Browse > Reasoning > Visual Reasoning

Visual Reasoning

20 papers with code ยท Reasoning

State-of-the-art leaderboards

Latest papers without code

Reasoning-Aware Graph Convolutional Network for Visual Question Answering

ICLR 2020

Relational reasoning methods based on graph networks are currently state-of-the-art models for Visual Question Answering (VQA) tasks involving real images.

QUESTION ANSWERING RELATIONAL REASONING VISUAL QUESTION ANSWERING VISUAL REASONING

Abstract Diagrammatic Reasoning with Multiplex Graph Networks

ICLR 2020

We have tested MXGNet on two types of diagrammatic reasoning tasks, namely Diagram Syllogisms and Raven Progressive Matrices (RPM).

GRAPH NEURAL NETWORK VISUAL REASONING

Modulated Self-attention Convolutional Network for VQA

8 Oct 2019

As new data-sets for real-world visual reasoning and compositional question answering are emerging, it might be needed to use the visual feature extraction as a end-to-end process during training.

QUESTION ANSWERING VISUAL QUESTION ANSWERING VISUAL REASONING

Meta Module Network for Compositional Visual Reasoning

8 Oct 2019

There are two main lines of research on visual reasoning: neural module network (NMN) with \emph{explicit} multi-hop reasoning through handcrafted neural modules, and monolithic network with \emph{implicit} reasoning in the latent feature space.

VISUAL REASONING

Few-Shot Abstract Visual Reasoning With Spectral Features

4 Oct 2019

We present an image preprocessing technique capable of improving the performance of few-shot classifiers on abstract visual reasoning tasks.

FEW-SHOT LEARNING VISUAL REASONING

CLEVRER: CoLlision Events for Video REpresentation and Reasoning

3 Oct 2019

While these models thrive on the perception-based task (descriptive), they perform poorly on the causal tasks (explanatory, predictive and counterfactual), suggesting that a principled approach for causal reasoning should incorporate the capability of both perceiving complex visual and language inputs, and understanding the underlying dynamics and causal relations.

VISUAL REASONING

Highlighting Bias with Explainable Neural-Symbolic Visual Reasoning

19 Sep 2019

Many high-performance models suffer from a lack of interpretability.

IMAGE CAPTIONING VISUAL REASONING

Procedural Reasoning Networks for Understanding Multimodal Procedures

19 Sep 2019

Our model learns to dynamically update entity states in relation to each other while reading the text instructions.

VISUAL REASONING

Dynamic Graph Attention for Referring Expression Comprehension

18 Sep 2019

In this paper, we explore the problem of referring expression comprehension from the perspective of language-driven visual reasoning, and propose a dynamic graph attention network to perform multi-step reasoning by modeling both the relationships among the objects in the image and the linguistic structure of the expression.

VISUAL REASONING

V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices

29 Jul 2019

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced.

VISUAL REASONING