ML p(r)ior | Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects

Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects

2016-02-02
Human vision greatly benefits from the information about sizes of objects. The role of size in several visual reasoning tasks has been thoroughly explored in human perception and cognition. However, the impact of the information about sizes of objects is yet to be determined in AI. We postulate that this is mainly attributed to the lack of a comprehensive repository of size information. In this paper, we introduce a method to automatically infer object sizes, leveraging visual and textual information from web. By maximizing the joint likelihood of textual and visual observations, our method learns reliable relative size estimates, with no explicit human supervision. We introduce the relative size dataset and show that our method outperforms competitive textual and visual baselines in reasoning about size comparisons.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2016-11-28

This paper focuses on semantic scene completion, a task for producing a complete 3D voxel representa… show more
PDF

Highlights - Most important sentences from the article

2016-12-20

When building artificial intelligence systems that can reason and answer questions about visual data… show more
PDF

Highlights - Most important sentences from the article

2017-11-17

We investigate the problem of producing structured graph representations of visual scenes. Our work … show more
PDF

Highlights - Most important sentences from the article

2018-12-05
1812.01855 | cs.CV

We aim to dismantle the prevalent black-box neural architectures used in complex visual reasoning ta… show more
PDF

Highlights - Most important sentences from the article

2018-08-28

Cross-sentence $n$-ary relation extraction detects relations among $n$ entities across multiple sent… show more
PDF

Highlights - Most important sentences from the article

2016-02-19

We consider the problem of model-based 3D-tracking of objects given dense depth images as input. Two… show more
PDF

Highlights - Most important sentences from the article

2017-01-10

Understanding a visual scene goes beyond recognizing individual objects in isolation. Relationships … show more
PDF

Highlights - Most important sentences from the article

2019-02-21

With the rapid development of fashion market, the customers' demands of customers for fashion recomm… show more
PDF

Highlights - Most important sentences from the article

2016-12-19

In this paper, we propose a novel approach for exploiting structural relations to track multiple obj… show more
PDF

Highlights - Most important sentences from the article

2018-02-15

Visual Question Answering (VQA) models have struggled with counting objects in natural images so far… show more
PDF

Highlights - Most important sentences from the article

2018-06-29

Generating scene graph to describe all the relations inside an image gains increasing interests thes… show more
PDF

Highlights - Most important sentences from the article

2018-03-21
1803.08035 | cs.CV

We consider the problem of zero-shot recognition: learning a visual classifier for a category with z… show more
PDF

Highlights - Most important sentences from the article

2018-06-19

Visual Question answering is a challenging problem requiring a combination of concepts from Computer… show more
PDF

Highlights - Most important sentences from the article

2017-07-31

Object detection, scene graph generation and region captioning, which are three scene understanding … show more
PDF

Highlights - Most important sentences from the article

2019-04-11

We propose a novel model to address the task of Visual Dialog which exhibits complex dialog structur… show more
PDF

Highlights - Most important sentences from the article