Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Kang, Yangyuxuan"'
This paper presents Ske2Grid, a new representation learning framework for improved skeleton-based action recognition. In Ske2Grid, we define a regular convolution operation upon a novel grid representation of human skeleton, which is a compact image-
Externí odkaz:
http://arxiv.org/abs/2308.07571
Incorporating knowledge graph into recommendation is an effective way to alleviate data sparsity. Most existing knowledge-aware methods usually perform recursive embedding propagation by enumerating graph neighbors. However, the number of nodes' neig
Externí odkaz:
http://arxiv.org/abs/2304.07506
Existing lifting networks for regressing 3D human poses from 2D single-view poses are typically constructed with linear layers based on graph-structured representation learning. In sharp contrast to them, this paper presents Grid Convolution (GridCon
Externí odkaz:
http://arxiv.org/abs/2302.08760