion Models?
04/06/2023	Siva Sai Nagender Vasireddy: DiffusionDet: Diffusion Model for Object Detection Harsh Singh: Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation
04/13/2023	Shijian Deng: High-resolution image reconstruction with latent diffusion models from human brain activity
04/20/2023	Siva Sai Nagender Vasireddy: Visual Programming for Compositional Visual Reasoning Sasha Kaplan: ViperGPT: Visual Inference via Python Execution for Reasoning
04/27/2023	Harsh Singh: SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
05/04/2023	Shijian Deng: Vision Transformers are Parameter-Efficient Audio-Visual Learners
05/18/2023	Siva Sai Nagender Vasireddy: SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning
05/25/2023	Harsh Singh: Image as Set of Points
06/01/2023	Saksham Singh Kushwaha: Dataset Condensation with Distribution Matching
06/08/2023	Shijian Deng: ImageBind: One Embedding Space To Bind Them All
06/15/2023	Siva Sai Nagender Vasireddy: Audio Visual Language Maps for Robot Navigation
06/22/2023	Sisi Aarukapalli: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
07/13/2023	Siva Sai Nagender Vasireddy: Semantic Audio-Visual Navigation
07/20/2023	Harsh Singh: Self-Supervised Video Forensics by Audio-Visual Anomaly Detection
07/27/2023	Shijian Deng: Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
08/03/2023	Akshay Vyas: ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution
TBD	The paper reading has been postponed until CVPR.

Current Participants

Prof. Yapeng Tian
Siva Sai Nagender Vasireddy, PhD Student
Shijian Deng, PhD Student
Saksham Singh Kushwaha, PhD Student
Weiguo Pian, PhD Student
Akshay Vyas, PhD Student
Zongyang Du, PhD Student
Sasha Kaplan, Undergraduate student
Sisi Aarukapalli, Undergraduate student

Past Participants