Alex Stergiou's repositories
keras-DepthwiseConv3D
Keras w/ Tensorflow backend implementation for 3D channel-wise convolutions
Squeeze-and-Recursion-Temporal-Gates
Code for : [Pattern Recognit. Lett. 2021] "Learn to cycle: Time-consistent feature discovery for action recognition" and [IJCNN 2021] "Multi-Temporal Convolutions for Human Action Recognition in Videos".
Saliency-Tubes-Visual-Explanations-for-Spatio-Temporal-Convolutions
[ICIP 2019] Implementation of Saliency Tubes for 3D Convolutions in Pytoch and Keras to localise the focus spatio-temporal regions of 3D CNNs.
Class_Feature_Visualization_Pyramid
[ICCVW 2019] PyTorch code for Class Visualization Pyramid for intpreting spatio-temporal class-specific activations throughout the network
progressive-action-prediction
[CVPR 2023] Code for action prediction from videos
Traffic-Sign-Recognition-basd-on-Synthesised-Training-Data
Using synthetic data in combination with Deep Learning, to determine if a system can be made that will be able to recognise and classify correctly real traffic signs.
Class-Agnostic-Feature-Visualisation
[ICIP 2021] PyTorch code for "The Mind's Eye: Visualizing Class-Agnostic Features of CNNs" for generation of kernel features.
Inception_v3_TV_Human_Interactions
Applying Transfer Learning on Inception V3 model (weights trained on Imagenet) for the Oxford TV Human Interactions dataset. The network gets as inputs images extracted every 5 frames from videos.
PlayItBack
[ICASSP 2023] PyTorch code for "Play It Back: Iterative Attention for Audio Recognition"
dataset2database
Script for creating SQL databases from video files to reduce random access overhead and inodes
Leaping-Into-Memories
[ICCV 2023] Code implementation for "Leaping Into Memories: Space-Time Deep Feature Synthesis"
video2spectrogram
Python script for extracting audio from video files and creating Mel spectrograms
Datasets-Visualisations-w-OpenCV
Creating grid visualisations of dataset examples with the OpenCV library
audioset-processing
Toolkit for downloading and processing Google's AudioSet dataset.
audiosetdl
Scripts for download AudioSet
auditory-slow-fast
Implementation of "Slow-Fast Auditory Streams for Audio Recognition, ICASSP, 2021" in PyTorch
deep-learning-models
Keras code and weights files for popular deep learning models.
DeepInversion
Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)