Search Results for author:
Found 12 papers, 7 papers with code
Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling
We propose a deep learning framework designed to significantly optimize bandwidth for motion-transfer-enabled video applications, including video conferencing, virtual reality interactions, health monitoring systems, and vision-based real-time anomaly detection.
MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts
Currently, the mainstream routing methods include dynamic routing and fixed routing.
Enhancing Bandwidth Efficiency for Video Motion Transfer Applications using Deep Learning Based Keypoint Prediction
Prediction of keypoints, to enable transmission using lower frames per second on the source device, is performed using a Variational Recurrent Neural Network (VRNN).
MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
Experiments reveal that models incorporating the proposed MiLe Loss can gain consistent performance improvement on downstream benchmarks.
Ranked #47 on
Multi-task Language Understanding
on MMLU
Gated Driver Attention Predictor
In this work, we explore the network connection gating mechanism for driver attention prediction (Gate-DAP).
Danlu Tongdu tablets treat lumbar spinal stenosis through reducing reactive oxygen species and apoptosis by regulating CDK2/CDK4/CDKN1A expression
Furthermore, the flow cytometry results showed that DLTD tablets efficiently reduced ROS content and inhibited rat neural stem cell apoptosis induced by hydrogen peroxide.
ViTASD: Robust Vision Transformer Baselines for Autism Spectrum Disorder Facial Diagnosis
Research progress in the field of ASD facial analysis in pediatric patients has been hindered due to a lack of well-established baselines.
A Two-Stage Approach to Device-Robust Acoustic Scene Classification
To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed.
Ranked #1 on
Acoustic Scene Classification
on TAU Urban Acoustic Scenes 2019
(using extra training data)
An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances
In contrast to building scene models with whole utterances, the ASM-removed sub-utterances, i. e., acoustic utterances without stop acoustic segments, are then used as inputs to the AlexNet-L back-end for final classification.
Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
On Task 1b development data set, we achieve an accuracy of 96. 7\% with a model size smaller than 500KB.
DocUNet: Document Image Unwarping via a Stacked U-Net
The network is trained on this dataset with various data augmentations to improve its generalization ability.
Ranked #4 on
SSIM
on DocUNet
(using extra training data)
Coherent Parametric Contours for Interactive Video Object Segmentation
Interactive video segmentation systems aim at producing sub-pixel-level object boundaries for visual effect applications.
