G2SP-CV 2024 (google.com)

Description of Topic

Graph representation learning and its applications have gained significant attention in recent years. Notably, Graph Signal Processing (GSP) and Graph Neural Networks (GNNs) have been extensively studied. GSP extends the concepts of classical digital signal processing to signals supported on graphs. Similarly, GNNs extend the concepts of Convolutional Neural Networks (CNNs) to non-Euclidean data modeled as graphs. GSP and GNNs have numerous applications such as semi-supervised learning, point cloud semantic segmentation, prediction of individual relations in social networks, image, and video processing. Early GSP researchers explored low-dimensional representations of high-dimensional data via spectral graph theory, i.e., mathematical analysis of eigen-structures of the adjacency and graph Laplacian matrices. Researchers first developed algorithms for low-level tasks such as signal compression, wavelet decomposition, filter banks on graphs, regression, and denoising, motivated by data collected from distributed sensor networks. Soon, researchers widened their scope and studied GSP techniques for image applications (image filtering, segmentation) and computer graphics. More recently, GSP tools were extended to video processing tasks such as moving object segmentation, demonstrating its potential in a wide range of computer vision problems.

From the GNN side, Bruna et al. proposed the first modern GNN by extending the convolutional operator of CNNs to graphs. Later, researchers used the concepts of GSP to propose localized spectral filtering. Subsequently, Kipf and Welling approximated the filtering operation of spectral filtering to perform efficient convolution operations on graph. Other major GNN works include the study of inductive representation learning on graphs and the development of graph attention networks. GNNs have shown great potential in computer vision applications such as point cloud semantic segmentation, video understanding, and event-based vision. However, designing GSP or GNN algorithms for specific computer vision tasks has several practical challenges such as spatio-temporal constraints, time-varying models, and real-time implementations. Indeed, the computational complexity of many existing GSP/GNN algorithms at present for very large graphs is currently one limitation. In semi-supervised learning, GSP-based classifiers provide clear interpretations from a graph spectral perspective when propagating label information from known to unknown nodes. However, centralized graph spectral algorithms are slow and no fast-distributed graph labeling algorithms are known to perform well. In that sense, research is required in the development of fast GSP/GNN tools to be competitive against well-established deep learning methods like CNNs.

The goals of this workshop are thus three-fold: 1) designing GSP/GNNs methods for  pattern recognition and computer vision applications; 2) proposing new adaptive and incremental algorithms that reach the requirements of real-time applications; and 3) proposing robust and interpretable algorithms to handle the key challenges in pattern recognition and computer vision applications.

Papers are solicited to address GSP/GNNs to be applied in computer vision, including but not limited to the following:

Graph Machine Learning for Computer Vision

Graph Neural Networks (GNNs)

GNN Architectures

Interpretable/Explainable GNNs

Unsupervised/Self-Supervised GNNs

GSP-based Graph Learning in GNNs

Sampling and Recovery of Graph Signals

Statistical Graph Signal Processing

Non-linear Graph Signal Processing

Signals in high-order Graphs

Graph-based Segmentation and Classification

Graph-based Image and Video Processing

Graph-based Image Restoration

Graph-based Image Filtering

Graph-based Event Data Processing

Main Organizers

Thierry Bouwmans, Associate Professor (HDR), Laboratoire MIA, La Rochelle Université, France.

Jhony H. Giraldo, Assistant Professor, LTCI, Télécom Paris, France.

Ananda S. Chowdhury, Professor, Jadavpur University, India.

Badri N. Subudhi, Associate Professor, Indian Institute of Technology Jammu, India.

Important Dates 

Full Paper Submission Deadline: July 30, 2024

Decisions to Authors:                  September 1, 2024

Camera-ready Deadline:             September 27, 2024

Selected papers, after extensions and further revisions, will be published in a special issue of an international journal.