Results 61 to 70 of about 25,642 (150)

Synthetic Data Enhancement and Network Compression Technology of Monocular Depth Estimation for Real-Time Autonomous Driving System

open access: yesSensors
Accurate 3D image recognition, critical for autonomous driving safety, is shifting from the LIDAR-based point cloud to camera-based depth estimation technologies driven by cost considerations and the point cloud’s limitations in detecting distant small ...
Woomin Jun, Jisang Yoo, Sungjin Lee
doaj   +1 more source

Feasibility Study of Edge Computing Empowered by Artificial Intelligence—A Quantitative Analysis Based on Large Models

open access: yesBig Data and Cognitive Computing
The advancement of artificial intelligence (AI) demands significant data and computational resources that have an adverse impact on the environment. To address this issue, a novel computing architecture that is both energy efficient and eco-friendly is ...
Yan Chen   +3 more
doaj   +1 more source

Angular Deep Supervised Hashing for Image Retrieval

open access: yesIEEE Access, 2019
Deep learning based image hashing methods learn hash codes by using powerful feature extractors and nonlinear transformations to achieve highly efficient image retrieval. For most end-to-end deep hashing methods, the supervised learning process relies on
Chang Zhou   +8 more
doaj   +1 more source

Quantized Microcavity Polariton Lasing Based on InGaN Localized Excitons

open access: yesNanomaterials
Exciton–polaritons, which are bosonic quasiparticles with an extremely low mass, play a key role in understanding macroscopic quantum effects related to Bose–Einstein condensation (BEC) in solid-state systems.
Huying Zheng   +10 more
doaj   +1 more source

Optimal Number of Choices in Rating Contexts

open access: yesBig Data and Cognitive Computing, 2019
In many settings, people must give numerical scores to entities from a small discrete set—for instance, rating physical attractiveness from 1–5 on dating sites, or papers from 1–10 for conference reviewing.
Sam Ganzfried, Farzana Beente Yusuf
doaj   +1 more source

Quantized Dirac operators

open access: yesCzechoslovak Journal of Physics, 2000
To appear in the Proceedings of the Quantum Groups And Integrable Systems meeting in Prag, June 22-24 2000.
openaire   +2 more sources

QuantNAS for Super Resolution: Searching for Efficient Quantization-Friendly Architectures Against Quantization Noise

open access: yesIEEE Access
This work aims to develop an automated procedure for discovering new, efficient solutions that can be effectively quantized in mixed-precision mode with minimal degradation.
Egor Shvetsov   +6 more
doaj   +1 more source

SpQuant-SNN: ultra-low precision membrane potential with sparse activations unlock the potential of on-device spiking neural networks applications

open access: yesFrontiers in Neuroscience
Spiking neural networks (SNNs) have received increasing attention due to their high biological plausibility and energy efficiency. The binary spike-based information propagation enables efficient sparse computation in event-based and static computer ...
Ahmed Hasssan   +3 more
doaj   +1 more source

Model-Based Speech Signal Coding Using Optimized Temporal Decomposition for Storage and Broadcasting Applications

open access: yesEURASIP Journal on Advances in Signal Processing, 2003
A dynamic programming-based optimization strategy for a temporal decomposition (TD) model of speech and its application to low-rate speech coding in storage and broadcasting is presented.
Bradley Alan B   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy