Automated Image Captioning for Rapid Prototyping and Resource Constrained Environments

TL;DR

This paper proposes a scalable, resource-efficient approach to automated image captioning that leverages top object detection and word embeddings to infer actions, suitable for resource-constrained environments.

Contribution

It introduces a novel insight that detecting key objects enables relevant captioning and action inference, emphasizing simplicity and scalability in image captioning systems.

Findings

Effective action prediction using object detection and word embeddings

Achieved reasonable captioning performance with low complexity

Reduced system development time and resource requirements

Abstract

Significant performance gains in deep learning coupled with the exponential growth of image and video data on the Internet have resulted in the recent emergence of automated image captioning systems. Ensuring scalability of automated image captioning systems with respect to the ever increasing volume of image and video data is a significant challenge. This paper provides a valuable insight in that the detection of a few significant (top) objects in an image allows one to extract other relevant information such as actions (verbs) in the image. We expect this insight to be useful in the design of scalable image captioning systems. We address two parameters by which the scalability of image captioning systems could be quantified, i.e., the traditional algorithmic time complexity which is important given the resource limitations of the user device and the system development time since the programmers' time is a critical resource constraint in many real-world scenarios. Additionally, we address the issue of how word embeddings could be used to infer the verb (action) from the nouns (objects) in a given image in a zero-shot manner. Our results show that it is possible to attain reasonably good performance on predicting actions and captioning images using our approaches with the added advantage of simplicity of implementation.