Expertini Research Research

Browse Research Papers

3,601+ open-access research outputs.

โœ• Clear
๐Ÿ” memory ๐Ÿ“‚ Engineering
Showing 3601 results for "memory" in Engineering
Engineering Preprint PDF DOI

Optimization of DNN-based speaker verification model through efficient quantization technique

Yeona Hong, Woo-Jin Chung, Hong-Goo Kang ยท 2024

As Deep Neural Networks (DNNs) rapidly advance in various fields, including speech verification, they typically involve high computational costs and substantial memory consumption, which can be challeโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution

Congrui Fu, Hui Yuan, Shiqi Jiang, Guanghui Zhang, Liquan Shen, Raouf Hamzaoui ยท 2024

By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficienโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

An Economic Framework for 6-DoF Grasp Detection

Xiao-Ming Wu, Jia-Feng Cai, Jian-Jian Jiang, Dian Zheng, Yi-Lin Wei, Wei-Shi Zheng ยท 2024

Robotic grasping in clutters is a fundamental task in robotic manipulation. In this work, we propose an economic framework for 6-DoF grasp detection, aiming to economize the resource cost in training โ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

MemWarp: Discontinuity-Preserving Cardiac Registration with Memorized Anatomical Filters

Hang Zhang, Xiang Chen, Renjiu Hu, Dongdong Liu, Gaolei Li, Rongguang Wang ยท 2024

Many existing learning-based deformable image registration methods impose constraints on deformation fields to ensure they are globally smooth and continuous. However, this assumption does not hold inโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition

Jingjing Xu, Wei Zhou, Zijian Yang, Eugen Beck, Ralf Schlueter ยท 2024

Varying-size models are often required to deploy ASR systems under different hardware and/or application constraints such as memory and latency. To avoid redundant training and optimization efforts foโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Latent Space Imaging

Matheus Souza, Yidan Zheng, Kaizhang Kang, Yogeshwar Nath Mishra, Qiang Fu, Wolfgang Heidrich ยท 2024

Digital imaging systems have traditionally relied on brute-force measurement and processing of pixels arranged on regular grids. In contrast, the human visual system performs significant data reductioโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Enhancing Robotic Arm Activity Recognition with Vision Transformers and Wavelet-Transformed Channel State Information

Rojin Zandi, Kian Behzad, Elaheh Motamedi, Hojjat Salehinejad, Milad Siami ยท 2024

Vision-based methods are commonly used in robotic arm activity recognition. These approaches typically rely on line-of-sight (LoS) and raise privacy concerns, particularly in smart home applications. โ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Poisson Ordinal Network for Gleason Group Estimation Using Bi-Parametric MRI

Yinsong Xu, Yipei Wang, Ziyi Shen, Iani J.M.B. Gayo, Natasha Thorley, Shonit Punwani, Aidong Men, Dean Barratt, Qingchao Chen, Yipeng Hu ยท 2024

The Gleason groups serve as the primary histological grading system for prostate cancer, providing crucial insights into the cancer's potential for growth and metastasis. In clinical practice, patholoโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Ternary Spike-based Neuromorphic Signal Processing System

Shuai Wang, Dehao Zhang, Ammar Belatreche, Yichen Xiao, Hongyu Qing, Wenjie We, Malu Zhang, Yang Yang ยท 2024

Deep Neural Networks (DNNs) have been successfully implemented across various signal processing fields, resulting in significant enhancements in performance. However, DNNs generally require substantiaโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Space Adaptive Search for Nonholonomic Mobile Robots Path Planning

Qi Wang ยท 2024

Path planning for a nonholonomic mobile robot is a challenging problem. This paper proposes a novel space adaptive search (SAS) approach that greatly reduces the computation cost of nonholonomic mobilโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation

Yuxuan Kuang, Junjie Ye, Haoran Geng, Jiageng Mao, Congyue Deng, Leonidas Guibas, He Wang, Yue Wang ยท 2024

This work proposes a retrieve-and-transfer framework for zero-shot robotic manipulation, dubbed RAM, featuring generalizability across various objects, environments, and embodiments. Unlike existing aโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

MetaLoco: Universal Quadrupedal Locomotion with Meta-Reinforcement Learning and Motion Imitation

Fatemeh Zargarbashi, Fabrizio Di Giuro, Jin Cheng, Dongho Kang, Bhavya Sukhija, Stelian Coros ยท 2024

This work presents a meta-reinforcement learning approach to develop a universal locomotion control policy capable of zero-shot generalization across diverse quadrupedal platforms. The proposed methodโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Specification-guided temporal logic control for stochastic systems: a multi-layered approach

Birgit C. van Huijgevoort, Ruohan Wang, Sadegh Soudjani, Sofie Haesaert ยท 2024

Designing controllers to satisfy temporal requirements has proven to be challenging for dynamical systems that are affected by uncertainty. This is mainly due to the states evolving in a continuous unโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

BasisN: Reprogramming-Free RRAM-Based In-Memory-Computing by Basis Combination for Deep Neural Networks

Amro Eldebiky, Grace Li Zhang, Xunzhao Yin, Cheng Zhuo, Ing-Chao Lin, Ulf Schlichtmann, Bing Li ยท 2024

Deep neural networks (DNNs) have made breakthroughs in various fields including image recognition and language processing. DNNs execute hundreds of millions of multiply-and-accumulate (MAC) operationsโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Ultra-Lightweight Collaborative Mapping for Robot Swarms

Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini ยท 2024

A key requirement in robotics is the ability to simultaneously self-localize and map a previously unknown environment, relying primarily on onboard sensing and computation. Achieving fully onboard accโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging

Zhipeng Deng, Luyang Luo, Hao Chen ยท 2024

The right to be forgotten, as stated in most data regulations, poses an underexplored challenge in federated learning (FL), leading to the development of federated unlearning (FU). However, current FUโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Off-Grid Ultrasound Imaging by Stochastic Optimization

Vincent van de Schaft, Oisin Nolan, Ruud J. G. van Sloun ยท 2024

Ultrasound images formed by delay-and-sum beamforming are plagued by artifacts that only clear up after compounding many transmissions. Some prior works pose imaging as an inverse problem. This approaโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Universal Plans: One Action Sequence to Solve Them All!

Kalle G. Timperi, Alexander J. LaValle, Steven M. LaValle ยท 2024

This paper introduces the notion of a universal plan, which when executed, is guaranteed to solve all planning problems in a category, regardless of the obstacles, initial state, and goal set. Such plโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Accompanied Singing Voice Synthesis with Fully Text-controlled Melody

Ruiqi Li, Zhiqing Hong, Yongqi Wang, Lichao Zhang, Rongjie Huang, Siqi Zheng, Zhou Zhao ยท 2024

Text-to-song (TTSong) is a music generation task that synthesizes accompanied singing voices. Current TTSong methods, inherited from singing voice synthesis (SVS), require melody-related information tโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

Hierarchical Decoupling Capacitor Optimization for Power Distribution Network of 2.5D ICs with Co-Analysis of Frequency and Time Domains Based on Deep Reinforcement Learning

Yuanyuan Duan, Haiyang Feng, Zhiping Yu, Hanming Wu, Leilai Shao, Xiaolei Zhu ยท 2024

With the growing need for higher memory bandwidth and computation density, 2.5D design, which involves integrating multiple chiplets onto an interposer, emerges as a promising solution. However, this โ€ฆ

Read Paper โ†’
โ† Prev Page 63 of 181 Next โ†’