Chih-Yuan Yang, Jane Yung-Jen Hsu, Sheng-Wei Li, Zi-Xiang Wei, Wei-Jie Chen, Yi-Hsin Yu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Existing zero-shot skeleton-based action recognition methods utilize projection networks to learn a shared latent space of skeleton features and semantic embeddings. The inherent imbalance in action recognition datasets, characterized by variable skeleton sequences yet constant class labels, presents significant challenges for alignment. To address the imbalance, we propose SA-DVAE-Semantic Alignment via Disentangled Variational Autoencoders, a method that first adopts feature disentanglement to separate skeleton features into two independent parts-one is semantic-related and another is irrelevant-to better align skeleton and semantic features. We implement this idea via a pair of modality-specific variational autoencoders coupled with a total correction penalty. We conduct experiments on three benchmark datasets: NTU RGB+D, NTU RGB+D 120 and PKU-MMD, and our experimental results show that SA-DAVE produces improved performance over existing methods. The code is available at https://github.com/ pha123661/SA-DVAE.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.13460")
get_code_for_paper("2407.13460")
have("2407.13460")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2407.13460.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2407.13460)
Connect an agent — have() is free.