Generalizing Image Captions for Image-Text Parallel Corpus

By Polina Kuznetsova, Vicente Ordonez, Alexander C. Berg, Tamara L. Berg, Yejin Choi. 2013

89 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Multimodal Learning

Citations in the corpus

A Retrieve-and-Edit Framework for Predicting Structured Outputs (2018, methodology): “However, the desired output might be a variation of another, previously-observed example [14, 13, 30, 18, 24].”
DenseCap: Fully Convolutional Localization Networks for Dense Captioning (2015, background): “Several pioneering approaches have explored the task of describing images with natural language [1, 27, 12, 34, 42, 43, 28, 20].”
TreeTalk: Composition and Compression of Trees for Image Descriptions (2014, background): “4 Tree Compression As noted by recent studies (Mason and Charniak, 2013; Kuznetsova et al., 2013; Jamieson et al., 2010), naturally existing image captions often include contextual information that does not directly describe visual content, which ultimately hinders their usefulness for describing…”
Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation (2019, neutral): “…Text Generation Our work is also related to the recent work on applying retrieval mechanisms to augment text generation, such as image captioning (Kuznetsova et al., 2013; Mason and Charniak, 2014), dialogue generation (Song et al., 2016; Yan et al., 2016; Wu et al., 2018) and style transfer…”
Scene Graph Generation from Objects, Phrases and Region Captions (2017, unknown): “It has been investigated for years [3, 13, 19, 24, 26, 39].”
Déjà Image-Captions: A Corpus of Expressive Descriptions in Repetition (2015, background): “In particular, everyday captions often contain extraneous information that is not directly relevant to what the image shows (Kuznetsova et al., 2013b; Hodosh et al., 2013).”
Open-vocabulary Object Retrieval (2014, methodology): “Therefore, our score function is based on comparing the given text query q with m different representations of an image in a weighted open-vocabulary text space.”
What Are You Talking About? Text-to-Image Coreference (2014, background): “There has been substantial work in automatic captioning or description generation of images [12, 13, 14] and video [2].”
Know More Say Less: Image Captioning Based on Scene Graphs (2019, background): “Some early approaches ﬁrst retrieve images from a corpus with image-caption pairs and then directly transfer the corresponding human-written sentences for the query images [33], [34].”
Image Caption Generation with Text-Conditional Semantic Attention (2016, background): “Generally, the literature on image captioning can be divided into three categories: templatebased methods [3], transfer-based methods [4] and neural network-based methods [5], respectively.”
Nonparametric Method for Data-driven Image Captioning (2014, background): “Compression meth-ods for removing visually irrelevant information (Kuznetsova et al., 2013) may also help increase the relevance of extracted captions.”
STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset (2017, background): “Some English image caption datasets have been proposed (Krishna et al., 2016; Kuznetsova et al., 2013; Ordonez et al., 2011; Vedantam et al., a r X i v : 1705 .”
Guiding the Long-Short Term Memory Model for Image Caption Generation (2015, methodology): “In particular, compared to template-based methods [9, 20, 28, 39], that use a rigid sentence structure, and transfer-based methods [21, 22, 23, 27], that re-use descriptions available in the training data, meth-”
Domain-Specific Image Captioning (2014, methodology): “Kuznetsova et al. (2013) propose a sentence compression model for editing image captions, but their compression objective is not conditioned on a query image, and their system also requires general-domain visual detections.”