StyleNet: Generating Attractive Visual Captions with Styles

By Chuang Gan, Zhe Gan, Xiaodong He, Jianfeng Gao, Li Deng. 2017

298 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Multimodal Learning

Citations in the corpus

Attention on Attention for Image Captioning (2019, neutral): “[42, 27, 47, 2, 7, 16, 15] and achieved impressive results.”
Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer (2018, methodology): “CAPTIONS In the CAPTIONS dataset (Gan et al., 2017), each example is a sentence that describes an image, and is labeled as either factual, romantic, or humorous.”
Semantic Compositional Networks for Visual Captioning (2016, neutral): “Similar ideas have been exploited in [25, 30, 38, 39, 41, 50, 14].”
Politeness Transfer: A Tag and Generate Approach (2020, background): “The Captions dataset (Gan et al., 2017) has image captions labeled as being factual, romantic or humorous.”
From Eliza to XiaoIce: challenges and opportunities with social chatbots (2018, background): “The generation-based approach treats image commenting as an image-to-language generation task (He and Deng 2017) but will have more flexibility for controlling high-level sentiment or style factors in comment generation (Mathews et al., 2015; Gan et al., 2017).”
A Comprehensive Survey of Deep Learning for Image Captioning (2018, methodology): “Gan et al. [39] proposed a novel image captioning system called StyleNet.”
Captioning Images Taken by People Who Are Blind (2020, methodology): “that most existing datasets were created in contrived settings. Typically, crowdsourced workers were employed to produce captions for images curated from online, public image databases such as Flickr [6,15,20,24,26,30,50,51]. Yet, we have observed over the past decade that people have Figure 1: Exam”
Adaptive Feature Abstraction for Translating Video to Text (2016, background): “2014; Sutskever, Vinyals, and Le 2014) and image caption generation (Karpathy and Li 2015; Kiros, Salakhutdinov, and Zemel 2014; Mao et al. 2015; Pu et al. 2016; Vinyals et al. 2015; Gan et al. 2017a; 2017b), most recent work on video captioning (Donahue et al.”
Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning (2017, background): “Visual dialog is the latest in a succession of vision-andlanguage problems that began with image captioning [9, 13, 36, 39], and includes visual question answering [1, 10, 40].”
Engaging Image Chat: Modeling Personality in Grounded Dialogue (2018, background): “Some works have extended image captioning from being purely factual towards more engaging captions by incorporating style and personality while still being single turn, e.g. (Chandrasekaran et al., 2017; Mathews et al., 2018, 2016; Gan et al., 2017).”
Style Transfer as Unsupervised Machine Translation (2018, unknown): “• Captions: This dataset consists of image captions (Gan et al. 2017).”
Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions (2018, background): “Others have conditioned the generation with a specific style or sentiment [27, 28, 11].”
VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation (2017, methodology): “We have witnessed the resurgence of image captioning [42, 29, 18, 6, 40, 4, 47, 12, 33, 10] which is often addressed by jointly modeling visual and textual content with deep neural networks.”
Language Models Can See: Plugging Visual Controls in Text Generation (2022, background): “Meanwhile, some controllable image captioning methods [48, 21, 8, 70, 7] propose to generate diverse descriptions by feeding different control signals (e.”
Towards Better Representations with Deep/Bayesian Learning (2018, methodology): “In the traditional factor analysis (Gan et al., 2017c), the linear relation between x and z is assumed, and inference is done using mean field VB or Gibbs sampling.”
Multimodal Intelligence: Representation Learning, Information Fusion, and Applications (2019, background): “been proposed for explicitly controlling the style [194], semantic content [190], and diversity [195] of generated captions.”
Deep Learning for Text Style Transfer: A Survey (2020, background): “Li et al. (2018) first propose to borrow the FlickrStyle stylized caption dataset (Gan et al. 2017) from the computer vision domain.”
Visual Grounding Via Accumulated Attention (2020, background): “As a research direction across vision and language, VG has beneﬁted from the development of Convolutional Neu-7746 ral Networks [7, 12], Recurrent Neural Networks [2, 6], and other areas such as Image Captioning [5, 26] and Visual Question Answering (VQA) [27].”