Deep image aesthetics classification using inception modules and fine-tuning connected layer

Jin, Xin; Chi, Jingying; Peng, Siwei; Tian, Yulu; Ye, Chaochen

doi:10.1109/wcsp.2016.7752571

Cited by 48 publications

(24 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Before deep learning era, many hand-crafted features [7,16] are designed for aesthetic image classification and scoring as surveyed by Deng et al [9]. Deep learning methods are proposed recently for aesthetic assessment [11,14,15,17,18,20,21,23,24,31]. They outperform traditional methods.…”

Section: Related Workmentioning

confidence: 99%

Aesthetic Attributes Assessment of Images

Jin

Zhao

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Figure 1: Aesthetic Attributes Assessment of Images. We predict caption and score of each aesthetic attribute of an image.ABSTRACT Image aesthetic quality assessment has been a relatively hot topic during the last decade. Most recently, comments type assessment (aesthetic captions) has been proposed to describe the general aesthetic impression of an image using text. In this paper, we propose Aesthetic Attributes Assessment of Images, which means the aesthetic attributes captioning. This is a new formula of image aesthetic assessment, which predicts aesthetic attributes captions together with the aesthetic score of each attribute. We introduce a new dataset named DPC-Captions which contains comments of up to 5 aesthetic attributes of one image through knowledge transfer from a full-annotated small-scale dataset. Then, we propose Aesthetic Multi-Attribute Network (AMAN), which is trained on a mixture of fully-annotated small-scale PCCD dataset and weakly-annotated large-scale DPC-Captions dataset. Our AMAN makes full use of transfer learning and attention model in a single framework. The experimental results on our DPC-Captions and PCCD dataset reveal that our method can predict captions of 5 aesthetic attributes together with numerical score assessment of each attribute. We use the evaluation criteria used in image captions to prove that our specially designed AMAN model outperforms traditional CNN-LSTM model and modern SCA-CNN model of image captions.

show abstract

Section: Related Workmentioning

confidence: 99%

Aesthetic Attributes Assessment of Images

Jin

Zhao

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…Cinematography rules are hard-coded into the system. To prevent including technically defective footage into the resulting film we propose to use the results shown in [5]. They used a crowd-sourced collection of rated photos to train a convolutional neural network to directly regress aesthetical score of an image.…”

Section: Automated Editing Of Video Footage From Multiple Cameras To mentioning

confidence: 99%

“…A GoogLeNet [7] network is used to extract a semantic feature vector of length 1024. A network trained to regress aesthetical score on AVA dataset [5] produces a vector of length 2. A network trained to classify an image into three classes of shot sizes (close-up, medium shot, long shot) produces a vector of length 3.…”

mentioning

confidence: 99%

Towards Data-Driven Automatic Video Editing

Podlesnyy¹

2019

Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery

View full text Add to dashboard Cite

Automatic video editing involving at least the steps of selecting the most valuable footage from points of view of visual quality and the importance of action filmed; and cutting the footage into a brief and coherent visual story that would be interesting to watch is implemented in a purely data-driven manner. Visual semantic and aesthetic features are extracted by the ImageNettrained convolutional neural network, and the editing controller is trained by an imitation learning algorithm. As a result, at test time the controller shows the signs of observing basic cinematography editing rules learned from the corpus of motion pictures masterpieces.

show abstract

“…They also investigate whether image aesthetic quality is a global or local attribute, and the role played by bottom-up and top-down salient regions to the prediction of the global image aesthetics. In [11], its authors aiming once again to take both local and global features of images into consideration, propose a DCNN architecture named ILGNet, which combines both the Inception modules and a connected layer of both local and global features. The network contains one pre-treatment layer and three inception modules.…”

Section: Related Workmentioning

confidence: 99%

Image Aesthetics Assessment Using Fully Convolutional Neural Networks

Apostolidis

Mezaris

2018

MultiMedia Modeling

View full text Add to dashboard Cite

This paper presents a new method for assessing the aesthetic quality of images. Based on the findings of previous works on this topic, we propose a method that addresses the shortcomings of existing ones, by: a) Making possible to feed higher-resolution images in the network, by introducing a fully convolutional neural network as the classifier. b) Maintaining the original aspect ratio of images in the input of the network, to avoid distortions caused by re-scaling. And c) combining local and global features from the image for making the assessment of its aesthetic quality. The proposed method is shown to achieve state of the art results on a standard large-scale benchmark dataset.

show abstract

Deep image aesthetics classification using inception modules and fine-tuning connected layer

Cited by 48 publications

References 29 publications

Aesthetic Attributes Assessment of Images

Aesthetic Attributes Assessment of Images

Towards Data-Driven Automatic Video Editing

Image Aesthetics Assessment Using Fully Convolutional Neural Networks

Contact Info

Product

Resources

About