Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner

Chen, Tseng-Hung; Liao, Yuan-Hong; Chuang, Ching-Yao; Hsu, Wan‐Ting; Fu, Jianlong; Sun, Min

doi:10.48550/arxiv.1705.00930

Cited by 6 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generative adversarial network for recommendation. In parallel, previous work has demonstrated the e ectiveness of generative adversarial network (GAN) [9] in various tasks such as image generation [2,24], image captioning [4], and sequence generation [33]. The most related work to ours is [29], which proposed a novel IR-GAN mechanism to iteratively optimize a generative retrieval component and a discriminative retrieval component.…”

Section: Related Workmentioning

confidence: 99%

Leveraging Long and Short-Term Information in Content-Aware Movie Recommendation via Adversarial Training

Zhao

Wang

Yang

et al. 2020

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Movie recommendation systems provide users with ranked lists of movies based on individual's preferences and constraints. Two types of models are commonly used to generate ranking results: long-term models and session-based models. While long-term models represent the interactions between users and movies that are supposed to change slowly across time, session-based models encode the information of users' interests and changing dynamics of movies' attributes in short terms. In this paper, we propose an LSIC model, leveraging Long and Short-term Information in Content-aware movie recommendation using adversarial training. In the adversarial process, we train a generator as an agent of reinforcement learning which recommends the next movie to a user sequentially. We also train a discriminator which attempts to distinguish the generated list of movies from the real records. The poster information of movies is integrated to further improve the performance of movie recommendation, which is speci cally essential when few ratings are available. The experiments demonstrate that the proposed model has robust superiority over competitors and sets the state-of-the-art. We will release the source code of this work after publication.

show abstract

Section: Related Workmentioning

confidence: 99%

Leveraging Long and Short-Term Information in Content-Aware Movie Recommendation via Adversarial Training

Zhao

Wang

Yang

et al. 2020

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…Few approaches Shetty et al, 2017) has leveraged adversarial training, while (Vijayakumar et al, 2016) used diverse beam search to decode diverse image captions in English. Approaches were also proposed to describe images from cross-domain (Chen et al, 2017).…”

Section: Image Description Generationmentioning

confidence: 99%

Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods

Mogadala,

Kalimuthu,

Klakow

2019

Preprint

View full text Add to dashboard Cite

Integration of vision and language tasks has seen a significant growth in the recent times due to surge of interest from multi-disciplinary communities such as deep learning, computer vision, and natural language processing. In this survey, we focus on ten different vision and language integration tasks in terms of their problem formulation, methods, existing datasets, evaluation measures, and comparison of results achieved with the corresponding state-of-the-art methods. This goes beyond earlier surveys which are either task-specific or concentrate only on one type of visual content i.e., image or video. We then conclude the survey by discussing some possible future directions for integration of vision and language research.

show abstract

“…In this paper, we specifically focus on image synthesis, whose goal is to generate images, since it is by far the most studied area where GAN has been applied. Besides image synthesis, there are many other applications of GAN in computer vision, such as image in-painting [16], image captioning [17] [18] [19], object detection [20] and semantic segmentation [21].…”

Section: Introductionmentioning

confidence: 99%

An Introduction to Image Synthesis with Generative Adversarial Nets

Huang¹,

Yu²,

Wang³

2018

Preprint

View full text Add to dashboard Cite

There has been a drastic growth of research in Generative Adversarial Nets (GANs) in the past few years. Proposed in 2014, GAN has been applied to various applications such as computer vision and natural language processing, and achieves impressive performance. Among the many applications of GAN, image synthesis is the most well-studied one, and research in this area has already demonstrated the great potential of using GAN in image synthesis. In this paper, we provide a taxonomy of methods used in image synthesis, review different models for text-to-image synthesis and image-to-image translation, and discuss some evaluation metrics as well as possible future research directions in image synthesis with GAN.

show abstract

Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner

Cited by 6 publications

References 11 publications

Leveraging Long and Short-Term Information in Content-Aware Movie Recommendation via Adversarial Training

Leveraging Long and Short-Term Information in Content-Aware Movie Recommendation via Adversarial Training

Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods

An Introduction to Image Synthesis with Generative Adversarial Nets

Contact Info

Product

Resources

About