Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleDecember 2024
Technology of Automatic Determination of Indications for 2RT-Laser Treatment of AMD from SD-OCT Images Based on Artificial Intelligence Methods
Optical Memory and Neural Networks (SPOMNN), Volume 33, Issue Suppl 2Pages S277–S284https://doi.org/10.3103/S1060992X24700565AbstractThe aim of this work is to develop and study the technology of automatic determination of indications for 2RT-laser treatment of AMD by SD-OCT images based on artificial intelligence methods. This is necessary to improve the accuracy and ...
- research-articleDecember 2024
Application of Computer Vision Algorithms to Solve the Problem of Smoke Detection in Industrial Production
Optical Memory and Neural Networks (SPOMNN), Volume 33, Issue Suppl 2Pages S270–S276https://doi.org/10.3103/S1060992X24700553AbstractThis paper proposes an approach for detecting smoke in industrial production using computer vision. The task of detecting smoke and fire can be framed as a detection problem, making modern convolutional neural network models well-suited for this ...
- ArticleNovember 2024
Steganography: An Improved Robust Model for Deep Hidden Network
PRICAI 2024: Trends in Artificial IntelligencePages 165–176https://doi.org/10.1007/978-981-96-0119-6_17AbstractIn existing deep learning image steganography methods, the neural network structure contains ineffective or complicated standard convolutional layers. These convolutional layers do not significantly improve performance, but instead increase ...
- ArticleSeptember 2024
Gaze Target Detection with Visual Prompt Tuning Based on Attention
Artificial Neural Networks and Machine Learning – ICANN 2024Pages 415–429https://doi.org/10.1007/978-3-031-72338-4_28AbstractExisting works focus on using convolutional networks as the feature map extractors for both scene and head in gaze target detection tasks. Cordonnier [1] demonstrated that attention mechanisms can entirely substitute convolutional layers and ...
- research-articleAugust 2024
Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networks
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4302–4313https://doi.org/10.1145/3637528.3671665Accurate traffic forecasting is crucial for the development of Intelligent Transportation Systems (ITS), playing a pivotal role in modern urban traffic management. Traditional forecasting methods, however, struggle with the irregular traffic time series ...
-
- ArticleMay 2024
Lightweight CNNs for Advanced Bird Species Recognition on the Edge
Bioinspired Systems for Translational Applications: From Robotics to Social EngineeringPages 95–104https://doi.org/10.1007/978-3-031-61137-7_10AbstractThis study embarked on a comprehensive exploration of deploying lightweight CNN models for the real-time classification of bird species, particularly focusing on their application within edge computing environments. Given the critical importance ...
- ArticleMay 2024
- ArticleSeptember 2023
Transfer Learning from ImageNet to the Domain of Pigmented Nevi
AbstractThe transfer learning method enables the use of a pretrained convolutional network to efficiently model a secondary domain with less data. In this article 18 public convolutional networks of different architecture and depth, pretrained on ImageNet,...
- research-articleJanuary 2023
PU-FPG: Point cloud upsampling via form preserving graph convolutional networks
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology (JIFS), Volume 45, Issue 5Pages 8595–8612https://doi.org/10.3233/JIFS-232490Point cloud upsampling can improve the resolutions of point clouds and maintain the forms of point clouds, which has attracted more and more attention in recent years. However, upsampling networks sometimes generate point clouds with unclear contours and ...
- surveySeptember 2022
Transformers in Vision: A Survey
ACM Computing Surveys (CSUR), Volume 54, Issue 10sArticle No.: 200, Pages 1–41https://doi.org/10.1145/3505244Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input ...
- research-articleJuly 2022
Event Camera Survey and Extension Application to Semantic Segmentation
IPMV '22: Proceedings of the 4th International Conference on Image Processing and Machine VisionPages 115–121https://doi.org/10.1145/3529446.3529465Event cameras are a kind of radically novel vision sensors. Unlike traditional standard cameras which acquire full images at a fixed rate, event cameras capture brightness changes for each pixel asynchronously. As a result, the output of event camera is ...
- research-articleAugust 2021
Sustainable society with a touchless solution using UbiMouse under the pandemic of COVID-19
SIGGRAPH '21: ACM SIGGRAPH 2021 Emerging TechnologiesArticle No.: 12, Pages 1–4https://doi.org/10.1145/3450550.3470532This paper introduces a new artificial intelligence software which is capable of controlling devices using fingers in the air. With Ubimouse, touch-panels, restaurant ordering systems, ATM systems, and etc., which are commonly used by various people in ...
