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-articleSeptember 2024JUST ACCEPTED
Performance Analysis of CNN Inference/Training with Convolution and Non-Convolution Operations on ASIC Accelerators
- Hadi Esmaeilzadeh,
- Soroush Ghodrati,
- Andrew B. Kahng,
- Sean Kinzer,
- Susmita Dey Manasi,
- Sachin S. Sapatnekar,
- Zhiang Wang
ACM Transactions on Design Automation of Electronic Systems (TODAES), Just Accepted https://doi.org/10.1145/3696665Today’s performance analysis frameworks for deep learning accelerators suffer from two significant limitations. First, although modern convolutional neural networks (CNNs) consist of many types of layers other than convolution, especially during training, ...
- research-articleSeptember 2024
Deepfake Detection Using Spatiotemporal Transformer
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Volume 20, Issue 11Article No.: 345, Pages 1–21https://doi.org/10.1145/3643030Recent advances in generative models and the availability of large-scale benchmarks have made deepfake video generation and manipulation easier. Nowadays, the number of new hyper-realistic deepfake videos used for negative purposes is dramatically ...
- research-articleAugust 2024
Cognitive Hybrid Deep Learning-based Multi-modal Sentiment Analysis for Online Product Reviews
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Volume 23, Issue 8Article No.: 113, Pages 1–14https://doi.org/10.1145/3615356Recently the field of sentiment analysis has gained a lot of attraction in literature. The idea that a machine can dynamically spot the text’s sentiments is fascinating. In this paper, we propose a method to classify the textual sentiments in Twitter ...
- ArticleAugust 2024
Improved CNN Model Using Innovative Adaptive-DropMessage for Gomoku Game
Advanced Intelligent Computing Technology and ApplicationsPages 72–83https://doi.org/10.1007/978-981-97-5588-2_7AbstractConvolutional Neural Networks (CNNs) has been used in many Gomoku AI systems. This paper introduces the innovative Adaptive-Drop Message method within the CNN framework. This method, combined with techniques including attention mechanisms, ...
- ArticleAugust 2024
YOLO-Underwater: A Real-Time Object Detection Framework for Enhanced Underwater Robotics Operations
Advanced Intelligent Computing Technology and ApplicationsPages 51–61https://doi.org/10.1007/978-981-97-5675-9_5AbstractWe propose a YOLOv7-underwater model for real-time underwater object detection, specifically designed to meet the requirements of underwater robotics. The model integrates a new ConvNeXt convolutional layer structure and a wide receptive field ...
-
- research-articleAugust 2024
CSASNet—A Crop Leaf Disease Identification Method Based on Improved ShuffleNetV2
Automatic Control and Computer Sciences (ACCS), Volume 58, Issue 4Pages 408–419https://doi.org/10.3103/S0146411624700524AbstractIn identifying crop leaf diseases, Due to the complex nature of the disease symptoms. There may be variations in disease symptoms with similar characteristics and similarities in disease symptoms with different elements. This can make it ...
- research-articleAugust 2024
CoSense: Deep Learning Augmented Sensing for Coexistence with Networking in Millimeter-Wave Picocells
ACM Transactions on Internet of Things (TIOT), Volume 5, Issue 3Article No.: 17, Pages 1–35https://doi.org/10.1145/3670415We present CoSense, a system that enables coexistence of networking and sensing on next-generation millimeter-wave (mmWave) picocells for traffic monitoring and pedestrian safety at intersections in all weather conditions. Although existing wireless ...
- ArticleJuly 2024
Spike Detection in Deep Brain Stimulation Surgery with Convolutional Neural Networks
AbstractThe paper addresses issues concerning the application of deep learning in deep brain stimulation (DBS) neurosurgery. DBS is a functional neurosurgical procedure used to treat conditions in the central nervous system that arise from improper ...
- abstractAugust 2024
A Review of Randomness Techniques in Deep Neural Networks
- Mohammed Ghaith Altarabichi,
- Sławomir Nowaczyk,
- Sepideh Pashami,
- Peyman Sheikholharam Mashhadi,
- Julia Handl
GECCO '24 Companion: Proceedings of the Genetic and Evolutionary Computation Conference CompanionPages 23–24https://doi.org/10.1145/3638530.3664077This paper investigates the effects of various randomization techniques on Deep Neural Networks (DNNs) learning performance. We categorize the existing randomness techniques into four key types: injection of noise/randomness at the data, model structure, ...
- ArticleJune 2024
Investigation on the Use of Mora in Assessment of L2 Speakers’ Japanese Language Proficiency
AbstractThis paper presents the analysis on the language use of non-native (L2) Japanese speakers with focus on their proficiency in group discussion conversations. Due to the demographic development the necessity to close the resulting gap with foreign ...
