Computer Science Focus on Research - University of Houston
Skip to main content

Computer Science Focus on Research

When: Monday, November 04, 2019
Where: PGH 563
Time: 11:00 AM

Focus on Research (FoR) is an opportunity for any COSC Ph.D. student to discuss a research project (with or without preliminary results), a conference dry run, or any research topic of interest to present to an audience of peers and faculty. It is a great avenue for Ph.D. students to practice presentation skills in front of a larger and broader audience.

A Deep Learning based Model for Head and Eye Motion Generation in Three-party Conversations

Aobo Jin, Ph.D. Student


We propose a novel deep-learning based approach to generate realistic three-party head and eye motions based on novel acoustic speech input, together with speaker marking (i.e., speaking time for each interlocutor). Specifically, we first acquire a high quality, three-party conversational motion dataset. Then based on the acquired dataset, we train a deep-learning based framework to automatically predict the dynamic directions of both the eyes and heads of all the interlocutors based on speech signal input. Via the combination of existing lip-sync and speech-driven hand/body gesture generation algorithms, we can generate realistic three-party conversational animations. Through many experiments and comparative user studies, we demonstrate that our approach can generate realistic three-party head-and-eye motions based on novel speech recorded on new subjects with different genders and ethnicities.


Aobo Jin is a 4th year Ph.D. student in the Department of Computer Science, University of Houston. His research is focused on computer graphics, animation, sketch-based modeling and machine learning, which is supervised by Dr. Zhigang Deng.

Visual Summarization of Lecture Videos

Mohammad Rajiur Rahman, Ph.D. Student


VideoPoints improves access to lecture videos by creating topical segments and searchable indexes from extracted texts. Lecture videos also contain visual contents like images, charts, and diagrams, etc. We postulate visual summarization of lecture videos would help learners easily navigate to a topic of interest. We want to design a summarization technique which extracts unique and important visual contents from the lecture video or video segment, and places them in a single frame.


Mohammad Rajiur Rahman is a 4th year Ph.D. student in the Department of Computer Science, University of Houston. His research is focused on visual content analysis of lecture videos, which is supervised by Dr. Jaspal Subhlok and Dr. Shishir Shah.