Areas of Attention for Image Captioning

12/03/2016
by   Marco Pedersoli, et al.
0

We propose "Areas of Attention", a novel attention-based model for automatic image captioning. Our approach models the dependencies between image regions, caption words, and the state of an RNN language model, using three pairwise interactions. In contrast to previous attention-based approaches that associate image regions only to the RNN state, our method allows a direct association between caption words and image regions. During training these associations are inferred from image-level captions, akin to weakly-supervised object detector training. These associations help to improve captioning by localizing the corresponding regions during testing. We also propose and compare different ways of generating attention areas: CNN activation grids, object proposals, and spatial transformers nets applied in a convolutional fashion. Spatial transformers give the best results. They allow for image specific attention areas, and can be trained jointly with the rest of the network. Our attention mechanism and spatial transformer attention areas together yield state-of-the-art results on the MSCOCO dataset.o meaningful latent semantic structure in the generated captions.

READ FULL TEXT

page 1

page 7

research
09/11/2021

Bornon: Bengali Image Captioning with Transformer-based Deep learning approach

Image captioning using Encoder-Decoder based approach where CNN is used ...
research
11/22/2019

Learning to Caption Images with Two-Stream Attention and Sentence Auto-Encoder

Automatically generating natural language descriptions from an image is ...
research
10/19/2022

Prophet Attention: Predicting Attention with Future Attention for Improved Image Captioning

Recently, attention based models have been used extensively in many sequ...
research
05/07/2015

Language Models for Image Captioning: The Quirks and What Works

Two recent approaches have achieved state-of-the-art results in image ca...
research
08/02/2021

Distributed Attention for Grounded Image Captioning

We study the problem of weakly supervised grounded image captioning. Tha...
research
09/18/2023

Collaborative Three-Stream Transformers for Video Captioning

As the most critical components in a sentence, subject, predicate and ob...
research
09/16/2021

Label-Attention Transformer with Geometrically Coherent Objects for Image Captioning

Automatic transcription of scene understanding in images and videos is a...

Please sign up or login with your details

Forgot password? Click here to reset