Visual Relationship Detection with Language Priors

07/31/2016
by   Cewu Lu, et al.
0

Visual relationships capture a wide variety of interactions between pairs of objects in images (e.g. "man riding bicycle" and "man pushing bicycle"). Consequently, the set of possible relationships is extremely large and it is difficult to obtain sufficient training examples for all possible relationships. Because of this limitation, previous work on visual relationship detection has concentrated on predicting only a handful of relationships. Though most relationships are infrequent, their objects (e.g. "man" and "bicycle") and predicates (e.g. "riding" and "pushing") independently occur more frequently. We propose a model that uses this insight to train visual models for objects and predicates individually and later combines them together to predict multiple relationships per image. We improve on prior work by leveraging language priors from semantic word embeddings to finetune the likelihood of a predicted relationship. Our model can scale to predict thousands of types of relationships from a few examples. Additionally, we localize the objects in the predicted relationships as bounding boxes in the image. We further demonstrate that understanding relationships can improve content based image retrieval.

READ FULL TEXT

page 2

page 3

page 4

page 9

page 12

page 14

research
11/16/2017

Natural Language Guided Visual Relationship Detection

Reasoning about the relationships between object pairs in images is a cr...
research
12/10/2020

Tensor Composition Net for Visual Relationship Prediction

We present a novel Tensor Composition Network (TCN) to predict visual re...
research
05/03/2020

On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs

We use large-scale corpora in six different gendered languages, along wi...
research
06/13/2022

Stable Relationships

We study a dynamic model of the relationship between two people where th...
research
08/27/2018

Improving Information Extraction from Images with Learned Semantic Models

Many applications require an understanding of an image that goes beyond ...
research
03/20/2019

On Class Imbalance and Background Filtering in Visual Relationship Detection

In this paper we investigate the problems of class imbalance and irrelev...
research
05/28/2018

Visual Relationship Detection Based on Guided Proposals and Semantic Knowledge Distillation

A thorough comprehension of image content demands a complex grasp of the...

Please sign up or login with your details

Forgot password? Click here to reset