Hamid Eghbal-zadeh

发表

Iterative knowledge distillation in R-CNNs for weakly-labeled semi-supervised sound event detection

G. Widmer, Khaled Koutini, Hamid Eghbal-zadeh, 2018, DCASE.

Timbral and Semantic Features for Music Playlists

Andreu Vall, Hamid Eghbal-zadeh, M. Schedl, 2016 .

Context-Adaptive Reinforcement Learning using Unsupervised Learning of Context Variables

Hamid Eghbal-zadeh, 2020, Preregister@NeurIPS.

A COSINE-DISTANCE BASED NEURAL NETWORK FOR MUSIC ARTIST RECOGNITION USING RAW I-VECTOR FEATURES

Hamid Eghbal-zadeh, 2016 .

Few-Shot Learning by Dimensionality Reduction in Gradient Space

S. Hochreiter, Markus Holzleitner, Johannes Brandstetter, 2022, 2206.03483.

History Compression via Language Models in Reinforcement Learning

Vihang P. Patil, S. Hochreiter, Markus Holzleitner, 2022, International Conference on Machine Learning.

Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning

Vihang P. Patil, S. Hochreiter, Hamid Eghbal-zadeh, 2022, CoLLAs.

R EACTIVE E XPLORATION TO C OPE WITH N ON -S TATIONARITY IN L IFELONG R EINFORCEMENT L EARNING

Vihang P. Patil, S. Hochreiter, Hamid Eghbal-zadeh, 2022 .

History Compression via Language Models in Reinforcement Learning

Vihang P. Patil, S. Hochreiter, Markus Holzleitner, 2022, ICML.

Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning

Vihang P. Patil, S. Hochreiter, Hamid Eghbal-zadeh, 2022, CoLLAs.

A Dataset Perspective on Offline Reinforcement Learning

Vihang P. Patil, S. Hochreiter, Hamid Eghbal-zadeh, 2021, CoLLAs.

Feature-combination hybrid recommender systems for automated music playlist continuation

Markus Schedl, Gerhard Widmer, Hamid Eghbal-zadeh, 2019, User Modeling and User-Adapted Interaction.

Music Playlist Continuation by Learning from Hand-Curated Examples and Song Features: Alleviating the Cold-Start Problem for Rare and Out-of-Set Songs

Markus Schedl, Hamid Eghbal-zadeh, Andreu Vall, 2017, DLRS@RecSys.

Efficient Training of Audio Transformers with Patchout

Jan Schlüter, G. Widmer, Khaled Koutini, 2021, INTERSPEECH.

The balancing principle for parameter choice in distance-regularized domain adaptation

Bernhard Nessler, Hamid Eghbal-zadeh, W. Zellinger, 2021, NeurIPS.

Receptive-field-regularized CNN variants for acoustic scene classification pdf

Gerhard Widmer, Khaled Koutini, Hamid Eghbal-zadeh, 2019, DCASE.

History Compression via Language Models in Reinforcement Learning

S. Hochreiter, Markus Holzleitner, Hamid Eghbal-zadeh, 2022, ICML.

Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks

Gerhard Widmer, Khaled Koutini, Hamid Eghbal-zadeh, 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

I-Vectors for Timbre-Based Music Similarity and Music Artist Classification

Markus Schedl, Gerhard Widmer, Hamid Eghbal-zadeh, 2015, ISMIR.

Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments pdf

Nicolas Turpault, Romain Serizel, Hamid Eghbal-Zadeh, 2018, DCASE.

Few-Shot Learning by Dimensionality Reduction in Gradient Space

S. Hochreiter, Markus Holzleitner, Johannes Brandstetter, 2022, CoLLAs.

Likelihood Estimation for Generative Adversarial Networks pdf

Gerhard Widmer, Hamid Eghbal-zadeh, G. Widmer, 2017, ArXiv.

Movie genome: alleviating new item cold start in movie recommendation

Markus Schedl, Bogdan Ionescu, Paolo Cremonesi, 2019, User Modeling and User-Adapted Interaction.

Audio-visual encoding of multimedia content for enhancing movie recommendations

Markus Schedl, Paolo Cremonesi, Yashar Deldjoo, 2018, RecSys.

The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification

Gerhard Widmer, Khaled Koutini, Hamid Eghbal-zadeh, 2019, 2019 27th European Signal Processing Conference (EUSIPCO).

CP-JKU SUBMISSIONS FOR DCASE-2016 : A HYBRID APPROACH USING BINAURAL I-VECTORS AND DEEP CONVOLUTIONAL NEURAL NETWORKS

Gerhard Widmer, Bernhard Lehner, Hamid Eghbal-Zadeh, 2016 .

F EW -S HOT L EARNING BY D IMENSIONALITY R EDUCTION IN G RADIENT S PACE

S. Hochreiter, Markus Holzleitner, Johannes Brandstetter, 2022 .

An automatic drum machine with touch UI based on a generative neural network

Peter Knees, Hamid Eghbal-Zadeh, Richard Vogl, 2019, IUI Companion.

InfODist: Online distillation with Informative rewards improves generalization in Curriculum Learning

S. Hochreiter, Markus Holzleitner, Michael Kopp, 2022 .

A hybrid approach with multi-channel i-vectors and convolutional neural networks for acoustic scene classification

Gerhard Widmer, Hamid Eghbal-zadeh, Bernhard Lehner, 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

Feature-combination hybrid recommender systems for automated music playlist continuation

Keki M. Burjorjee, G. Widmer, Andreu Vall, 2019, User Modeling and User-Adapted Interaction.

Deep SNP: An End-to-end Deep Neural Network with Attention-based Localization for Break-point Detection in SNP Array Genomic data

Gerhard Widmer, Khaled Koutini, Hamid Eghbal-zadeh, 2018, bioRxiv.

CLASSIFYING SHORT ACOUSTIC SCENES WITH I-VECTORS AND CNNS : CHALLENGES AND OPTIMISATIONS FOR THE 2017 DCASE ASC TASK

Gerhard Widmer, Khaled Koutini, Hamid Eghbal-zadeh, 2017 .

Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification pdf

Gerhard Widmer, Khaled Koutini, Hamid Eghbal-zadeh, 2019, DCASE.

On the Interrelation Between Listener Characteristics and the Perception of Emotions in Classical Orchestra Music

Markus Schedl, Agustín Martorell, Hamid Eghbal-Zadeh, 2018, IEEE Transactions on Affective Computing.

On Conditioning GANs to Hierarchical Ontologies pdf

Hamid Eghbal-zadeh, Thomas Hoch, Lukas Fischer, 2019, DEXA Workshops.

Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs pdf

Gerhard Widmer, Khaled Koutini, Verena Haunschmid, 2019, MediaEval.