Showing 2026Show all
2 papers · 1 filter
cs.CV2026
HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding
Rui Chen, Xingyu Chen, Pengxin Xu +2
Temporal action detection in long untrimmed videos suffers from inaccurate localization and low-quality proposals, especially with sparse annotations and ambiguous boundaries. For…
cs.LG2026
Local Message-Passing for Discrete Graph Generation
Jay Revolinsky, Harry Shomer, Jiliang Tang
Discrete graph generation has emerged as a powerful paradigm for modeling graph-structured data, yet state of the art models often rely on Graph Transformers or higher order archit…