Picture for Marios Pattichis

Marios Pattichis

DT-LSD: Deformable Transformer-based Line Segment Detection

Add code
Nov 20, 2024
Viaarxiv icon

Bilingual Speech Recognition by Estimating Speaker Geometry from Video Data

Add code
Dec 26, 2021
Figure 1 for Bilingual Speech Recognition by Estimating Speaker Geometry from Video Data
Figure 2 for Bilingual Speech Recognition by Estimating Speaker Geometry from Video Data
Figure 3 for Bilingual Speech Recognition by Estimating Speaker Geometry from Video Data
Figure 4 for Bilingual Speech Recognition by Estimating Speaker Geometry from Video Data
Viaarxiv icon

Fast 2D Convolutions and Cross-Correlations Using Scalable Architectures

Add code
Dec 24, 2021
Figure 1 for Fast 2D Convolutions and Cross-Correlations Using Scalable Architectures
Figure 2 for Fast 2D Convolutions and Cross-Correlations Using Scalable Architectures
Figure 3 for Fast 2D Convolutions and Cross-Correlations Using Scalable Architectures
Figure 4 for Fast 2D Convolutions and Cross-Correlations Using Scalable Architectures
Viaarxiv icon

Fast and Scalable Computation of the Forward and Inverse Discrete Periodic Radon Transform

Add code
Dec 24, 2021
Figure 1 for Fast and Scalable Computation of the Forward and Inverse Discrete Periodic Radon Transform
Figure 2 for Fast and Scalable Computation of the Forward and Inverse Discrete Periodic Radon Transform
Figure 3 for Fast and Scalable Computation of the Forward and Inverse Discrete Periodic Radon Transform
Figure 4 for Fast and Scalable Computation of the Forward and Inverse Discrete Periodic Radon Transform
Viaarxiv icon

Facial Recognition in Collaborative Learning Videos

Add code
Oct 25, 2021
Figure 1 for Facial Recognition in Collaborative Learning Videos
Figure 2 for Facial Recognition in Collaborative Learning Videos
Figure 3 for Facial Recognition in Collaborative Learning Videos
Figure 4 for Facial Recognition in Collaborative Learning Videos
Viaarxiv icon

Adaptive Video Encoding For Different Video Codecs

Add code
May 17, 2021
Figure 1 for Adaptive Video Encoding For Different Video Codecs
Figure 2 for Adaptive Video Encoding For Different Video Codecs
Figure 3 for Adaptive Video Encoding For Different Video Codecs
Figure 4 for Adaptive Video Encoding For Different Video Codecs
Viaarxiv icon

Interpretable Neural Networks for Predicting Mortality Risk using Multi-modal Electronic Health Records

Add code
Jan 23, 2019
Figure 1 for Interpretable Neural Networks for Predicting Mortality Risk using Multi-modal Electronic Health Records
Figure 2 for Interpretable Neural Networks for Predicting Mortality Risk using Multi-modal Electronic Health Records
Figure 3 for Interpretable Neural Networks for Predicting Mortality Risk using Multi-modal Electronic Health Records
Figure 4 for Interpretable Neural Networks for Predicting Mortality Risk using Multi-modal Electronic Health Records
Viaarxiv icon