Filters








1,422,507 Hits in 3.5 sec

Preference-Based Image Generation

Hadi Kazemi, Fariborz Taherkhani, Nasser M. Nasrabadi
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
In this paper, we introduce the Preference-Based Image Generation (PbIG), a new method to retrieve the corresponding latent code of the user's mental image.  ...  We propose to adopt preference-based reinforcement learning, which learns from a user's judgment of the generated images by a pretrained generative model.  ...  Preference-Based Image Generation (PbIG) In our proposed Preference-Based Image Generation (PbIG) the state of environment does not change as the user has a fixed mental image at all time, and taking new  ... 
doi:10.1109/wacv45572.2020.9093406 dblp:conf/wacv/KazemiTN20 fatcat:a7lvwpxf3nfwdiqrbgo37xgh2a

Preference-based Evaluation Metrics for Web Image Search

Xiaohui Xie, Jiaxin Mao, Yiqun Liu, Maarten de Rijke, Haitian Chen, Min Zhang, Shaoping Ma
2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval  
Compared to general web search, web image search may be an even better fit for preference-based evaluation because of its grid-based presentation style.  ...  While preference judgments have been studied extensively for general web search, there exists no thorough investigation on how preference judgments and preference-based evaluation metrics can be used to  ...  In web image search, grid-based result panels are used instead of the linear result lists that are common in general web search.  ... 
doi:10.1145/3397271.3401146 dblp:conf/sigir/XieMLRCZM20 fatcat:wgimluovu5frlcrsmivd7mznfq

Joint regression and learning from pairwise rankings for personalized image aesthetic assessment

Jin Zhou, Qing Zhang, Jian-Hao Fan, Wei Sun, Wei-Shi Zheng
2021 Computational Visual Media  
a generic aesthetic assessment model by CNN-based regression.  ...  However, these methods focus primarily on predicting generally perceived preference of an image, making them usually have limited practicability, since each user may have completely different preferences  ...  Generic image aesthetic regression With the collected personal images, we regress a generic aesthetic model that numerically describes the universal visual preference for images of similar categories.  ... 
doi:10.1007/s41095-021-0207-y fatcat:yve552ozqbahzh66bhkl6tn3lu

Deep Learning Model with Transfer Learning to Infer Personal Preferences in Images

Jaeho Oh, Mincheol Kim, Sang-Woo Ban
2020 Applied Sciences  
In this paper, we propose a deep convolutional neural network model with transfer learning that reflects personal preferences from inter-domain databases of images having atypical visual characteristics  ...  The proposed model utilized three public image databases (Fashion-MNIST, Labeled Faces in the Wild [LFW], and Indoor Scene Recognition) that include images with atypical visual characteristics in order  ...  Structure of Grad-CAM for generating a heat map reflecting the user's preference based on atypical features. Figure 4 . 4 Figure 4. Fashion-MNIST dataset images and labels [6,16].  ... 
doi:10.3390/app10217641 fatcat:6cynirgvrzhffg7geh7tkmftby

USER'S PREFERENCE-BASED COLOR TRANSFORMATION USING INTERACTIVE GENETIC ALGORITHM [article]

Hang-Bong Kang, Hye-Yoon Woo
2010 Eurographics State of the Art Reports  
To obtain general preferences for color, we first divided the images into two categories as favourable and unfavourable groups based on the users' evaluation.  ...  In this paper, we propose a new color transform method in the image based on the user's preferences.  ...  If we can transform colors in the captured images into favorable and unfavorable colors, a user can easily create his own preferred images.  ... 
doi:10.2312/egp.20101027 fatcat:iz66vmyxnbdtpicfl67ohfpgxm

Preferred Racial Skin Color Reproduction in an Image based on Race Classification

Dae-Chul Kim, Wang-Jun Kyung, Yeong-Ho Ha
2015 Journal of Imaging Science and Technology  
Based on this classification, the racial preferred skin color for each detected skin region is then selected from candidate racial preferred skin colors that are predefined in a database generated through  ...  Kim, Kyung, and Ha: Preferred racial skin color reproduction in an image based on race classification Figure 1. Block diagram of the proposed skin color reproduction.  ...  For Asians, 360 prototype skin images are generated by changing the hue and saturation values under a predefined skin color based on HSV color space.  ... 
doi:10.2352/j.imagingsci.technol.2015.59.2.020504 fatcat:24bzpm3gxzcn7bp2j5mh3jn5wi

Which is the Better Inpainted Image?Training Data Generation Without Any Manual Operations

Mariko Isogawa, Dan Mikami, Kosuke Takahashi, Daisuke Iwai, Kosuke Sato, Hideaki Kimata
2018 International Journal of Computer Vision  
Thus, existing learning-based image quality assessment (IQA) methods for inpainting require subjectively annotated data for training.  ...  We also propose a masking method for generating training data towards fully automated training data generation.  ...  Shohei Mori for sharing the image inpainting implementation.  ... 
doi:10.1007/s11263-018-1132-0 fatcat:ofza7jlki5cz5ollmawiel4yca

Assessment of Color Perception and Preference with Eye-Tracking Analysis in a Dental Treatment Environment

