Ahmed Imtiaz Humayun

Orcid: 0000-0002-9530-1134

According to our database1, Ahmed Imtiaz Humayun authored at least 29 papers between 2018 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Learning Transferable Features for Implicit Neural Representations.
CoRR, 2024

Self-Improving Diffusion Models with Synthetic Data.
CoRR, 2024

Understanding the Local Geometry of Generative Model Manifolds.
CoRR, 2024

On the Geometry of Deep Learning.
CoRR, 2024

ScaLES: Scalable Latent Exploration Score for Pre-Trained Generative Networks.
CoRR, 2024

Deep Networks Always Grok and Here is Why.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Self-Consuming Generative Models Go MAD.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Unicode Normalization and Grapheme Parsing of Indic Languages.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

2023
Training Dynamics of Deep Network Linear Regions.
CoRR, 2023

Abugida Normalizer and Parser for Unicode texts.
CoRR, 2023

OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking.
CoRR, 2023


SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Bengali Common Voice Speech Dataset for Automatic Speech Recognition.
CoRR, 2022

MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining.
Proceedings of the Tenth International Conference on Learning Representations, 2022

No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds.
Proceedings of the IEEE International Conference on Acoustics, 2022

Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
A Large Multi-target Dataset of Common Bengali Handwritten Graphemes.
Proceedings of the 16th International Conference on Document Analysis and Recognition, 2021

Wearing A Mask: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels.
Proceedings of the IEEE International Conference on Acoustics, 2021

Detection of Junctional Ectopic Tachycardia by Central Venous Pressure.
Proceedings of the Artificial Intelligence in Medicine, 2021

2020
Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks.
IEEE J. Biomed. Health Informatics, 2020

Multi-label Classification of Common Bengali Handwritten Graphemes: Dataset and Challenge.
CoRR, 2020

2019
X-Ray Image Compression Using Convolutional Recurrent Neural Networks.
Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics, 2019

End-to-end Sleep Staging with Raw Single Channel EEG using Deep Residual ConvNets.
Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics, 2019

2018
AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018.
CoRR, 2018

NumtaDB - Assembled Bengali Handwritten Digits.
CoRR, 2018

Predictive Real-Time Beat Tracking from Music for Embedded Application.
Proceedings of the IEEE 1st Conference on Multimedia Information Processing and Retrieval, 2018

An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification.
Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection.
Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2018


  Loading...