DeepAI AI Chat
Log In Sign Up

Towards ontology driven learning of visual concept detectors

by   Sanchit Arora, et al.
Dextro, Inc

The maturity of deep learning techniques has led in recent years to a breakthrough in object recognition in visual media. While for some specific benchmarks, neural techniques seem to match if not outperform human judgement, challenges are still open for detecting arbitrary concepts in arbitrary videos. In this paper, we propose a system that combines neural techniques, a large scale visual concepts ontology, and an active learning loop, to provide on the fly model learning of arbitrary concepts. We give an overview of the system as a whole, and focus on the central role of the ontology for guiding and bootstrapping the learning of new concepts, improving the recall of concept detection, and, on the user end, providing semantic search on a library of annotated videos.


page 1

page 2

page 3

page 4


EventNet: A Large Scale Structured Concept Library for Complex Event Detection in Video

Event-specific concepts are the semantic concepts designed for the event...

Classifying concepts via visual properties

We assume that substances in the world are represented by two types of c...

JSI at the FinSim-2 task: Ontology-Augmented Financial Concept Classification

Ontologies are increasingly used for machine reasoning over the last few...

Human-in-the-loop Extraction of Interpretable Concepts in Deep Learning Models

The interpretation of deep neural networks (DNNs) has become a key topic...

Machine Learning Techniques with Ontology for Subjective Answer Evaluation

Computerized Evaluation of English Essays is performed using Machine lea...

Automatic Ontology Learning from Domain-Specific Short Unstructured Text Data

Ontology learning is a critical task in industry, dealing with identifyi...

Visual Affect Around the World: A Large-scale Multilingual Visual Sentiment Ontology

Every culture and language is unique. Our work expressly focuses on the ...