Filters








4,793 Hits in 5.6 sec

Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning [article]

Manish Bhattarai, Diane Oyen, Juan Castorena, Liping Yang, Brendt Wohlberg
2020 arXiv   pre-print
We begin by using deep learning to generate sketches from natural images for image retrieval and then train a second deep learning model on the sketches.  ...  We then use our small set of manually labeled patent diagram images via transfer learning to adapt the image search from sketches of natural images to diagrams.  ...  We use deep learning to generate sketches from natural images (using existing natural image repositories for image retrieval/image search/ image comparison).  ... 
arXiv:2004.10780v1 fatcat:b557no42uvd25mexqhe6qiwlem

Deep CNN-based Features for Hand-Drawn Sketch Recognition via Transfer Learning Approach

Shaukat Hayat, Kun She, Muhammad Mateen, Yao Yu
2019 International Journal of Advanced Computer Science and Applications  
transfer learning with global average pooling (GAP) strategy is proposed.  ...  Increasing use of touchscreens and portable devices raised the challenge for computer vision community to access the sketches more efficiently and effectively.  ...  Based on trained knowledge, these models re-used for sketch dataset (Target domain) and fine-tuned. The concept of transfer learning is shown in Fig. 6 .  ... 
doi:10.14569/ijacsa.2019.0100958 fatcat:fpnjutrnwvfj7dfd3kaxovmaii

Data augmentation-assisted deep learning of hand-drawn partially colored sketches for visual search

Jamil Ahmad, Khan Muhammad, Sung Wook Baik, Zhihan Lv
2017 PLoS ONE  
The deep features extracted from CNN allow retrieval of images using both sketches and full color images as queries.  ...  in a sketch-based image retrieval framework.  ...  Acknowledgments The authors thank Prof Marc Alexa and Prof Ugur Gudukbay for providing the sketches dataset and multi-view objects dataset.  ... 
doi:10.1371/journal.pone.0183838 pmid:28859140 pmcid:PMC5578632 fatcat:o3vpabm4xna3dcmqjkqxhuzizy

Extended 2D Scene Sketch-Based 3D Scene Retrieval

Juefei Yuan, Hameed Abdul-Rashid, Bo Li, Yijuan Lu, Tobias Schreck, Ngoc-Minh Bui, Trong-Le Do, Khac-Tuan Nguyen, Thanh-An Nguyen, Vinh-Tiep Nguyen, Minh-Triet Tran, Tianyang Wang
2019 Eurographics Workshop on 3D Object Retrieval, EG 3DOR  
Deep learning techniques have been proved their great potentials again in dealing with this challenging retrieval task, in terms of both retrieval accuracy and scalability to a larger dataset.  ...  Therefore, the objective of this track is to further evaluate the performance and scalability of different 2D scene sketch-based 3D scene model retrieval algorithms using this extended and more comprehensive  ...  We gratefully acknowledge the support from NVIDIA Corporation for the donation of the Titan X/Xp GPUs used in this research and anonymous content creators from the Internet.  ... 
doi:10.2312/3dor.20191059 fatcat:vupz3eoigjgx3dgegcz4nwsasy

Entropy information‐based heterogeneous deep selective fused features using deep convolutional neural network for sketch recognition

Shaukat Hayat, She Kun, Sara Shahzad, Parinya Suwansrikham, Muhammad Mateen, Yao Yu
2021 IET Computer Vision  
First, the high-level deep layers of the networks were used to get multi-features hierarchy from sketch images.  ...  The performance of the proposed scheme is evaluated on two different sketch datasets such as TU-Berlin and Sketchy for classification and retrieval tasks.  ...  Deep learning has the ability to learn more discriminative features from sketch input images and performs better in sketch recognition and retrieval than traditional approaches.  ... 
doi:10.1049/cvi2.12019 fatcat:ldnhxmennjbsjmkvm7vijidyku

Deep Learning for Free-Hand Sketch: A Survey [article]

Peng Xu, Timothy M. Hospedales, Qiyue Yin, Yi-Zhe Song, Tao Xiang, Liang Wang
2022 arXiv   pre-print
The progress of deep learning has immensely benefited free-hand sketch research and applications.  ...  This paper presents a comprehensive survey of the deep learning techniques oriented at free-hand sketch data, and the applications that they enable.  ...  ., free-hand sketch based recognition and image/3D retrieval. (ii) mainly review classic non-deep techniques.  ... 
arXiv:2001.02600v3 fatcat:lek5sivzsrat3i52lqh2eifnia

An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval [article]

Osman Tursun, Simon Denman, Sridha Sridharan, Ethan Goan, Clinton Fookes
2021 arXiv   pre-print
The majority of previous studies using deep neural networks have achieved improved results through either projecting sketch and images into a common low-dimensional space or transferring knowledge from  ...  ZS-SBIR inherits the main challenges of multiple computer vision problems including content-based Image Retrieval (CBIR), zero-shot learning and domain adaptation.  ...  Conclusion In this work, we propose a simple and efficient framework for zero-shot sketch-based image retrieval (ZS-SBIR).  ... 
arXiv:2102.04016v1 fatcat:bh74enxzzzeepasgzuehkjpmkm

Business Process Sketch Recognition

Bernhard Schäfer
2019 International Conference on Business Process Management  
To recognize the symbols and structure of handwritten flowcharts, we have developed Arrow R-CNN. Arrow R-CNN is the first deep learning detector for flowchart structure recognition.  ...  In early stages of a BPM project, simple process diagrams are often sketched on paper or whiteboard. Transferring a process sketch into existing modeling systems is a tedious manual process.  ...  In general, training deep learning models requires a lot of data.  ... 
dblp:conf/bpm/Schafer19 fatcat:zqxirjrxd5bl3dfuwj5i7375zm

