This work proposes HCNet (Hyperbolic hierarchical Clause Network), which first decomposes each expression into four hierarchical clauses via dependency parsing, then refines sentence representations through a hierarchical text enhancer that attends to coarser clause levels.
Ying-Chun Tian, Cheng Yang, Qing-Bao Huang· Proceedings of the 34th ACM...· 0 citations
Existing weakly supervised referring expression comprehension (WREC) and segmentation (WRES) methods perform anchor-text matching using flat sentence-level representations, thereby discarding the multi-granularity hierarchical semantics inherent in both visual and linguistic modalities. Because referring expressions na...
Ying-Chun Tian, Cheng Yang, Qing-Bao Huang· Proceedings of the 34th ACM...· 0 citations
This work proposes OCAAD, an Object-Centric Alignment and Anchor Distillation framework, and introduces two complementary modules that bridges the semantic gap between anchors and objects by transferring object-level knowledge from attention heads to anchors via overlap-aware contrastive learning.
Ying-Chun Tian, Cheng Yang, Qing-Bao Huang· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.