Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963437997> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2963437997 abstract "Understanding human activity and being able to explain it in detail surpasses mere action classification by far in both complexity and value. The challenge is thus to describe an activity on the basis of its most fundamental constituents, the individual postures and their distinctive transitions. Supervised learning of such a fine-grained representation based on elementary poses is very tedious and does not scale. Therefore, we propose a completely unsupervised deep learning procedure based solely on video sequences, which starts from scratch without requiring pre-trained networks, predefined body models, or keypoints. A combinatorial sequence matching algorithm proposes relations between frames from subsets of the training data, while a CNN is reconciling the transitivity conflicts of the different subsets to learn a single concerted pose embedding despite changes in appearance across sequences. Without any manual annotation, the model learns a structured representation of postures and their temporal development. The model not only enables retrieval of similar postures but also temporal super-resolution. Additionally, based on a recurrent formulation, next frames can be synthesized." @default.
- W2963437997 created "2019-07-30" @default.
- W2963437997 creator A5009727485 @default.
- W2963437997 creator A5011106959 @default.
- W2963437997 creator A5036114910 @default.
- W2963437997 creator A5084415727 @default.
- W2963437997 date "2017-10-01" @default.
- W2963437997 modified "2023-10-18" @default.
- W2963437997 title "Unsupervised Video Understanding by Reconciliation of Posture Similarities" @default.
- W2963437997 cites W1154498256 @default.
- W2963437997 cites W131856359 @default.
- W2963437997 cites W1907587592 @default.
- W2963437997 cites W1975517671 @default.
- W2963437997 cites W1978383016 @default.
- W2963437997 cites W1985108724 @default.
- W2963437997 cites W2015461918 @default.
- W2963437997 cites W2016053056 @default.
- W2963437997 cites W2022171669 @default.
- W2963437997 cites W2029242918 @default.
- W2963437997 cites W2031240623 @default.
- W2963437997 cites W2056120433 @default.
- W2963437997 cites W2063153269 @default.
- W2963437997 cites W2080873731 @default.
- W2963437997 cites W2099333815 @default.
- W2963437997 cites W2103015390 @default.
- W2963437997 cites W2108598243 @default.
- W2963437997 cites W2113325037 @default.
- W2963437997 cites W2115213191 @default.
- W2963437997 cites W2120419212 @default.
- W2963437997 cites W2126574503 @default.
- W2963437997 cites W2136848157 @default.
- W2963437997 cites W2137542411 @default.
- W2963437997 cites W2137591992 @default.
- W2963437997 cites W2139117248 @default.
- W2963437997 cites W2155893237 @default.
- W2963437997 cites W2156135524 @default.
- W2963437997 cites W219040644 @default.
- W2963437997 cites W2207655606 @default.
- W2963437997 cites W2342662179 @default.
- W2963437997 cites W2422305492 @default.
- W2963437997 cites W3141200356 @default.
- W2963437997 cites W3182920176 @default.
- W2963437997 cites W343636949 @default.
- W2963437997 doi "https://doi.org/10.1109/iccv.2017.471" @default.
- W2963437997 hasPublicationYear "2017" @default.
- W2963437997 type Work @default.
- W2963437997 sameAs 2963437997 @default.
- W2963437997 citedByCount "20" @default.
- W2963437997 countsByYear W29634379972018 @default.
- W2963437997 countsByYear W29634379972019 @default.
- W2963437997 countsByYear W29634379972020 @default.
- W2963437997 countsByYear W29634379972021 @default.
- W2963437997 countsByYear W29634379972022 @default.
- W2963437997 crossrefType "proceedings-article" @default.
- W2963437997 hasAuthorship W2963437997A5009727485 @default.
- W2963437997 hasAuthorship W2963437997A5011106959 @default.
- W2963437997 hasAuthorship W2963437997A5036114910 @default.
- W2963437997 hasAuthorship W2963437997A5084415727 @default.
- W2963437997 hasBestOaLocation W29634379972 @default.
- W2963437997 hasConcept C154945302 @default.
- W2963437997 hasConcept C204321447 @default.
- W2963437997 hasConcept C31972630 @default.
- W2963437997 hasConcept C41008148 @default.
- W2963437997 hasConceptScore W2963437997C154945302 @default.
- W2963437997 hasConceptScore W2963437997C204321447 @default.
- W2963437997 hasConceptScore W2963437997C31972630 @default.
- W2963437997 hasConceptScore W2963437997C41008148 @default.
- W2963437997 hasLocation W29634379971 @default.
- W2963437997 hasLocation W29634379972 @default.
- W2963437997 hasOpenAccess W2963437997 @default.
- W2963437997 hasPrimaryLocation W29634379971 @default.
- W2963437997 hasRelatedWork W1891287906 @default.
- W2963437997 hasRelatedWork W1969923398 @default.
- W2963437997 hasRelatedWork W2021592657 @default.
- W2963437997 hasRelatedWork W2036807459 @default.
- W2963437997 hasRelatedWork W2058170566 @default.
- W2963437997 hasRelatedWork W2110717643 @default.
- W2963437997 hasRelatedWork W2229312674 @default.
- W2963437997 hasRelatedWork W2755342338 @default.
- W2963437997 hasRelatedWork W2772917594 @default.
- W2963437997 hasRelatedWork W3116076068 @default.
- W2963437997 isParatext "false" @default.
- W2963437997 isRetracted "false" @default.
- W2963437997 magId "2963437997" @default.
- W2963437997 workType "article" @default.