Three-Stream Joint Network for Zero-Shot Sketch-Based Image Retrieval [article]

Yu-Wei Zhan, Xin Luo, Yongxin Wang, Zhen-Duo Chen, Xin-Shun Xu
2022 arXiv   pre-print
The Zero-Shot Sketch-based Image Retrieval (ZS-SBIR) is a challenging task because of the large domain gap between sketches and natural images as well as the semantic inconsistency between seen and unseen  ...  In addition, we use a teacher network to extract the implicit semantics of the samples without the aid of other semantics and transfer the learned knowledge to unseen classes.  ...  In recent years, with the advances of deep neural networks, a large number of works have emerged to extract deep features from images and sketches using CNNs to learn better representations [1, 30, 42  ... 
arXiv:2204.05666v1 fatcat:ug5w5236e5bs3ase3e6oyu2syu

Determining Inference Semantics for Disjunctive Logic Programs (Extended Abstract)

Yi-Dong Shen, Thomas Eiter
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
[Gelfond and Lifschitz, 1991] introduced simple disjunctive logic programs and defined the answer set semantics called GL-semantics.  ...  To address this, we present a novel and more permissive semantics, called determining inference semantics.  ...  Acknowledgements This work was supported partly by the JST CREST Grant JPMJCR1686, partly by the Grant-in-Aid for JSPS Fellows 18F18378, and partly by the Microsoft Collaborative Research Grant.  ... 
doi:10.24963/ijcai.2020/692 dblp:conf/ijcai/WangWZWZS20 fatcat:b6fxzp2wqzc6fiuotnit2jusoq

Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification [article]

Zheng Wang, Zhixiang Wang, Yinqiang Zheng, Yang Wu, Wenjun Zeng, Shin'ichi Satoh
2020 arXiv   pre-print
We also summarize and compare the representative approaches from two perspectives, i.e., the application scenario and the learning pipeline.  ...  According to the application scenario, we classify the methods into four categories -- low-resolution, infrared, sketch, and text.  ...  Acknowledgement This work was supported partly by the JST CREST Grant JP-MJCR1686, partly by the Grant-in-Aid for JSPS Fellows 18F18378, and partly by the Microsoft Collaborative Research Grant.  ... 
arXiv:1905.10048v4 fatcat:trxlyflmcfaoxenlwskfpcikiu

A Journey from basic Image Features to Lofty Human Intelligence in Content-based Image Retrieval: Motivation, Applications and Future Trends

2020 International journal of recent technology and engineering  
For the purpose of retrieving images from a vast storehouse of images, there is an urgent requirement of an effectual image retrieval system and the most effective system in this domain is denoted as content-based  ...  But, there exists a semantic gap between the basic image features and high-level human perception and to reduce this gap various techniques can be used.  ...  Hybrid deep learning architecture (HDLA) [26] , is a technique based on deep learning which can be used for an effective image retrieval.  ... 
doi:10.35940/ijrte.b4011.079220 fatcat:aedu4uzoxrhafhab46ordfxm2m

Automatic Classification of UML Class Diagrams Using Deep Learning Technique: Convolutional Neural Network

Bethany Gosala, Sripriya Roy Chowdhuri, Jyoti Singh, Manjari Gupta, Alok Mishra
2021 Applied Sciences  
We developed a new approach for automatically classifying class diagrams using the approach of Convolutional Neural Network under the domain of Deep Learning.  ...  Earlier research used Machine Learning techniques for classifying class diagrams.  ...  [23] proposed a content-based and keyword-based retrieval of models from repositories.  ... 
doi:10.3390/app11094267 fatcat:itgachdnhrb5ve4jik6wigv7yi

Visual‐attention GAN for interior sketch colourisation

Xinrong Li, Hong Li, Chiyu Wang, Xun Hu, Wei Zhang
2021 IET Image Processing  
The experimental results show that, compared with the existing methods, the proposed method can better deal with the problem of sketch and generate stable and reliable images.  ...  In the professional field of interior designing, sketch colouring is often a time-consuming and vapidity task.  ...  ACKNOWLEDGEMENTS This work was supported by the National Natural Science Foundation of China under Grants: Methodologies for Understanding Big Data and Knowledge Discovery (61836016).  ... 
doi:10.1049/ipr2.12080 fatcat:2u2bjpbhmzf5zicwayyaccakyq

SKETRACK: Stroke-Based Recognition of Online Hand-Drawn Sketches of Arrow-Connected Diagrams and Digital Logic Circuit Diagrams

Oğuz Altun, Orhan Nooruldeen
2019 Scientific Programming  
This paper focuses on the design and development of a new, efficient stroke-based online hand-drawn sketch recognition scheme named SKETRACK for hand-drawn arrow diagrams and digital logic circuit diagrams  ...  The strokes are clustered using the spectral clustering algorithm based on p-distance and Euclidean distance to compute the similarity between the features and minimize the feature dimensionality by grouping  ...  of deep CNN for sketch-based image retrieval application with a sketch recognition accuracy of 79.18%.  ... 
doi:10.1155/2019/6501264 fatcat:chjuvsd4jrajldmuabyypg6szi
« Previous Showing results 1 — 15 out of 4,793 results