Picture for Muhammad Haroon Yousaf

Muhammad Haroon Yousaf

Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach

Add code
Aug 14, 2024
Viaarxiv icon

Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plan

Add code
Apr 16, 2024
Viaarxiv icon

Classification of Potholes Based on Surface Area Using Pre-Trained Models of Convolutional Neural Network

Add code
Sep 29, 2023
Viaarxiv icon

Single-branch Network for Multimodal Training

Add code
Mar 10, 2023
Viaarxiv icon

Speaker Recognition in Realistic Scenario Using Multimodal Data

Add code
Feb 25, 2023
Viaarxiv icon

Learning Branched Fusion and Orthogonal Projection for Face-Voice Association

Add code
Aug 22, 2022
Figure 1 for Learning Branched Fusion and Orthogonal Projection for Face-Voice Association
Figure 2 for Learning Branched Fusion and Orthogonal Projection for Face-Voice Association
Figure 3 for Learning Branched Fusion and Orthogonal Projection for Face-Voice Association
Figure 4 for Learning Branched Fusion and Orthogonal Projection for Face-Voice Association
Viaarxiv icon

Fusion and Orthogonal Projection for Improved Face-Voice Association

Add code
Dec 20, 2021
Figure 1 for Fusion and Orthogonal Projection for Improved Face-Voice Association
Figure 2 for Fusion and Orthogonal Projection for Improved Face-Voice Association
Figure 3 for Fusion and Orthogonal Projection for Improved Face-Voice Association
Figure 4 for Fusion and Orthogonal Projection for Improved Face-Voice Association
Viaarxiv icon

Cross-modal Speaker Verification and Recognition: A Multilingual Perspective

Add code
Apr 28, 2020
Figure 1 for Cross-modal Speaker Verification and Recognition: A Multilingual Perspective
Figure 2 for Cross-modal Speaker Verification and Recognition: A Multilingual Perspective
Figure 3 for Cross-modal Speaker Verification and Recognition: A Multilingual Perspective
Figure 4 for Cross-modal Speaker Verification and Recognition: A Multilingual Perspective
Viaarxiv icon