Matches in SemOpenAlex for { <https://semopenalex.org/work/W2734973448> ?p ?o ?g. }
- W2734973448 abstract "Fine-grained activity understanding in videos has attracted considerable recent attention with a shift from action classification to detailed actor and action understanding that provides compelling results for perceptual needs of cutting-edge autonomous systems. However, current methods for detailed understanding of actor and action have significant limitations: they require large amounts of finely labeled data, and they fail to capture any internal relationship among actors and actions. To address these issues, in this paper, we propose a novel, robust multi-task ranking model for weakly supervised actor-action segmentation where only video-level tags are given for training samples. Our model is able to share useful information among different actors and actions while learning a ranking matrix to select representative supervoxels for actors and actions respectively. Final segmentation results are generated by a conditional random field that considers various ranking scores for different video parts. Extensive experimental results on the Actor-Action Dataset (A2D) demonstrate that the proposed approach outperforms the state-of-the-art weakly supervised methods and performs as well as the top-performing fully supervised method." @default.
- W2734973448 created "2017-07-21" @default.
- W2734973448 creator A5016879676 @default.
- W2734973448 creator A5048411184 @default.
- W2734973448 creator A5064805926 @default.
- W2734973448 creator A5079301873 @default.
- W2734973448 date "2017-07-01" @default.
- W2734973448 modified "2023-10-14" @default.
- W2734973448 title "Weakly Supervised Actor-Action Segmentation via Robust Multi-task Ranking" @default.
- W2734973448 cites W122025198 @default.
- W2734973448 cites W1522734439 @default.
- W2734973448 cites W1613163714 @default.
- W2734973448 cites W1900424585 @default.
- W2734973448 cites W1903029394 @default.
- W2734973448 cites W1905722737 @default.
- W2734973448 cites W1920142129 @default.
- W2734973448 cites W1927052826 @default.
- W2734973448 cites W1961270558 @default.
- W2734973448 cites W1974644251 @default.
- W2734973448 cites W1985583020 @default.
- W2734973448 cites W1990802205 @default.
- W2734973448 cites W2010132303 @default.
- W2734973448 cites W2016053056 @default.
- W2734973448 cites W2018068650 @default.
- W2734973448 cites W2018096278 @default.
- W2734973448 cites W2029859592 @default.
- W2734973448 cites W2030346542 @default.
- W2734973448 cites W2035720976 @default.
- W2734973448 cites W2039314265 @default.
- W2734973448 cites W2042041679 @default.
- W2734973448 cites W2074753351 @default.
- W2734973448 cites W2081490348 @default.
- W2734973448 cites W2095661305 @default.
- W2734973448 cites W2097117768 @default.
- W2734973448 cites W2100556411 @default.
- W2734973448 cites W2101194540 @default.
- W2734973448 cites W2105101328 @default.
- W2734973448 cites W2105297725 @default.
- W2734973448 cites W2108710284 @default.
- W2734973448 cites W2113940248 @default.
- W2734973448 cites W2131720600 @default.
- W2734973448 cites W2142194269 @default.
- W2734973448 cites W2149427297 @default.
- W2734973448 cites W2162813810 @default.
- W2734973448 cites W2169393274 @default.
- W2734973448 cites W2183182206 @default.
- W2734973448 cites W2212903133 @default.
- W2734973448 cites W2337287714 @default.
- W2734973448 cites W2425121537 @default.
- W2734973448 cites W2460134573 @default.
- W2734973448 cites W2461677039 @default.
- W2734973448 cites W2491875666 @default.
- W2734973448 cites W2518874898 @default.
- W2734973448 cites W2519080876 @default.
- W2734973448 cites W2529163075 @default.
- W2734973448 cites W2533503513 @default.
- W2734973448 cites W2963094665 @default.
- W2734973448 cites W2963563573 @default.
- W2734973448 cites W2964214371 @default.
- W2734973448 cites W3021229333 @default.
- W2734973448 cites W3103236591 @default.
- W2734973448 cites W3184458996 @default.
- W2734973448 cites W4249279051 @default.
- W2734973448 doi "https://doi.org/10.1109/cvpr.2017.115" @default.
- W2734973448 hasPublicationYear "2017" @default.
- W2734973448 type Work @default.
- W2734973448 sameAs 2734973448 @default.
- W2734973448 citedByCount "40" @default.
- W2734973448 countsByYear W27349734482017 @default.
- W2734973448 countsByYear W27349734482018 @default.
- W2734973448 countsByYear W27349734482019 @default.
- W2734973448 countsByYear W27349734482020 @default.
- W2734973448 countsByYear W27349734482021 @default.
- W2734973448 countsByYear W27349734482022 @default.
- W2734973448 countsByYear W27349734482023 @default.
- W2734973448 crossrefType "proceedings-article" @default.
- W2734973448 hasAuthorship W2734973448A5016879676 @default.
- W2734973448 hasAuthorship W2734973448A5048411184 @default.
- W2734973448 hasAuthorship W2734973448A5064805926 @default.
- W2734973448 hasAuthorship W2734973448A5079301873 @default.
- W2734973448 hasConcept C119857082 @default.
- W2734973448 hasConcept C121332964 @default.
- W2734973448 hasConcept C152565575 @default.
- W2734973448 hasConcept C153180895 @default.
- W2734973448 hasConcept C154945302 @default.
- W2734973448 hasConcept C162324750 @default.
- W2734973448 hasConcept C187736073 @default.
- W2734973448 hasConcept C189430467 @default.
- W2734973448 hasConcept C202444582 @default.
- W2734973448 hasConcept C2780451532 @default.
- W2734973448 hasConcept C2780791683 @default.
- W2734973448 hasConcept C33923547 @default.
- W2734973448 hasConcept C41008148 @default.
- W2734973448 hasConcept C62520636 @default.
- W2734973448 hasConcept C89600930 @default.
- W2734973448 hasConcept C9652623 @default.
- W2734973448 hasConceptScore W2734973448C119857082 @default.
- W2734973448 hasConceptScore W2734973448C121332964 @default.
- W2734973448 hasConceptScore W2734973448C152565575 @default.
- W2734973448 hasConceptScore W2734973448C153180895 @default.