paper-with-me

Papers

End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space

2018-11-01 · WS 2018 11 · Pranava Swaroop Madhyastha, Josiah Wang, Lucia Specia

We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn {}distributional similarity{'} in a multimodal feature space, by mapping a test image to similar training images in this space and generating a caption from the same space. To validate our hypothesis, we focus on the {}image{'} side of image captioning, and vary the input image representation but keep the RNN text generation model of a CNN-RNN constant. Our analysis indicates that image captioning models (i) are capable of separating structure from noisy input representations; (ii) experience virtually no significant performance loss when a high dimensional representation is compressed to a lower dimensional space; (iii) cluster images with similar visual and linguistic information together. Our experiments all point to one fact: that our distributional similarity hypothesis holds. We conclude that, regardless of the image representation, image captioning systems seem to match images and generate captions in a learned joint image-text semantic subspace.

📄 PDF Abstract BibTeX

Code (1)

sheffieldnlp/whatIC 공식 구현

Tasks

Image CaptioningText Generation

Similar Papers 제목 키워드 기반

End-to-end Image Captioning Exploits Multimodal Distributional Similarity

2018-09-11 · Pranava Madhyastha, Josiah Wang, Lucia Specia

We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn `distributional similarity' in a multimodal feature space by mapping a test image to similar training imag…

Image CaptioningText Generation

What is image captioning made of?

2018-01-01 · ICLR 2018 1 · Pranava Madhyastha, Josiah Wang, Lucia Specia

We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn ‘distributional similarity’ in a multimodal feature space, by mapping a test image to similar training ima…

Image CaptioningText Generation

Captioning Images with Diverse Objects

2016-06-24 · CVPR 2017 7 · Subhashini Venugopalan, Lisa Anne Hendricks, Marcus Rohrbach, Raymond Mooney 외

Recent captioning models are limited in their ability to scale and describe concepts unseen in paired image-text corpora. We propose the Novel Object Captioner (NOC), a deep visual semantic captioning model that can desc…

ObjectObject Recognition

iPIC-XAI: Improving PIC-XAI for Enhanced Image Captioning Explanation

2023-09-23 · 2023 14th IEEE International Conference on Cognitive Infocommunications (CogInfoCom) 2023 9 · Modafar Al-Shouha, Gábor Szűcs

Image captioning task with its complexity has taken advantage of the recent developments in Deep learning (DL). However, DL-models are fundamentally abstruse and explaining their behaviour is a challenge. In this paper w…

Image CaptioningTAG

Going Beneath the Surface: Evaluating Image Captioning for Grammaticality, Truthfulness and Diversity

2019-12-19 · Huiyuan Xie, Tom Sherborne, Alexander Kuhnle, Ann Copestake

Image captioning as a multimodal task has drawn much interest in recent years. However, evaluation for this task remains a challenging problem. Existing evaluation metrics focus on surface similarity between a candidate …

DiagnosticDiversityImage Captioning