Search Results for author: Wu

Found 14 papers, 4 papers with code

Relay-Assisted Carrier Aggregation (RACA) Uplink System for Enhancing Data Rate of Extended Reality (XR)

no code implementations2 Jul 2024 Chi-Wei Chen, Wen-Chiao Tsai, Lung-Sheng Tsai, An-Yeu, Wu

In Extended Reality (XR) applications, high data rates and low latency are crucial for immersive experiences.

LATTE: Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer

no code implementations11 Apr 2024 Jiing-Ping Wang, Ming-Guang Lin, An-Yeu, Wu

With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer.

MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer

no code implementations26 Jan 2024 Yu-Shan Tai, An-Yeu, Wu

However, without considering the asymmetry in activations and relying on hand-crafted settings, these methods often struggle to maintain performance under low-bit quantization.

Quantization

Music ControlNet: A model similar to SD ControlNetD that can accurately control music generation

1 code implementation . 2023 Wu, Shih-Lun and Donahue, Chris and Watanabe, Shinji and Bryan, Nicholas J.

While the image-domain Uni-ControlNet method already allows generation with any subset of controls, we devise a new strategy to allow creators to input controls that are only partially specified in time.

Music Generation Text-to-Music Generation

TSPTQ-ViT: Two-scaled post-training quantization for vision transformer

no code implementations22 May 2023 Yu-Shan Tai, Ming-Guang Lin, An-Yeu, Wu

Due to the non-normally distributed values after Softmax and GeLU, post-training quantization on ViTs results in severe accuracy degradation.

Quantization

C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication-Efficient Split Learning

1 code implementation25 Jul 2022 Cheng-Yen Hsieh, Yu-Chuan Chuang, An-Yeu, Wu

Based on the simulation results on CIFAR-10 and CIFAR-100, our method achieves a 16x compression ratio with negligible accuracy drops compared with the vanilla SL.

MAUS: A Dataset for Mental Workload Assessmenton N-back Task Using Wearable Sensor

1 code implementation3 Nov 2021 Win-Ken Beh, Yi-Hsuan Wu, An-Yeu, Wu

Besides, we also presents a reproducible baseline system as a preliminary benchmark (The code of the baseline system on MAUS dataset is available on Github: https://github. com/rickwu11/MAUS\_dataset\_baseline\_system), which testing accuracy are 71. 6 %, 66. 7 %, and 59. 9 % in ECG, fingertip PPG, wristband PPG, respectively.

Electrocardiography (ECG) Sleep Quality

High-resolution global irrigation prediction with Sentinel-2 30m data

no code implementations9 Dec 2020 Weixin, Wu, Sonal Thakkar, Will Hawkins, Puya Vahabi, Alberto Todeschini

An accurate and precise understanding of global irrigation usage is crucial for a variety of climate science efforts.

Clustering Vocal Bursts Intensity Prediction

Causal Mosaic: Cause-Effect Inference via Nonlinear ICA and Ensemble Method

no code implementations7 Jan 2020 Pengzhou, Wu, Kenji Fukumizu

We address the problem of distinguishing cause from effect in bivariate setting.

AdaBoost-assisted Extreme Learning Machine for Efficient Online Sequential Classification

no code implementations16 Sep 2019 Yi-Ta Chen, Yu-Chuan Chuang, An-Yeu, Wu

In this paper, we propose an AdaBoost-assisted extreme learning machine for efficient online sequential classification (AOS-ELM).

General Classification

Deep Learning for Epidemiological Predictions

no code implementations The 41st International ACM SIGIR Conference 2018 Wu, Yuexin Yang, Yiming Nishiura, Hiroshi Saitoh, Masaya

Predicting new and urgent trends in epidemiological data is an important problem for public health, and has attracted increasing attention in the data mining and machine learning communities.

Epidemiology GPR +2

Integration of LiDAR and Hyperspectral Data for Land-cover Classification: A Case Study

no code implementations9 Jul 2017 Pedram Ghamisi, Gabriele Cavallaro, Dan, Wu, Jon Atli Benediktsson, Antonio Plaza

In this paper, an approach is proposed to fuse LiDAR and hyperspectral data, which considers both spectral and spatial information in a single framework.

Attribute General Classification +1

TF-Label: a Topological-Folding Labeling Scheme for Reachability Querying in a Large Graph

1 code implementation1 Jun 2013 Cheng, J., Huang, S., Wu, H., Fu, A.W.

We propose TF-label, an efficient and scalable labeling scheme for processing reachability queries.

Cannot find the paper you are looking for? You can Submit a new open access paper.