Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation
IEEE transactions on pattern analysis and machine intelligence, pp. 1-1, 2020.
Relations amongst entities play a central role in image understanding. Due to the complexity of modeling (subject, predicate, object) relation triplets, it is crucial to develop a method that can not only recognize seen relations, but also generalize to unseen cases. Inspired by a previously proposed visual translation embedding model, or...More
Full Text (Upload PDF)
PPT (Upload PPT)