Skip to main content

Archived Events

ENG2 202A,
HEC 103, 4328 Scorpius Street
Orlando, FL 32816 United States
+ Google Map

Coupled-Instances Domain Adaptation for Cross-Spectrum Face Recognition

Speaker: Joel Douglas From: Systems & Technology Research Abstract State-of-the-art performance for object detection, object classification and activity recognition requires curation of large datasets which are necessary to make deep networks with tens of millions of parameters able to generalize. However, data of this scale is not available for many applications, especially in the infrared […]

Find out more »
HEC 101, 4328 Scorpius Street, HEC 245F
Orlando, FL 32816 United States
+ Google Map

VoxelMorph: Unsupervised learning for fast probabilistic diffeomorphic registration

Speaker: Mert R. Sabuncu From: Cornell University Abstract In this talk, I will present VoxelMorph - a fast learning-based framework for deformable, pairwise image registration. Traditional registration methods optimize an objective function for each pair of images, which can be time-consuming for large datasets and/or with rich deformation models. In contrast to this approach, and building on recent learning-based methods, we […]

Find out more »
HEC 101, 4328 Scorpius Street, HEC 245F
Orlando, FL 32816 United States
+ Google Map

A Navigational Approach to Health

Speaker: Ramesh Jain From: Institute for Future Health, Department of Computer Science, University of California Abstract What if an app could guide you to better health, similar to how GPS navigation directs you to your desired destination?   Advances in sensors, mobile computing, artificial intelligence, data management, cloud computing, biology, and medicine allow approaching human health […]

Find out more »
Research I – 101, 4353 Scorpius Street
Orlando, FL 32816 United States
+ Google Map

What can be derived from an instance?

Speaker: Arnold Smeulders From: Unviersity of Amsterdam Abstract: In the end, computer vision learning is built from instances. When picture costs are low, much lower than documenting an instance, it pays to get the most out of each instance. Where searching for an instance in a large database is a relevant and hard problem by […]

Find out more »
HEC 101, 4328 Scorpius Street, HEC 245F
Orlando, FL 32816 United States
+ Google Map

Recent Advances in Algorithms for Automatic Target Detection and Recognition

Speaker: Dr. Abhijit Mahalanobis From: Lockheed Martin Corporation Abstract: The problem of detecting and recognizing targets continues to be substantial interest to the DoD community for tactical and surveillance imaging systems. Although many techniques have been developed over the years, challenges remain due to the limited number of pixels on targets (POT), lack of training […]

Find out more »
HEC 101, 4328 Scorpius Street, HEC 245F
Orlando, FL 32816 United States
+ Google Map

Fun Research in Computer Vision and Robotics

Speaker: Dr. Takeo Kanade From: Carnegie Mellon University Abstratct: In this talk, I would like to touch upon highlights of various research and development in which I was involved in the area of computer vision and robotics. A few candidates for topics that I will cover include face image analysis, vision-based autonomous robots, EyeVision, biological […]

Find out more »
HEC 101, 4328 Scorpius Street, HEC 245F
Orlando, FL 32816 United States
+ Google Map

Vision, Brain, Computation and Attention: What You Really Need to Know

Speaker: Dr. John Tsotsos From: York University Abstract: The Selective Tuning model for vision and attention, under development since 1987, started life as a model of some aspects of visual attention in humans that might have utility in machine vision, especially as it applies to how algorithms deal with the combinatorics of visual processing. It […]

Find out more »
HEC 101, 4328 Scorpius Street, HEC 245F
Orlando, FL 32816 United States
+ Google Map

Two Routes for Image-to-Image Translation: Rule-based vs. Learning-based

Speaker: Minglun Gong From: Memorial University of Newfoundland Abstract: Many image processing and computer vision tasks, such as image segmentation, stylization, and abstraction, can be posed as image-to-image translation problems. This talk presents two different image-to-image translation approaches, one is rule-base and the other is learning-based. The rule-based algorithm is capable of stylizing an input […]

Find out more »

Déjà Vécu: Learning from Legacy MoCap Data for Robust Human Action Recognition

Speaker: Ajmal Mian From: University of Western Australia Abstract: Annotating human action videos is tedious and expensive. We bypass this step and capitalize on legacy motion capture (MoCap) data to synthesize video frames. The MoCap data is fitted with synthetic 3D humans with varying sizes, gender and clothing, placed in random backgrounds and rendered from […]

Find out more »
HEC 101, 4328 Scorpius Street, HEC 245F
Orlando, FL 32816 United States
+ Google Map

3D-Centric Data-Driven Visual Computing

Speaker: Qixing Huang From: University of Texas Abstract: Over the past decade, the quantity of accessible visual data has undergone unprecedented expansion. This data is not only vast but also exists within numerous modalities such as images, videos, and 3D models. While researchers have aptly exploited the inflation of these first two areas, the significant growth […]

Find out more »
HEC 101, 4328 Scorpius Street, HEC 245F
Orlando, FL 32816 United States
+ Google Map
HEC 101, 4328 Scorpius Street, HEC 245F
Orlando, FL 32816 United States
+ Google Map