Visual Reasoning
State-of-the-art leaderboards
Greatest papers with code
Compositional Attention Networks for Machine Reasoning
ICLR 2018
• stanfordnlp/mac-network
• 
We present the MAC network, a novel fully differentiable neural network architecture, designed to facilitate explicit and expressive reasoning.
FiLM: Visual Reasoning with a General Conditioning Layer
We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation.
Inferring and Executing Programs for Visual Reasoning
Existing methods for visual reasoning attempt to directly map inputs to outputs using black-box architectures without explicitly modeling the underlying reasoning processes.
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover shortcomings.
QUESTION ANSWERING VISUAL QUESTION ANSWERING VISUAL REASONING
Object Level Visual Reasoning in Videos
ECCV 2018
• fabienbaradel/object_level_visual_reasoning
• 
Human activity recognition is typically addressed by detecting key concepts like global and local motion, features related to object classes present in the scene, as well as features related to the global context.
HUMAN ACTIVITY RECOGNITION OBJECT DETECTION VISUAL REASONING
A Dataset and Architecture for Visual Reasoning with a Working Memory
ECCV 2018
• google/cog
•
COG is much simpler than the general problem of video analysis, yet it addresses many of the problems relating to visual and logical reasoning and memory -- problems that remain challenging for modern deep learning architectures.
Explainable and Explicit Visual Reasoning over Scene Graphs
• shijx12/XNM-Net
•
We aim to dismantle the prevalent black-box neural architectures used in complex visual reasoning tasks, into the proposed eXplainable and eXplicit Neural Modules (XNMs), which advance beyond existing neural module networks towards using scene graphs --- objects as nodes and the pairwise relationships as edges --- for explainable and explicit reasoning with structured knowledge.
FigureQA: An Annotated Figure Dataset for Visual Reasoning
ICLR 2018
• vmichals/FigureQA-baseline
•
To resolve, such questions often require reference to multiple plot elements and synthesis of information distributed spatially throughout a figure.
Mapping Natural Language Commands to Web Elements
EMNLP 2018
• stanfordnlp/phrasenode
•
The web provides a rich, open-domain environment with textual, structural, and spatial properties.
Visual Reasoning by Progressive Module Networks
ICLR 2019
• seung-kim/pmn_demo
•
Thus, a module for a new task learns to query existing modules and composes their outputs in order to produce its own output.