Schedule

May 5
Reception and poster session will take place at 6-8 PM at the Singh Center, 3205 Walnut St, Philadelphia, PA 19104.

May 6
08:30 breakfast and registration  
09:00 George Pavlakos Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
09:15 Arijit Ray Guess What? The Visual 20 Questions Game
09:30 Tejas Khot Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
09:45 Yuxiong Wang Growing a Brain: Fine-Tuning by Increasing Model Capacity
10:00 Rahul Mangharam APEX: Autonomous Vehicle Plan Verification and Execution
10:15 Arsalan Mousavian 3D Bounding Box Estimation Using Deep Learning and Geometry
10:30 break  
10:45 Aleksandrs Ecins Detecting Symmetric Objects in 3D Pointclouds
11:00 Chong You Provable Self-Representation Based Outlier Detection in a Union of Subspaces
11:15 Soumyadip Sengupta A New Rank Constraint on Multi-view Fundamental Matrices, and its Application to Camera Location Recovery
11:30 Hang Zhang Deep TEN: Texture Encoding Network
11:45 Gabriel Schwartz Local Materials and Global Context
12:00 lunch + poster session  
   
13:30 Jonas Cleveland, CEO, COSY COSY (Cognitive Operational Systems, Inc.)
13:45 Shan Su Predicting Behaviors of Basketball Players from First Person Videos
14:00 Vishwanath Sindagi Exploiting Context for Crowd Counting in Unconstrained Images
14:15 Joe Yue-Hei Ng ActionFlowNet: Learning Motion Representation for Action Recognition
14:30 Tae Soo Kim Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
14:45  Weichao Qiu  UnrealCV: Connecting Computer Vision to Unreal Engine
15:00 coffee break

15:30 Xiang Xiang Regularizing Face Verification Nets To Discrete-Valued Pain Regression
15:45 Rajeev Ranjan An All-In-One Convolutional Neural Network for Face Analysis
16:00 Wei Shen DeepSkeleton: Object Skeleton Extraction in Natural Images by Learning Scale-associated Deep Side Outputs
16:15 Jin Sun Seeing What Is Not There: Learning Context to Determine Where Objects Are Missing
16:30 Pramuditha Perera CNNs for One-class Learning Problems
16:45 Abhinav Shrivastava Top-down Mechanisms for Object Detection