Abstract | ||
---|---|---|
Visual relationship recognition is essential for deeper scene understanding. It poses to recognize 〈subject-predicate-object〉 triplets between object pairs. Previous methods usually treat vastly different predicates equally and neglect the subtle differences between predicates. In this paper, we propose a novel and concise perspective called "predicate-aware learning network (PAL-Net)" for visual ... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICME51207.2021.9428175 | 2021 IEEE International Conference on Multimedia and Expo (ICME) |
Keywords | DocType | ISBN |
Visualization,Conferences,Semantics,Genomics,Performance gain,Task analysis,Bioinformatics | Conference | 978-1-6654-3864-3 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |