38 citations · 73 across the 10 of their papers we have counts for
10 papers
Exploiting Latent Properties to Optimize Neural Codecs
Muhammet Balcilar, Bharath Bhushan Damodaran, Karam Naser +2
End-to-end image and video codecs are becoming increasingly competitive, compared to traditional compression techniques that have been developed through decades of manual engineeri…
Latent-Shift: Gradient of Entropy Helps Neural Codecs
Muhammet Balcilar, Bharath Bhushan Damodaran, Karam Naser +2
End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts. These t…
RQAT-INR: Improved Implicit Neural Image Compression
Bharath Bhushan Damodaran, Muhammet Balcilar, Franck Galpin +1
Deep variational autoencoders for image and video compression have gained significant attraction in the recent years, due to their potential to offer competitive or better compress…
Entropy Coding Improvement for Low-complexity Compressive Auto-encoders
Franck Galpin, Muhammet Balcilar, Frédéric Lefebvre +2
End-to-end image and video compression using auto-encoders (AE) offers new appealing perspectives in terms of rate-distortion gains and applications. While most complex models are…
Reducing The Mismatch Between Marginal and Learned Distributions in Neural Video Compression
Muhammet Balcilar, Bharath Bhushan Damodaran, Pierre Hellier
During the last four years, we have witnessed the success of end-to-end trainable models for image compression. Compared to decades of incremental work, these machine learning (ML)…
Improving The Reconstruction Quality by Overfitted Decoder Bias in Neural Image Compression
Oussama Jourairi, Muhammet Balcilar, Anne Lambert +1
End-to-end trainable models have reached the performance of traditional handcrafted compression techniques on videos and images. Since the parameters of these models are learned ov…
Reducing The Amortization Gap of Entropy Bottleneck In End-to-End Image Compression
Muhammet Balcilar, Bharath Damodaran, Pierre Hellier
End-to-end deep trainable models are about to exceed the performance of the traditional handcrafted compression techniques on videos and images. The core idea is to learn a non-lin…
Breaking the Limits of Message Passing Graph Neural Networks
Muhammet Balcilar, Pierre Héroux, Benoit Gaüzère +3
Since the Message Passing (Graph) Neural Networks (MPNNs) have a linear complexity with respect to the number of nodes when applied to sparse graphs, they have been widely implemen…
Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
Muhammet Balcilar, Guillaume Renton, Pierre Heroux +3
This paper aims at revisiting Graph Convolutional Neural Networks by bridging the gap between spectral and spatial design of graph convolutions. We theoretically demonstrate some e…
Audio Captcha Recognition Using RastaPLP Features by SVM
Ahmet Faruk Cakmak, Muhammet Balcilar
Nowadays, CAPTCHAs are computer generated tests that human can pass but current computer systems can not. They have common usage in various web services in order to be able to dete…