Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119462709> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3119462709 endingPage "495" @default.
- W3119462709 startingPage "479" @default.
- W3119462709 abstract "Existing approaches for human-centered tasks such as human instance segmentation are focused on improving the architectures of models, leveraging weak supervision or transforming supervision among related tasks. Nonetheless, the structures are highly specific and the weak supervision is limited by available priors or number of related tasks. In this paper, we present a novel self-supervised framework for human instance segmentation. The framework includes one module which iteratively conducts mutual refinement between segmentation and optical flow estimation, and the other module which iteratively refines pose estimations by exploring the prior knowledge about the consistency in human graph structures from consecutive frames. The results of the proposed framework are employed for fine-tuning segmentation networks in a feedback fashion. Experimental results on the OCHuman and COCOPersons datasets demonstrate that the self-supervised framework achieves current state-of-the-art performance against existing models on the challenging datasets without requiring additional labels. Unlabeled video data is utilized together with prior knowledge to significantly improve performance and reduce the reliance on annotations. Code released at: https://github.com/AllenYLJiang/SSINS." @default.
- W3119462709 created "2021-01-18" @default.
- W3119462709 creator A5012270936 @default.
- W3119462709 creator A5016123060 @default.
- W3119462709 creator A5024501453 @default.
- W3119462709 creator A5045163085 @default.
- W3119462709 creator A5056101043 @default.
- W3119462709 date "2020-01-01" @default.
- W3119462709 modified "2023-09-24" @default.
- W3119462709 title "A Self-supervised Framework for Human Instance Segmentation" @default.
- W3119462709 cites W1861492603 @default.
- W3119462709 cites W1923115158 @default.
- W3119462709 cites W1960289438 @default.
- W3119462709 cites W1962739028 @default.
- W3119462709 cites W1973255633 @default.
- W3119462709 cites W2204578866 @default.
- W3119462709 cites W2216125271 @default.
- W3119462709 cites W2302255633 @default.
- W3119462709 cites W2531409750 @default.
- W3119462709 cites W2555182955 @default.
- W3119462709 cites W2559085405 @default.
- W3119462709 cites W2560474170 @default.
- W3119462709 cites W2598915960 @default.
- W3119462709 cites W2777795072 @default.
- W3119462709 cites W2798453399 @default.
- W3119462709 cites W2886799640 @default.
- W3119462709 cites W2887240357 @default.
- W3119462709 cites W2916798096 @default.
- W3119462709 cites W2958537753 @default.
- W3119462709 cites W2962773068 @default.
- W3119462709 cites W2962891704 @default.
- W3119462709 cites W2963136578 @default.
- W3119462709 cites W2963150697 @default.
- W3119462709 cites W2963225012 @default.
- W3119462709 cites W2963578952 @default.
- W3119462709 cites W2963758239 @default.
- W3119462709 cites W2963781481 @default.
- W3119462709 cites W2964072977 @default.
- W3119462709 cites W2964084369 @default.
- W3119462709 cites W2964221239 @default.
- W3119462709 cites W2964309882 @default.
- W3119462709 doi "https://doi.org/10.1007/978-3-030-66096-3_33" @default.
- W3119462709 hasPublicationYear "2020" @default.
- W3119462709 type Work @default.
- W3119462709 sameAs 3119462709 @default.
- W3119462709 citedByCount "1" @default.
- W3119462709 countsByYear W31194627092023 @default.
- W3119462709 crossrefType "book-chapter" @default.
- W3119462709 hasAuthorship W3119462709A5012270936 @default.
- W3119462709 hasAuthorship W3119462709A5016123060 @default.
- W3119462709 hasAuthorship W3119462709A5024501453 @default.
- W3119462709 hasAuthorship W3119462709A5045163085 @default.
- W3119462709 hasAuthorship W3119462709A5056101043 @default.
- W3119462709 hasConcept C119857082 @default.
- W3119462709 hasConcept C154945302 @default.
- W3119462709 hasConcept C41008148 @default.
- W3119462709 hasConcept C89600930 @default.
- W3119462709 hasConceptScore W3119462709C119857082 @default.
- W3119462709 hasConceptScore W3119462709C154945302 @default.
- W3119462709 hasConceptScore W3119462709C41008148 @default.
- W3119462709 hasConceptScore W3119462709C89600930 @default.
- W3119462709 hasLocation W31194627091 @default.
- W3119462709 hasOpenAccess W3119462709 @default.
- W3119462709 hasPrimaryLocation W31194627091 @default.
- W3119462709 hasRelatedWork W2961085424 @default.
- W3119462709 hasRelatedWork W3046775127 @default.
- W3119462709 hasRelatedWork W3107474891 @default.
- W3119462709 hasRelatedWork W3170094116 @default.
- W3119462709 hasRelatedWork W3209574120 @default.
- W3119462709 hasRelatedWork W4205958290 @default.
- W3119462709 hasRelatedWork W4286629047 @default.
- W3119462709 hasRelatedWork W4306321456 @default.
- W3119462709 hasRelatedWork W4306674287 @default.
- W3119462709 hasRelatedWork W4224009465 @default.
- W3119462709 isParatext "false" @default.
- W3119462709 isRetracted "false" @default.
- W3119462709 magId "3119462709" @default.
- W3119462709 workType "book-chapter" @default.