FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2575671312> ?p ?o ?g. }

• W2575671312 abstract "This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation. Specifically, we use unsupervised motion-based segmentation on videos to obtain segments, which we use as pseudo ground truth to train a convolutional network to segment objects from a single frame. Given the extensive evidence that motion plays a key role in the development of the human visual system, we hope that this straightforward approach to unsupervised learning will be more effective than cleverly designed pretext tasks studied in the literature. Indeed, our extensive experiments show that this is the case. When used for transfer learning on object detection, our representation significantly outperforms previous unsupervised approaches across multiple settings, especially when training data for the target task is scarce." @default.
• W2575671312 created "2017-01-26" @default.
• W2575671312 creator A5029105520 @default.
• W2575671312 creator A5036548506 @default.
• W2575671312 creator A5049246408 @default.
• W2575671312 creator A5057866698 @default.
• W2575671312 creator A5066151318 @default.
• W2575671312 date "2017-07-01" @default.
• W2575671312 modified "2023-10-16" @default.
• W2575671312 title "Learning Features by Watching Objects Move" @default.
• W2575671312 cites W1520997877 @default.
• W2575671312 cites W1536680647 @default.
• W2575671312 cites W1903029394 @default.
• W2575671312 cites W2025768430 @default.
• W2575671312 cites W2038765747 @default.
• W2575671312 cites W2076756823 @default.
• W2575671312 cites W2100495367 @default.
• W2575671312 cites W2116877738 @default.
• W2575671312 cites W2117539524 @default.
• W2575671312 cites W2118246710 @default.
• W2575671312 cites W2123081785 @default.
• W2575671312 cites W2126164636 @default.
• W2575671312 cites W2144794286 @default.
• W2575671312 cites W2157655975 @default.
• W2575671312 cites W2161969291 @default.
• W2575671312 cites W2163922914 @default.
• W2575671312 cites W219040644 @default.
• W2575671312 cites W2198618282 @default.
• W2575671312 cites W2250384498 @default.
• W2575671312 cites W2470139095 @default.
• W2575671312 cites W2470142083 @default.
• W2575671312 cites W2487442924 @default.
• W2575671312 cites W2558661413 @default.
• W2575671312 cites W2962958090 @default.
• W2575671312 cites W2963420272 @default.
• W2575671312 cites W343636949 @default.
• W2575671312 cites W4231109964 @default.
• W2575671312 cites W56385144 @default.
• W2575671312 doi "https://doi.org/10.1109/cvpr.2017.638" @default.
• W2575671312 hasPublicationYear "2017" @default.
• W2575671312 type Work @default.
• W2575671312 sameAs 2575671312 @default.
• W2575671312 citedByCount "416" @default.
• W2575671312 countsByYear W25756713122016 @default.
• W2575671312 countsByYear W25756713122017 @default.
• W2575671312 countsByYear W25756713122018 @default.
• W2575671312 countsByYear W25756713122019 @default.
• W2575671312 countsByYear W25756713122020 @default.
• W2575671312 countsByYear W25756713122021 @default.
• W2575671312 countsByYear W25756713122022 @default.
• W2575671312 countsByYear W25756713122023 @default.
• W2575671312 crossrefType "proceedings-article" @default.
• W2575671312 hasAuthorship W2575671312A5029105520 @default.
• W2575671312 hasAuthorship W2575671312A5036548506 @default.
• W2575671312 hasAuthorship W2575671312A5049246408 @default.
• W2575671312 hasAuthorship W2575671312A5057866698 @default.
• W2575671312 hasAuthorship W2575671312A5066151318 @default.
• W2575671312 hasBestOaLocation W25756713122 @default.
• W2575671312 hasConcept C104114177 @default.
• W2575671312 hasConcept C119857082 @default.
• W2575671312 hasConcept C126042441 @default.
• W2575671312 hasConcept C138885662 @default.
• W2575671312 hasConcept C150899416 @default.
• W2575671312 hasConcept C153180895 @default.
• W2575671312 hasConcept C154945302 @default.
• W2575671312 hasConcept C162324750 @default.
• W2575671312 hasConcept C17744445 @default.
• W2575671312 hasConcept C187736073 @default.
• W2575671312 hasConcept C199539241 @default.
• W2575671312 hasConcept C2776359362 @default.
• W2575671312 hasConcept C2776401178 @default.
• W2575671312 hasConcept C2779627259 @default.
• W2575671312 hasConcept C2780451532 @default.
• W2575671312 hasConcept C2781238097 @default.
• W2575671312 hasConcept C41008148 @default.
• W2575671312 hasConcept C41895202 @default.
• W2575671312 hasConcept C59404180 @default.
• W2575671312 hasConcept C76155785 @default.
• W2575671312 hasConcept C8038995 @default.
• W2575671312 hasConcept C81363708 @default.
• W2575671312 hasConcept C89600930 @default.
• W2575671312 hasConcept C94124525 @default.
• W2575671312 hasConcept C94625758 @default.
• W2575671312 hasConceptScore W2575671312C104114177 @default.
• W2575671312 hasConceptScore W2575671312C119857082 @default.
• W2575671312 hasConceptScore W2575671312C126042441 @default.
• W2575671312 hasConceptScore W2575671312C138885662 @default.
• W2575671312 hasConceptScore W2575671312C150899416 @default.
• W2575671312 hasConceptScore W2575671312C153180895 @default.
• W2575671312 hasConceptScore W2575671312C154945302 @default.
• W2575671312 hasConceptScore W2575671312C162324750 @default.
• W2575671312 hasConceptScore W2575671312C17744445 @default.
• W2575671312 hasConceptScore W2575671312C187736073 @default.
• W2575671312 hasConceptScore W2575671312C199539241 @default.
• W2575671312 hasConceptScore W2575671312C2776359362 @default.
• W2575671312 hasConceptScore W2575671312C2776401178 @default.
• W2575671312 hasConceptScore W2575671312C2779627259 @default.
• W2575671312 hasConceptScore W2575671312C2780451532 @default.
• W2575671312 hasConceptScore W2575671312C2781238097 @default.
• W2575671312 hasConceptScore W2575671312C41008148 @default.

• next