MIDI-to-Audio piano synthesizer based on DDSP. read more of DDSP-Piano: Differentiable Piano model for MIDI-to-Audio Performance Synthesis

This is a component which is able to detect shot boundaries, the sampling structure and dynamic keyframes in a videos at a speed of four times faster than real-time. read more of Faster than real-time detection of shot boundaries, sampling structure and dynamic keyframes in video

The repository contains the python code for the manifold mixing model soup algorithm as proposed in the paper at https://arxiv.org/abs/2309.08610. read more of Manifold mixing model soups for better out-of-distribution accuracy

The dataset enables the open evaluation of photographic profile rating and ranking algorithms that can provide users with privacy-related feedback. read more of The ImageCLEFAware 2021 Dataset

Method that provides privacy-related feedback for photographic user profiles read more of LERVUP - LEarning to Rate Visual User Profiles

Implementation of different class-incremental methods read more of Class Incremental Learning Methods for Visual Tasks

FaVCI2D is a face verification dataset including demographically-diversified faces and challenging negative faces. read more of Face Verification with Challenging Imposters and Diversified Demographics

AdvisIL recommends appropriate algorithm-backbone architecture combinations for a user-provided class-incremental learning scenario. read more of AdvisIL - A Class-Incremental Learning Advisor

Transfer-learning-based method addressing exemplar-free class-incremental learning read more of Feature Translation for Exemplar-Free Class-Incremental Learning

MAD-TSC is a multilingual aligned dataset for target-dependent sentiment classification (TSC) on the news domain. read more of MAD-TSC: A Multilingual Aligned News Dataset for Target-dependent Sentiment Classification