Generating Affective Captions using Concept And Syntax Transition Networks

Karayil, Tushar; Blandfort, Philipp; Borth, Damian; Dengel, Andreas

doi:10.1145/2964284.2984070

Cited by 8 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [68][69][70], a VggNet architecture was adopted to extract low-level features; in [71], such a task was accomplished by a Res_152 architecture. Karayil et al [72], conversely, used AlexNet to model ANPs; a multi-directed graph ranked the ANP couples provided by the CNN and generated captions accordingly. For the purpose of improving sentiment description, Sun et al [73] extended a pre-trained caption generation model with an emotion classifier to add abstract knowledge.…”

Section: Sentiment Analysis: Other Applicationsmentioning

confidence: 99%

A Survey on Deep Learning in Image Polarity Detection: Balancing Generalization Performances and Computational Costs

et al. 2019

View full text Add to dashboard Cite

Deep convolutional neural networks (CNNs) provide an effective tool to extract complex information from images. In the area of image polarity detection, CNNs are customarily utilized in combination with transfer learning techniques to tackle a major problem: the unavailability of large sets of labeled data. Thus, polarity predictors in general exploit a pre-trained CNN as the feature extractor that in turn feeds a classification unit. While the latter unit is trained from scratch, the pre-trained CNN is subject to fine-tuning. As a result, the specific CNN architecture employed as the feature extractor strongly affects the overall performance of the model. This paper analyses state-of-the-art literature on image polarity detection and identifies the most reliable CNN architectures. Moreover, the paper provides an experimental protocol that should allow assessing the role played by the baseline architecture in the polarity detection task. Performance is evaluated in terms of both generalization abilities and computational complexity. The latter attribute becomes critical as polarity predictors, in the era of social networks, might need to be updated within hours or even minutes. In this regard, the paper gives practical hints on the advantages and disadvantages of the examined architectures both in terms of generalization and computational cost.

show abstract

Section: Sentiment Analysis: Other Applicationsmentioning

confidence: 99%

A Survey on Deep Learning in Image Polarity Detection: Balancing Generalization Performances and Computational Costs

et al. 2019

View full text Add to dashboard Cite

show abstract

“…For instance, Wang et al [37] propose a deeper bidirectional variant of Long Short Term Memory (LSTM) to take both history and future context into account in image captioning. A concept and syntax transition network [19] is presented to deal with large real-world captioning datasets such as YFCC100M [34]. Furthermore, in [31], reinforcement learning is also utilized to train the CNN-RNN based model directly on test metrics of the captioning task, showing significant gains in performance.…”

Section: Progress On Image Captioningmentioning

confidence: 99%

Fluency-Guided Cross-Lingual Image Captioning

Lan

Dong

2017

Proceedings of the 25th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Image captioning has so far been explored mostly in English, as most available datasets are in this language. However, the application of image captioning should not be restricted by language. Only few studies have been conducted for image captioning in a cross-lingual setting. Different from these works that manually build a dataset for a target language, we aim to learn a cross-lingual captioning model fully from machine-translated sentences. To conquer the lack of fluency in the translated sentences, we propose in this paper a fluency-guided learning framework. The framework comprises a module to automatically estimate the fluency of the sentences and another module to utilize the estimated fluency scores to effectively train an image captioning model for the target language. As experiments on two bilingual (English-Chinese) datasets show, our approach improves both fluency and relevance of the generated captions in Chinese, but without using any manually written sentences from the target language.Comment: 9 pages, 2 figures, accepted as ORAL by ACM Multimedia 201

show abstract

A State-of-Art Review on Automatic Video Annotation Techniques

Randive

Mohan

2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Generating Affective Captions using Concept And Syntax Transition Networks

Cited by 8 publications

References 13 publications

A Survey on Deep Learning in Image Polarity Detection: Balancing Generalization Performances and Computational Costs

A Survey on Deep Learning in Image Polarity Detection: Balancing Generalization Performances and Computational Costs

Fluency-Guided Cross-Lingual Image Captioning

A State-of-Art Review on Automatic Video Annotation Techniques

Contact Info

Product

Resources

About