- research-articleOctober 2020
SRHEN: Stepwise-Refining Homography Estimation Network via Parsing Geometric Correspondences in Deep Latent Space
MM '20: Proceedings of the 28th ACM International Conference on MultimediaPages 3063–3071https://doi.org/10.1145/3394171.3413870The crux of homography estimation is that the homography is characterized by the geometric correspondences between two related images rather than appearance features, which differs from typical image recognition tasks. Existing methods either decompose ...
- research-articleJanuary 2020
Kymatio: scattering transforms in Python
- Mathieu Andreux,
- Tomás Angles,
- Georgios Exarchakisgeo,
- Robertozzi Leonardu,
- Gaspar Rochette,
- Louis Thiry,
- John Zarka,
- Stéphane Mallat,
- Joakim Andén,
- Eugene Belilovsky,
- Joan Bruna,
- Vincent Lostanlen,
- Muawiz Chaudhary,
- Matthew J. Hirn,
- Edouard Oyallon,
- Sixin Zhang,
- Carmine Cella,
- Michael Eickenberg
The Journal of Machine Learning Research (JMLR), Volume 21, Issue 1Article No.: 60, Pages 2256–2261The wavelet scattering transform is an invariant and stable signal representation suitable for many signal processing and machine learning applications. We present the Kymatio software package, an easy-to-use, high-performance Python implementation of the ...
- research-articleNovember 2019
Inferring Context from Pixels for Multimodal Image Classification
- Manan Shah,
- Krishnamurthy Viswanathan,
- Chun-Ta Lu,
- Ariel Fuxman,
- Zhen Li,
- Aleksei Timofeev,
- Chao Jia,
- Chen Sun
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementPages 189–198https://doi.org/10.1145/3357384.3357987Image classification models take image pixels as input and predict labels in a predefined taxonomy. While contextual information (e.g. text surrounding an image) can provide valuable orthogonal signals to improve classification, the typical setting in ...
- research-articleJuly 2019
PlanIT: planning and instantiating indoor scenes with relation graph and spatial prior networks
ACM Transactions on Graphics (TOG), Volume 38, Issue 4Article No.: 132, Pages 1–15https://doi.org/10.1145/3306346.3322941We present a new framework for interior scene synthesis that combines a high-level relation graph representation with spatial prior neural networks. We observe that prior work on scene synthesis is divided into two camps: object-oriented approaches (...
- research-articleJanuary 2019
All convolutional neural networks for radar-based precipitation nowcasting
Procedia Computer Science (PROCS), Volume 150, Issue CPages 186–192https://doi.org/10.1016/j.procs.2019.02.036AbstractToday deep learning is taking its rise in hydrometeorological applications, and it is critical to extensively evaluate its prediction performance and robustness. In our study, we use deep all convolutional neural networks for radar-based ...
- research-articleAugust 2018
A Distributed Semi-Supervised Platform for DNase-Seq Data Analytics using Deep Generative Convolutional Networks
BCB '18: Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health InformaticsPages 244–253https://doi.org/10.1145/3233547.3233601A deep learning approach for analyzing DNase-seq datasets is presented, which has promising potentials for unraveling biological underpinnings on transcription regulation mechanisms. Further understanding of these mechanisms can lead to important ...
- research-articleJuly 2018
Deep convolutional priors for indoor scene synthesis
ACM Transactions on Graphics (TOG), Volume 37, Issue 4Article No.: 70, Pages 1–14https://doi.org/10.1145/3197517.3201362We present a convolutional neural network based approach for indoor scene synthesis. By representing 3D scenes with a semantically-enriched image-based representation based on orthographic top-down views, we learn convolutional object placement priors ...
- posterApril 2018
Siamese Cookie Embedding Networks for Cross-Device User Matching
WWW '18: Companion Proceedings of the The Web Conference 2018Pages 85–86https://doi.org/10.1145/3184558.3186941Over the last decade, the number of devices per person has increased substantially. This poses a challenge for cookie-based personalization applications, such as online search and advertising, as it narrows the personalization signal to a single device ...