1 citations · 1 across the 4 of their papers we have counts for
4 papers · 1 filter
The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations
Kushal Vyas, Alper Kayabasi, Daniel Kim +3
The approximation and convergence properties of implicit neural representations (INRs) are known to be highly sensitive to parameter initialization strategies. While several data-d…
Bias for Action: Video Implicit Neural Representations with Bias Modulation
Alper Kayabasi, Anil Kumar Vadathya, Guha Balakrishnan +1
We propose a new continuous video modeling framework based on implicit neural representations (INRs) called ActINR. At the core of our approach is the observation that INRs can be…
Elimination of Non-Novel Segments at Multi-Scale for Few-Shot Segmentation
Alper Kayabaşı, Gülin Tüfekci, İlkay Ulusoy
Few-shot segmentation aims to devise a generalizing model that segments query images from unseen classes during training with the guidance of a few support images whose class tally…
Detecting Driver Drowsiness as an Anomaly Using LSTM Autoencoders
Gülin Tüfekci, Alper Kayabaşi, Erdem Akagündüz +1
In this paper, an LSTM autoencoder-based architecture is utilized for drowsiness detection with ResNet-34 as feature extractor. The problem is considered as anomaly detection for a…