Zero-shot object prediction using semantic scene knowledge

04/27/2016
by   Rene Grzeszick, et al.
0

This work focuses on the semantic relations between scenes and objects for visual object recognition. Semantic knowledge can be a powerful source of information especially in scenarios with few or no annotated training samples. These scenarios are referred to as zero-shot or few-shot recognition and often build on visual attributes. Here, instead of relying on various visual attributes, a more direct way is pursued: after recognizing the scene that is depicted in an image, semantic relations between scenes and objects are used for predicting the presence of objects in an unsupervised manner. Most importantly, relations between scenes and objects can easily be obtained from external sources such as large scale text corpora from the web and, therefore, do not require tremendous manual labeling efforts. It will be shown that in cluttered scenes, where visual recognition is difficult, scene knowledge is an important cue for predicting objects.

READ FULL TEXT
research
10/26/2021

Zero-Shot Action Recognition from Diverse Object-Scene Compositions

This paper investigates the problem of zero-shot action recognition, in ...
research
04/25/2016

Modeling the Contribution of Central Versus Peripheral Vision in Scene, Object, and Face Recognition

It is commonly believed that the central visual field is important for r...
research
07/18/2018

Finding any Waldo: zero-shot invariant and efficient visual search

Searching for a target object in a cluttered scene constitutes a fundame...
research
08/19/2022

Background Invariance Testing According to Semantic Proximity

In many applications, machine learned (ML) models are required to hold s...
research
01/25/2023

Implicit Shape Model Trees: Recognition of 3-D Indoor Scenes and Prediction of Object Poses for Mobile Robots

For a mobile robot, we present an approach to recognize scenes in arrang...
research
11/05/2020

Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games

In visual guessing games, a Guesser has to identify a target object in a...
research
05/22/2023

Zero-shot Multi-level Feature Transmission Policy Powered by Semantic Knowledge Base

Remote zero-shot object recognition, i.e., offloading zero-shot object r...

Please sign up or login with your details

Forgot password? Click here to reset