4 papers
ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning
Aman Anand, Amir Eskandari, Elyas Rahsno +1
Self-supervised learning (SSL) has shown remarkable success in skeleton-based action recognition by leveraging data augmentations to learn meaningful representations. However, exis…
InfGraND: An Influence-Guided GNN-to-MLP Knowledge Distillation
Amir Eskandari, Aman Anand, Elyas Rashno +1
Graph Neural Networks (GNNs) are the go-to model for graph data analysis. However, GNNs rely on two key operations - aggregation and update, which can pose challenges for low-laten…
Depth-Guided Self-Supervised Human Keypoint Detection via Cross-Modal Distillation
Aman Anand, Elyas Rashno, Amir Eskandari +1
Existing unsupervised keypoint detection methods apply artificial deformations to images such as masking a significant portion of images and using reconstruction of original image…
SDA-GRIN for Adaptive Spatial-Temporal Multivariate Time Series Imputation
Amir Eskandari, Aman Anand, Drishti Sharma +1
In various applications, the multivariate time series often suffers from missing data. This issue can significantly disrupt systems that rely on the data. Spatial and temporal depe…