Search Results - "Tomen, Nergis"

Resolution Learning in Deep Convolutional Networks Using Scale-Space Theory by Pintea, Silvia L., Tomen, Nergis, Goes, Stanley F., Loog, Marco, van Gemert, Jan C.

“…Resolution in deep convolutional neural networks (CNNs) is typically bounded by the receptive field size through filter sizes, and subsampling layers or…”
Get full text

Benchmarking of hardware-efficient real-time neural decoding in brain–computer interfaces by Hueber, Paul, Tang, Guangzhi, Sifalakis, Manolis, Liaw, Hua-Peng, Micheli, Aurora, Tomen, Nergis, Liu, Yao-Hong

“…Designing processors for implantable closed-loop neuromodulation systems presents a formidable challenge owing to the constrained operational environment,…”
Get full text

Phase transitions in cortical dynamics explain improved information processing under attention by Tomen, Nergis, Ernst, Udo

“…Doc number: P126…”
Get full text

Spectral Leakage and Rethinking the Kernel Size in CNNs by Tomen, Nergis, van Gemert, Jan C.

“…Convolutional layers in CNNs implement linear filters which decompose the input into different frequency bands. However, most modern architectures neglect…”
Get full text

Marginally subcritical dynamics explain enhanced stimulus discriminability under attention by Tomen, Nergis, Rotermund, David, Ernst, Udo

“…Recent experimental and theoretical work has established the hypothesis that cortical neurons operate close to a critical state which describes a phase…”
Get full text

Pushing the boundaries of event subsampling in event-based video classification using CNNs by Araghi, Hesam, van Gemert, Jan, Tomen, Nergis

“…Event cameras offer low-power visual sensing capabilities ideal for edge-device applications. However, their high event rate, driven by high temporal details,…”
Get full text

Spectral Leakage and Rethinking the Kernel Size in CNNs by Tomen, Nergis, van Gemert, Jan

“…Convolutional layers in CNNs implement linear filters which decompose the input into different frequency bands. However, most modern architectures neglect…”
Get full text

Deep Continuous Networks by Tomen, Nergis, Pintea, Silvia L, van Gemert, Jan C

“…In International Conference on Machine Learning 2021 Jul 1 (pp. 10324-10335). PMLR CNNs and computational models of biological vision share some fundamental…”
Get full text

Resolution learning in deep convolutional networks using scale-space theory by Pintea, Silvia L, Tomen, Nergis, Goes, Stanley F, Loog, Marco, van Gemert, Jan C

“…IEEE Transactions on Image Processing, vol. 30, pp. 8342-8353, 2021 Resolution in deep convolutional neural networks (CNNs) is typically bounded by the…”
Get full text

VIPriors 4: Visual Inductive Priors for Data-Efficient Deep Learning Challenges by Bruintjes, Robert-Jan, Lengyel, Attila, Rios, Marcos Baptista, Kayhan, Osman Semih, Zambrano, Davide, Tomen, Nergis, van Gemert, Jan

“…The fourth edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop features two data-impaired challenges. These challenges…”
Get full text

Heart rate estimation in intense exercise videos by Napolean, Yeshwanth, Marwade, Anwesh, Tomen, Nergis, Alkemade, Puck, Eijsvogels, Thijs, van Gemert, Jan

“…Estimating heart rate from video allows non-contact health monitoring with applications in patient care, human interaction, and sports. Existing work can…”
Get full text

VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges by Bruintjes, Robert-Jan, Lengyel, Attila, Rios, Marcos Baptista, Kayhan, Osman Semih, Zambrano, Davide, Tomen, Nergis, van Gemert, Jan

“…The third edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop featured four data-impaired challenges, focusing on…”
Get full text

Frequency learning for structured CNN filters with Gaussian fractional derivatives by Saldanha, Nikhil, Pintea, Silvia L, van Gemert, Jan C, Tomen, Nergis

“…Frequency information lies at the base of discriminating between textures, and therefore between different objects. Classical CNN architectures limit the…”
Get full text

VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges by Lengyel, Attila, Bruintjes, Robert-Jan, Rios, Marcos Baptista, Kayhan, Osman Semih, Zambrano, Davide, Tomen, Nergis, van Gemert, Jan

“…The second edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges featured five data-impaired challenges, where models…”
Get full text

Top-Down Networks: A coarse-to-fine reimagination of CNNs by Lelekas, Ioannis, Tomen, Nergis, Pintea, Silvia L, van Gemert, Jan C

“…Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to…”
Get full text

Top-Down Networks: A coarse-to-fine reimagination of CNNs by Lelekas, Ioannis, Tomen, Nergis, Pintea, Silvia L., van Gemert, Jan C.

“…Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to…”
Get full text

Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems by Garcia, Alejandro Castañeda, van Gemert, Jan, Brinks, Daan, Tömen, Nergis

“…Extracting physical dynamical system parameters from videos is of great interest to applications in natural science and technology. The state-of-the-art in…”
Get full text

Deep activity propagation via weight initialization in spiking neural networks by Micheli, Aurora, Booij, Olaf, van Gemert, Jan, Tömen, Nergis

“…Spiking Neural Networks (SNNs) and neuromorphic computing offer bio-inspired advantages such as sparsity and ultra-low power consumption, providing a promising…”
Get full text

Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation by Zeng, Liang, Lengyel, Attila, Tömen, Nergis, van Gemert, Jan

“…In this work, we leverage estimated depth to boost self-supervised contrastive learning for segmentation of urban scenes, where unlabeled videos are readily…”
Get full text

Feature Space Quantization for Data-Driven Search by Tomen, N., Takemiya, M., Matsuo, T., Hasegawa, I., Kamitani, Y.

“…There is a growing need to be able to detect arbitrary patterns and trends in large data sets. Practically detecting arbitrary patterns in neuroimaging…”
Get full text