Search Results for author:
Found 10 papers, 4 papers with code
Latent-Shift: Gradient of Entropy Helps Neural Codecs
End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts.
Entropy Coding Improvement for Low-complexity Compressive Auto-encoders
End-to-end image and video compression using auto-encoders (AE) offers new appealing perspectives in terms of rate-distortion gains and applications.
RQAT-INR: Improved Implicit Neural Image Compression
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 compression rates compared to the decades long traditional codecs such as AVC, HEVC or VVC.
Reducing The Mismatch Between Marginal and Learned Distributions in Neural Video Compression
In this paper, we propose to evaluate the amortization gap for three state-of-the-art ML video compression methods.
Improving The Reconstruction Quality by Overfitted Decoder Bias in Neural Image Compression
End-to-end trainable models have reached the performance of traditional handcrafted compression techniques on videos and images.
Reducing The Amortization Gap of Entropy Bottleneck In End-to-End Image Compression
The decoder is also learned as a deep trainable network, and the reconstructed image measures the distortion.
Breaking the Limits of Message Passing Graph Neural Networks
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 implemented and still raise a lot of interest even though their theoretical expressive power is limited to the first order Weisfeiler-Lehman test (1-WL).
Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective
Since the graph isomorphism problem is NP-intermediate, and Weisfeiler-Lehman (WL) test can give sufficient but not enough evidence in polynomial time, the theoretical power of GNNs is usually evaluated by the equivalence of WL-test order, followed by an empirical analysis of the models on some reference inductive and transductive datasets.
Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
Moreover, the proposed framework is used to design new convolutions in spectral domain with a custom frequency profile while applying them in the spatial domain.
Ranked #1 on
Node Classification
on Cora: fixed 20 node per class
Audio Captcha Recognition Using RastaPLP Features by SVM
Briefly, audio CAPTCHAs are sound files which consist of human sound under heavy noise where the speaker pronounces a bunch of digits consecutively.
