Keyphrases
Neural Model
100%
Speech Signal
75%
Visually-grounded Speech
66%
Semantic Space
66%
Visual Scenes
66%
Spoken Language
66%
Visual Context
66%
Word Learning
66%
Utterance
58%
Phoneme
50%
Visual Features
50%
Computational Model
50%
Referring Expressions
50%
Recurrent Highway Networks
33%
Ground Model
33%
VISION Study
33%
Input Signals
33%
Interaction between Elements
33%
Training Model
33%
Spoken Speech
33%
Discrete Representation
33%
Audio Signal
33%
Recurrent Neural Network Model
33%
Raw Speech
33%
Speech Audio
33%
Scene Feature
33%
Adult-directed Speech
33%
Phoneme Sequence
33%
Layer Recurrent Neural Network
33%
Self-supervision
33%
Grounded Language Learning
33%
Referential Games
33%
Joint Processing
33%
Image Level
33%
Relational Representation
33%
Visual Question Answering
33%
Modeling Relation
33%
Physical World
33%
Linguistic Knowledge
33%
Recurrent Neural Network
33%
Shared Semantics
33%
Dataset Building
33%
Language Structure
33%
Neural Network Model
33%
Image Description
33%
Levels of Representation
33%
Distributional Semantics
33%
Meaning Representation
33%
Word Meaning
33%
Speech Data
33%
Computer Science
Spoken Language
66%
Language Learner
53%
Visual Feature
33%
Word Expression
33%
Visual Question Answering
33%
Relational Representation
33%
Neural Network Model
33%
Dialog History
33%
Directed Speech
33%
Physical World
33%
Shared Information
33%
Collaborative Game
33%
Visual Informations
33%
Baseline Model
33%
Formalization
33%
Random Selection
33%
Language Development
33%
Computer Vision
33%
Recurrent Layer
33%
Vector Quantization
33%
Language Input
33%
Human Language
20%
Recurrent Neural Network
16%
Network Architecture
16%
Computational Modeling
16%
Unsupervised Learning
16%
Semantic Representation
16%
Gated Recurrent Unit Network
16%
Discretization Layer
16%
Neural Representation
16%
Neural Network
16%
Language Semantics
8%
Written Language
8%
Varying Degree
8%
Speech Processing
8%
Task Performance
7%