- research-articleJune 2024
Investigation of Visual Language Landscape of Tourist Attractions from Multimodal Perspective
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Volume 23, Issue 6Article No.: 92, Pages 1–17https://doi.org/10.1145/3638049With the development of economic globalization, the tourism industry has been welcomed by the public. The visual language landscape of tourist attractions can not only assist tourists to play and watch the project, but if it is properly planned, the ...
- research-articleJune 2024
Application of Intelligent Image Recognition and Digital Media Art in the Inheritance of Black Pottery Intangible Cultural Heritage
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Volume 23, Issue 6Article No.: 82, Pages 1–15https://doi.org/10.1145/3597430With the development of science and technology, intelligent image recognition and digital media art are gradually applied to the inheritance of intangible cultural heritage. In the inheritance of black pottery, intelligent image recognition can help ...
- short-paperJune 2024
Exploring the Interplay between Facial Expression Recognition and Physical States
Interacción '24: Proceedings of the XXIV International Conference on Human Computer InteractionArticle No.: 22, Pages 1–5https://doi.org/10.1145/3657242.3658602This paper suggests a new viewpoint in Facial Expression Recognition (FER), moving beyond conventional approaches focused on understanding human emotions to include also physical states expressions such as pain and effort. These expressions involve ...
- research-articleJuly 2024
Crowd Movement Type Estimation in Video by Integral Optical Flow and Convolution Neural Network
Pattern Recognition and Image Analysis (SPPRIA), Volume 34, Issue 2Pages 266–274https://doi.org/10.1134/S1054661824700068AbstractThe paper proposes a new approach for crowd movement type estimation in video by combining convolutional neural network and integral optical flow. At first, main notions of crowd detection and tracking are given. Secondly, crowd movement features ...
- ArticleMay 2024
Improved Surface Defect Classification from a Simple Convolutional Neural Network by Image Preprocessing and Data Augmentation
- Francisco López de la Rosa,
- Lucía Moreno-Salvador,
- José L. Gómez-Sirvent,
- Rafael Morales,
- Roberto Sánchez-Reolid,
- Antonio Fernández-Caballero
Bioinspired Systems for Translational Applications: From Robotics to Social EngineeringPages 23–32https://doi.org/10.1007/978-3-031-61137-7_3AbstractConvolutional neural networks (CNNs) play an important role in an increasing number of image processing tasks. There is an obvious demand to improve their classification performance and efficiency. Current research in this area tends to focus on ...
- research-articleAugust 2024
YOLOv5-Z:A Target Detection Algorithm Suitable for New Theories of Medical Image Recognition
MIDA '24: Proceedings of the 2024 International Conference on Machine Intelligence and Digital ApplicationsPages 35–39https://doi.org/10.1145/3662739.3663382The enhanced YOLO algorithm YOLOv5-Z is designed for precise target detection. This paper primarily focuses on optimizing the YOLOv5 target detection model by refining the detection frame generation strategy, ensuring the generated rectangular outline ...
- short-paperJune 2024
CNN-LSTM based Spectrum Sensing in Full-Duplex-aided CR-IoT Networks
AICCONF '24: Proceedings of the Cognitive Models and Artificial Intelligence ConferencePages 270–272https://doi.org/10.1145/3660853.3660926In this paper, we propose a convolutional neural network-long and short-term memory (CNN-LSTM) based secure cooperative spectrum sensing (CSS) in full duplex-aided cognitive radio-Internet of things (CR-IoT) network. It enhances security by separating ...
- research-articleAugust 2024
Addressing Data Imbalance via Image Augmentation for Automated Quality Inspection in Steel Production
ICCTA '24: Proceedings of the 2024 10th International Conference on Computer Technology ApplicationsPages 174–181https://doi.org/10.1145/3674558.3674583Automated quality inspection is widely used in industry, however, there is often the problem of data imbalance, as defect samples occur less frequently during production leading to significant challenges in machine learning projects. Nevertheless, a ...
- research-articleJuly 2024
TabConv: Low-Computation CNN Inference via Table Lookups
CF '24: Proceedings of the 21st ACM International Conference on Computing FrontiersPages 180–188https://doi.org/10.1145/3649153.3649212Convolutional Neural Networks (CNNs) have demonstrated remarkable ability throughout the field of computer vision. However, CNN inference requires a large number of arithmetic operations making them expensive to deploy in hardware. Current approaches ...
- research-articleAugust 2024
Liver Tumor Classification from DCE-MRI images using Discriminative Learning
IMIP '24: Proceedings of the 2024 6th International Conference on Intelligent Medicine and Image ProcessingPages 22–28https://doi.org/10.1145/3669828.3669832Liver cancer remains a significant global health concern, and early-stage differential diagnosis and treatment can dramatically improve patient survival rates. However, current diagnostic methods are challenging and subjective, highlighting the need for ...