Eun-Sung Song, Won-Hyeon Kim, Beom-Hui Lee, Dong-Wook Han, Jong-Ho Lee, Bongju Kim
2021 International Journal of Environmental Research and Public Health  
In addition, for the psychological color images associated with color preference, the subjects tended to prefer images such as warmth, friendliness, and calmness.  ...  This study aimed to investigate gaze characteristics based on a color preference survey of the dental unit chair, which has the most influence on spatial perception in the dental treatment environment,  ...  It is difficult to generalize the result of color preference based on the gaze analysis as a method for establishing a color scheme for a medical environment.  ... 
doi:10.3390/ijerph18157981 fatcat:fttmozxwz5crpczv6nr344budm

Visually-Aware Fashion Recommendation and Design with Generative Image Models [article]

Wang-Cheng Kang, Chen Fang, Zhaowen Wang, Julian McAuley
2017 arXiv   pre-print
Furthermore, we show that our model can be used generatively, i.e., given a user and a product category, we can generate new images (i.e., clothing items) that are most consistent with their personal taste  ...  Here, we seek to extend this contribution by showing that recommendation performance can be significantly improved by learning 'fashion aware' image representations directly, i.e., by training the image  ...  (based on Generative Adversarial Networks).  ... 
arXiv:1711.02231v1 fatcat:xytgylq6bvbthhcebq3hccunfe

Development of Fashion Product Retrieval and Recommendations Model Based on Deep Learning

Jaechoon Jo, Seolhwa Lee, Chanhee Lee, Dongyub Lee, Heuiseok Lim
2020 Electronics  
The vector-based preference fashion recommendation model also showed positive performance.  ...  It was found that the "Precision at 5" of the image-based similar product retrieval model was 0.774 and that of the sketch-based similar product retrieval model was 0.445.  ...  As the proposed images were filtered by professionals, general users can select their preferred style from the images that were already screened for uncomfortable or unattractive styles.  ... 
doi:10.3390/electronics9030508 fatcat:kmffxze2zbemfhqwxcioksveui

Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption

Wei Zhang, Yue Ying, Pan Lu, Hongyuan Zha
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Personalized image caption, a natural extension of the standard image caption task, requires to generate brief image descriptions tailored for users' writing style and traits, and is more practical to  ...  It learns short-term user literal-preference based on users' recent captions through a short-term user encoder at the low level.  ...  The retrieval based models in the first part of the table perform poorly compared with other generative models.  ... 
doi:10.1609/aaai.v34i05.6503 fatcat:fmqhiw2o3zdtppmgekcczebvbe

Human-in-the-Loop Design with Machine Learning

Pan Wang, Danlin Peng, Ling Li, Liuqing Chen, Chao Wu, Xiaoyi Wang, Peter Childs, Yike Guo
2019 Proceedings of the International Conference on Engineering Design  
The results indicate that the method can generate preferred designs styles guided by the preference related brain signals.  ...  Secondly, a GAN model is trained conditioned on the encoded EEG features to generate design images.  ...  Designers could have a prejudgment based on these generated images.  ... 
doi:10.1017/dsi.2019.264 fatcat:egboi5gc7ja5ba34ra7ukezuim

Evolutionary programming based recommendation system for online shopping

Jehan Jung, Yuka Matsuba, Rammohan Mallipeddi, Hiroyuki Funaya, Kazushi Ikeda, Minho Lee
2013 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference  
In this paper, we propose an interactive evolutionary programming based recommendation system for online shopping that estimates the human preference based on eye movement analysis.  ...  Therefore, in the proposed system, human preference is measured from the way the human subjects look at the images of different clothes.  ...  In other words, when several images are presented simultaneously there exists a correlation between accumulated fixation time and the viewer's preference for one image over others [8] .  ... 
doi:10.1109/apsipa.2013.6694236 dblp:conf/apsipa/JungMMFIL13 fatcat:zlaeu6nhgzbhza3kyf6djfebxi

Knowing a tree from the forest

Kai Yu, Wei-Ying Ma, Volker Tresp, Zhao Xu, Xiaofei He, HongJiang Zhang, Hans-Peter Kriegel
2003 Proceedings of the eleventh ACM international conference on Multimedia - MULTIMEDIA '03  
In the second setting, we report evaluations based on user preferences collected through an online web-based survey.  ...  AIR is of great interests to us because of its application potentials and interesting research challengesthe retrieval is not only based on painting contents or styles, but also heavily based on user preference  ...  Based on the profile type, we generate a number of examples, with approximately 1/3 liked images and 2/3 disliked ones, to feed the art image retrieval system.  ... 
doi:10.1145/957142.957145 fatcat:5qhojr5yrrehzf2y6pecpknqyu

Knowing a tree from the forest

Kai Yu, Wei-Ying Ma, Volker Tresp, Zhao Xu, Xiaofei He, HongJiang Zhang, Hans-Peter Kriegel
2003 Proceedings of the eleventh ACM international conference on Multimedia - MULTIMEDIA '03  
In the second setting, we report evaluations based on user preferences collected through an online web-based survey.  ...  AIR is of great interests to us because of its application potentials and interesting research challengesthe retrieval is not only based on painting contents or styles, but also heavily based on user preference  ...  Based on the profile type, we generate a number of examples, with approximately 1/3 liked images and 2/3 disliked ones, to feed the art image retrieval system.  ... 
doi:10.1145/957013.957145 dblp:conf/mm/YuMTXHZK03 fatcat:wwtdpdmuh5csdiuiuatzkw6eny
« Previous Showing results 1 — 15 out of 1,422,507 results