• Interactive Poisson Blending on GPU
    Interactive Poisson Blending on GPU
  • 404 Not Found In Two Triangles
    404 Not Found In Two Triangles
  • Simplest and Fastest GLSL Edge Detection using Fwidth
    Simplest and Fastest GLSL Edge Detection using Fwidth

Category: Talks

Lessons learnt from VRSurus: A Tangible Virtual Reality Game Project

Lessons learnt from a live demo of VRSurus at UIST 2015. Introduction: We introduce VRSurus, a tangible serious game that aims to inspire children to protect the environment in immersive virtual reality (VR). VRSurus is built upon a physical puppet and a VR head-mounted display (Oculus Rift DK2) to create “tangible virtual animatronics”. The player will…


[Summary] How to Write a Literature Review? An Introduction to Writing and Research in Graduate School.

By Office of Writing Initiatives, Graduate School Research Commons, University Libraries, UMD. Joining an Academic Conversation Move from undergraduate to graduate work is a move from discovery and consumption of knowledge to analysis, synthesis, evaluation, and production of knowledge.   Skills Needed to Write a Literature Review An awareness of the rhetorical and linguistic conventions…


[Summary] Immersed in N-Dimensions: Using the Creative Process as A Computational Framework for Unfolding Complex Systems

In this information-rich age where large amounts of both structured and unstructured data are being generated, processed, and transformed at ever increasing rates, how does one master control, working with these data as if it were intuitive and second nature? While new techniques for analyzing such “big data” are being developed based on data mining and…


Balancing Research, Teaching and Life

Here is a great slide by Prof. Emily Bneder from UW. http://faculty.washington.edu/ebender/papers/BalancingTeachingResearch2015.pdf  


[Summary] Consistent and Online Re-identification in Vision Networks

Abir Das from University of California, Riverside gave a talk on Consistent and Online Re-identification in Vision Networks on CFAR seminar.  Summary In computer vision, person re-identification is the task of identifying and monitoring people moving across a number of non-overlapping cameras. Several factors like significant changes in viewing angle, lighting, background clutter, and occlusion cause features…


PhD Defense: Historical Graph Data Management

Today Udayan Khurana presented his PhD Defense presentation on Historical Graph Data Management at 3258 A.V. Williams Building (AVW). Here is a brief overview: Abstract Over the last decade, we have witnessed an increasing interest in temporal analysis of information networks such as social networks or citation networks. Finding temporal interaction patterns, visualizing the evolution of graph properties,…


[Summary & Joke] What’s Wrong with Deep Learning? – CVPR 2015 Plenary Talk

Yann LeCun Facebook AI Research & New York University Video http://techtalks.tv/talks/whats-wrong-with-deep-learning/61639/   One of the most famous joke in Computer Vision field is that Dr. LeCun’s “controversial” paper “Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers” was rejected by CVPR but now is accepted by ICML’12. 🙂 Dr. LeCun published the reviews…


[Photo Summary] CompSciConnect Students Take Part in a 3-D Out of This World Experience in the UMIACS Augmentarium

We demoed some projects for 26 middle school girls on Wednesday, July 1st in the Augmentarium from 11AM-12PM. This is part of the Computer Science Connect Maryland Day Camp run by the CS department. @PGCTV reports on @umdcs CompSciConnect students demonstrating 3-D virtual reality games in the #UMIACS Augmentarium   #UMIACS Director Amitabh Varshney discusses virtual…


[Summary] PhD Proposal: Structured Approaches to Exploring Inter-Personal Relationships in Natural Language Text

A Ph.D. proposal talk by Snigdha Chaturvedi, who is expected to graduate in June 2016. The presentation was terrific covering relationship prediction in movies, novels and MOOCs. Time:  06.30.2015 15:00 to 16:30Location:  AVW 4424URL:  https://talks.cs.umd.edu/talks/1055 In this thesis we propose methods to model inter-personal relationships in text. Due to their inherent social nature, people continuously interact…


[Talk] Sketch-based 3D Shape Retrieval using Convolutional Neural Networks

Today in CFAR seminar, Dr. Yi Li and his student Fang Wang from Australian National University ented the work on Sketch-based 3D Shape Retrieval using Convolutional Neural Networks. Here is the paper in arXiv. Here is my summary: Yet-another-CNN-application The question for superior performance What if I don’t have 100 GPUs like Google / Facebook? What if I don’t…