bmezaris Goto Github PK
Type: User
Type: User
[ACM ICMR 2020] Attention Mechanisms, Signal Encodings and Fusion Strategies for Improved Ad-hoc Video Search with Dual Encoding Networks
In this work, a novel pruning framework is introduced to compress noisy or less discriminant filters in small fractional steps, in deep convolutional networks. The proposed framework utilizes a class-separability criterion that can exploit effectively the labeling information in annotated training sets. Additionally, an asymptotic schedule for the pruning rate and scaling factor is adopted so that the selected filters’ weights collapse gradually to zero, providing improved robustness. Experimental results on the CIFAR-10, Google speech commands (GSC) and ImageNet32 (a downsampled version of ILSVRC-2012) show the efficacy of the proposed approach.
Implementation of various fully convolutional networks in Keras
Gated-ViGAT. Code and data for our paper: N. Gkalelis, D. Daskalakis, V. Mezaris, "Gated-ViGAT: Efficient bottom-up event recognition and explanation using a new frame selection policy and gating mechanism", IEEE International Symposium on Multimedia (ISM), Naples, Italy, Dec. 2022.
Code for our paper "Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism", by I. Gkartzonika, N. Gkalelis, V. Mezaris, presented and included in the Proceedings of the ECCV 2022 Workshop on Vision with Biased or Scarce Data (VBSD), Oct. 2022.
Lecture video segmentation dataset
Structured Pruning of LSTMs via Eigenanalysis and Geometric Median. This code can be used for generating more compact LSTMs, which is very useful for mobile multimedia applications and deep learning applications in other resource-constrained environments.
Code and materials for our paper: D. Daskalakis, N. Gkalelis, V. Mezaris, "Masked Feature Modelling for the unsupervised pre-training of a Graph Attention Network block for bottom-up video event recognition", Proc. 25th IEEE Int. Symp. on Multimedia (ISM 2023), Laguna Hills, CA, USA, Dec. 2023.
This repository hosts the code and data for our paper "ObjectGraphs: Using Objects and a Graph Convolutional Network for the Bottom-up Recognition and Explanation of Events in Video", Proc. 2nd Int. Workshop on Large Scale Holistic Video Understanding (HVU) at the IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2021.
Video dataset and code for transforming a video's aspect ratio, from our papers "A fast smart-cropping method and dataset for video retargeting", IEEE ICIP 2021, and "A Web Service for Video Smart-Cropping", IEEE ISM 2021.
Subclass deep neural networks
Code and data for our learning-based eXplainable AI (XAI) method TAME: M. Ntrougkas, N. Gkalelis, V. Mezaris, "TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks", Proc. IEEE Int. Symposium on Multimedia (ISM), Naples, Italy, Dec. 2022.
A PyTorch Implementation of the T x V model from "Are all combinations equal? Combining textual and visual features with multiple space learning for text-based video retrieval", Proc. ECCVW 2022.
This repository hosts the scripts and some of the pre-trained models presented in out paper "ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network", IEEE Access, 2022.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.