Все публикации

0:05:00

Learning to Learn Words from Visual Scenes | MvM@CVPR20 Spotlight

0:05:00

Oops! Predicting Unintentional Action in Video | MvM@CVPR20 Spotlight

0:04:58

Story Completion with Explicit Modeling of Commonsense Knowledge | MvM@CVPR20 Spotlight

0:04:33

Learning Intuitive Physics by Explaining Surprise | MvM@CVPR20 Spotlight

0:04:49

Visual Commonsense Representation Learning via Causal Inference | MvM@CVPR20 Spotlight

0:04:55

SomethingFinder: Localizing undefined regions using referring expressions | MvM@CVPR20 Spotlight

0:04:56

Hierarchical Color Learning in Convolutional Neural Networks | MvM@CVPR20 Spotlight

0:06:42

3DQ-Nets: Visual Concepts Emerge in Pose-Equivariant 3D Representations | MvM@CVPR20 Spotlight

0:05:19

Understanding Knowledge Gaps in Visual Question Answering | MvM@CVPR20 Spotlight

1:07:58

Panel: Spelke, Oliva, Yurovsky, Tenenbuam, Smith, Olshausen, Zitnick, Gopnik, Malik | MvM@CVPR20

0:38:33

Alison Gopnik | Children are MESSes: Model Building Exploratory Social Learning Systems | MvM@CVPR20

0:38:18

Jitendra Malik | Turing's Baby | MvM@CVPR20

0:47:14

Bruno Olshausen | How far are we from the common sense of a jumping spider? | MvM@CVPR20

0:39:33

Larry Zitnick | What is the right question to ask? | MvM@CVPR2020

0:47:05

Linda Smith | Common sense and the visual experiences of toddlers | MvM@CVPR20

0:12:32

Response Time Analysis for Explainability of Visual Processing | MvM@CVPR20 Oral

0:12:08

Visual Commonsense Representation Learning via Causal Inference | MvM@CVPR20 Oral

0:12:43

Learning to Learn Words from Visual Scenes | MvM@CVPR20 Oral

0:41:42

Dan Yurovsky | Toddlers' common sense operates in socially-supported contexts | MvM@CVPR20

0:52:00

Josh Tenenbaum | Reverse-engineering core common sense | MvM@CVPR20

0:35:03

Aude Oliva | Cognitive Insights for Models of Visual Recognition | MvM@CVPR20

0:50:19

Elizabeth Spelke | What infants know (and don't know) | MvM@CVPR20

0:04:11

Minds vs. Machines | Opening Remarks | MvM@CVPR20