Monday, November 26, 2018
09:00-10:00
|
Breakfast, sign-in, poster setup
|
|
10:00-10:15
|
Welcome and introduction
|
|
10:15-12:00
|
Oral presentations
|
-
The Sound of Pixels,
Hang Zhao (MIT)
-
Improving Shape Deformation in Unsupervised Image-to-Image
Translation, Aaron Gokaslan (Brown)
-
Top-Down Spatiotemporal Saliency for Visual Grounding,
Sarah Adel Bargal (Boston Univ)
-
Cross-View Action Recognition via Joint Dictionary and Transfer
Learning, Deepak Kumar (UMass Dartmouth)
-
Neural-Symbolic VQA: Disentangling Reasoning from Vision
and Language Understanding, Kexin Yi (Harvard)
-
Geodesic Flow,
Berk Sevilmis (Brown)
-
Seeing through Realistic Fog,
Guy Satat (MIT)
|
12:00-01:00
|
Lunch
|
|
01:00-03:00
|
Poster presentations
|
|
03:00-05:30
|
Oral presentations
|
-
Simultaneous Extraction of 3D Neuronal Structures by Detection
and Tracking, Felix Gonda (Harvard)
-
Iterative Segmentation from Limited Training Data: Applications
to Congenital Heart Disease, Danielle Pace (MIT)
-
DYAN: A Dynamical Atoms-Based Network For Video Prediction,
Wenqian Liu (Northeastern)
-
A Unified Framework of DNN Weight Pruning and Weight
Clustering/Quantization Using ADMM, Tianyun Zhang (Syracuse/Northeastern)
-
MaskConnect: Connectivity Learning by Gradient Descent,
Karim Ahmed (Dartmouth)
-
CSGNet: Neural Shape Parser for Constructive Solid Geometry,
Gopal Sharma (UMass Amherst)
-
Toward Driving Scene Understanding: A Dataset for Learning
Driver Behavior and Causal Reasoning, Vasili Ramanishka (Boston Univ)
|