3 citations · 4 across the 4 of their papers we have counts for
4 papers
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
Hong Yan, Yang Liu, Yushen Wei +3
Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current me…
Visual Causal Scene Refinement for Video Question Answering
Yushen Wei, Yang Liu, Hong Yan +2
Existing methods for video question answering (VideoQA) often suffer from spurious correlations between different modalities, leading to a failure in identifying the dominant visua…
Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations
Tiexin Qin, Benjamin Walker, Terry Lyons +2
This paper focuses on representation learning for dynamic graphs with temporal interactions. A fundamental issue is that both the graph structure and the nodes own their own dynami…
Learning with Signatures
J. de Curtò, I. de Zarzà, Hong Yan +1
In this work we investigate the use of the Signature Transform in the context of Learning. Under this assumption, we advance a supervised framework that potentially provides state-…