Abstract Evaluation metrics for image captioning face two challenges. Firstly, commonly used metrics such as CIDEr, METEOR, ROUGE and BLEU often do not correlate well with …
R Luo, B Price, S Cohen… - Proceedings of the …, 2018 - openaccess.thecvf.com
One property that remains lacking in image captions generated by contemporary methods is discriminability: being able to tell two images apart given the caption for one of them. We …
We explore a variety of nearest neighbor baseline approaches for image captioning. These approaches find a set of nearest neighbor images in the training set from which a caption …
Q Wang, AB Chan - … of the IEEE/CVF Conference on …, 2019 - openaccess.thecvf.com
Recently, the state-of-the-art models for image captioning have overtaken human performance based on the most popular metrics, such as BLEU, METEOR, ROUGE and …
Image captioning is a challenging problem owing to the complexity in understanding the image content and diverse ways of describing it in natural language. Recent advances in …
K Tran, X He, L Zhang, J Sun, C Carapcea… - Proceedings of the …, 2016 - cv-foundation.org
We present an image caption system that addresses new challenges of automatically describing images in the wild. The challenges include generating high quality caption with …
Automatically describing an image with a natural language has been an emerging challenge in both fields of computer vision and natural language processing. In this paper …
Two recent approaches have achieved state-of-the-art results in image captioning. The first uses a pipelined process where a set of candidate words is generated by a convolutional …
C Chunseong Park, B Kim… - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
We address personalization issues of image captioning, which have not been discussed yet in previous research. For a query image, we aim to generate a descriptive sentence …