4 papers
Context Propagation from Proposals for Semantic Video Object Segmentation
Tinghuai Wang
In this paper, we propose a novel approach to learning semantic contextual relationships in videos for semantic object segmentation. Our algorithm derives the semantic contexts fro…
Graph-Boosted Attentive Network for Semantic Body Parsing
Tinghuai Wang, Huiling Wang
Human body parsing remains a challenging problem in natural scenes due to multi-instance and inter-part semantic confusions as well as occlusions. This paper proposes a novel appro…
Non-parametric Contextual Relationship Learning for Semantic Video Object Segmentation
Tinghuai Wang, Huiling Wang
We propose a novel approach for modeling semantic contextual relationships in videos. This graph-based model enables the learning and propagation of higher-level spatial-temporal c…
Submodular video object proposal selection for semantic object segmentation
Tinghuai Wang
Learning a data-driven spatio-temporal semantic representation of the objects is the key to coherent and consistent labelling in video. This paper proposes to achieve semantic vide…