Minds vs. Machines: How far are we from the common sense of a toddler?

CVPR 2020 Workshop, June 15, Seattle, WA


The following papers were accepted for publication in the workshop proceedings. Please join the poster session, 12:25 - 13:00 PST and 14:20 - 15:20 PST on June 15, by clicking on any of the zoom links at that time.

Title Authors Zoom link (for poster session) PDF

Learning to Learn Words from Visual Scenes

Dídac Surís, Dave Epstein, Heng Ji, Shih-Fu Chang, and Carl Vondrick ZOOM PDF

Oops! Predicting Unintentional Action in Video

Dave Epstein, Boyuan Chen, and Carl Vondrick ZOOM PDF

Learning Intuitive Physics by Explaining Surprise

Hung Nguyen, Jay S Patravali, Fuxin Li, and Alan Fern ZOOM PDF

Story Completion with Explicit Modeling of Commonsense Knowledge

Mingda Zhang, Keren Ye, Rebecca Hwa, and Adriana Kovashka ZOOM PDF

Visual Commonsense Representation Learning via Causal Inference

Tan Wang, Jianqiang Huang, Hanwang Zhang, and Qianru Sun ZOOM PDF

SomethingFinder: Localizing undefined regions using referring expressions

Sungmin Eum, David Han, and Gordon Briggs ZOOM (password "cvpr") PDF

Response Time Analysis for Explainability of Visual Processing in CNNs

Eric Taylor, Shashank Shekhar, and Graham Taylor https://cmu.zoom.us/j/95909508673 PDF

Hierarchical Color Learning in Convolutional Neural Networks

Chris Hickey, and Byoung-Tak Zhang ZOOM (password cvpr) PDF

Understanding Knowledge Gaps in Visual Question Answering: Implications for Gap Identification and Testing

Goonmeet Bajaj, Bortik Bandyopadhyay, Daniel Schmidt, Pranav Maneriker, Christopher Myers, and Srinivasan Parthasarathy ZOOM PDF

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quantized Neural Scene Representations

Mihir Prabhudesai, Shamit Lal, Hsiao-Yu Tung, Adam Harley, Shubankar Potdar, and Katerina Fragkiadaki ZOOM PDF