FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201541489> ?p ?o ?g. }

• W3201541489 endingPage "3489" @default.
• W3201541489 startingPage "3475" @default.
• W3201541489 abstract "Self-supervised representation learning for videos has been very attractive recently because these methods exploit the information inherently obtained from the video itself instead of annotated labels that is quite time-consuming. However, existing methods ignore the importance of global observation while performing spatio-temporal transformation perception, which highly limits the expression capabilities of the video representation. This paper proposes a novel pretext task that combines the temporal information perception of the video with the motion amplitude perception of moving objects to learn the spatio-temporal representation of the video. Specifically, given a video clip containing several video segments, each video segment is sampled by different sampling rates and the order of video segments is disrupted. Then, the network is used to regress the sampling rate of each video segment and classify the order of input video segments. In the pre-training stage, the network can learn rich spatio-temporal semantic information where content-related contrastive learning is introduced to make the learned video representation more discriminative. To alleviate the appearance dependency caused by contrastive learning, we design a novel and robust vector similarity measurement approach, which can take feature alignment into consideration. Moreover, a view synthesis framework is proposed to further improve the performance of contrastive learning by automatically generating reasonable transformed views. We conduct benchmark experiments with several 3D backbone networks on two datasets. The results show that our proposed method outperforms the existing state-of-the-art methods across the three backbones on two downstream tasks of human action recognition and video retrieval." @default.
• W3201541489 created "2021-09-27" @default.
• W3201541489 creator A5026184280 @default.
• W3201541489 creator A5029335401 @default.
• W3201541489 creator A5056776038 @default.
• W3201541489 creator A5072168215 @default.
• W3201541489 creator A5090796235 @default.
• W3201541489 date "2022-06-01" @default.
• W3201541489 modified "2023-10-16" @default.
• W3201541489 title "Self-Supervised Representation Learning for Videos by Segmenting via Sampling Rate Order Prediction" @default.
• W3201541489 cites W1522734439 @default.
• W3201541489 cites W1927052826 @default.
• W3201541489 cites W2108598243 @default.
• W3201541489 cites W2126579184 @default.
• W3201541489 cites W2194775991 @default.
• W3201541489 cites W2321533354 @default.
• W3201541489 cites W2487442924 @default.
• W3201541489 cites W2550462002 @default.
• W3201541489 cites W2618530766 @default.
• W3201541489 cites W2765592255 @default.
• W3201541489 cites W2798271879 @default.
• W3201541489 cites W2799087757 @default.
• W3201541489 cites W2883429621 @default.
• W3201541489 cites W2948242301 @default.
• W3201541489 cites W2963155035 @default.
• W3201541489 cites W2963426332 @default.
• W3201541489 cites W2963524571 @default.
• W3201541489 cites W2963631366 @default.
• W3201541489 cites W2963814513 @default.
• W3201541489 cites W2964037671 @default.
• W3201541489 cites W2990152177 @default.
• W3201541489 cites W2990503944 @default.
• W3201541489 cites W2997907976 @default.
• W3201541489 cites W3010874390 @default.
• W3201541489 cites W3034215340 @default.
• W3201541489 cites W3034381931 @default.
• W3201541489 cites W3035118106 @default.
• W3201541489 cites W3035303837 @default.
• W3201541489 cites W3035524453 @default.
• W3201541489 cites W3036435328 @default.
• W3201541489 cites W3037982482 @default.
• W3201541489 cites W3047425522 @default.
• W3201541489 cites W3110190397 @default.
• W3201541489 cites W3169537050 @default.
• W3201541489 cites W3176780013 @default.
• W3201541489 cites W4249022109 @default.
• W3201541489 doi "https://doi.org/10.1109/tcsvt.2021.3114209" @default.
• W3201541489 hasPublicationYear "2022" @default.
• W3201541489 type Work @default.
• W3201541489 sameAs 3201541489 @default.
• W3201541489 citedByCount "2" @default.
• W3201541489 countsByYear W32015414892023 @default.
• W3201541489 crossrefType "journal-article" @default.
• W3201541489 hasAuthorship W3201541489A5026184280 @default.
• W3201541489 hasAuthorship W3201541489A5029335401 @default.
• W3201541489 hasAuthorship W3201541489A5056776038 @default.
• W3201541489 hasAuthorship W3201541489A5072168215 @default.
• W3201541489 hasAuthorship W3201541489A5090796235 @default.
• W3201541489 hasBestOaLocation W32015414892 @default.
• W3201541489 hasConcept C119857082 @default.
• W3201541489 hasConcept C13280743 @default.
• W3201541489 hasConcept C138885662 @default.
• W3201541489 hasConcept C153180895 @default.
• W3201541489 hasConcept C154945302 @default.
• W3201541489 hasConcept C17744445 @default.
• W3201541489 hasConcept C185798385 @default.
• W3201541489 hasConcept C199539241 @default.
• W3201541489 hasConcept C205649164 @default.
• W3201541489 hasConcept C2776359362 @default.
• W3201541489 hasConcept C2776401178 @default.
• W3201541489 hasConcept C41008148 @default.
• W3201541489 hasConcept C41895202 @default.
• W3201541489 hasConcept C59404180 @default.
• W3201541489 hasConcept C94625758 @default.
• W3201541489 hasConcept C97931131 @default.
• W3201541489 hasConceptScore W3201541489C119857082 @default.
• W3201541489 hasConceptScore W3201541489C13280743 @default.
• W3201541489 hasConceptScore W3201541489C138885662 @default.
• W3201541489 hasConceptScore W3201541489C153180895 @default.
• W3201541489 hasConceptScore W3201541489C154945302 @default.
• W3201541489 hasConceptScore W3201541489C17744445 @default.
• W3201541489 hasConceptScore W3201541489C185798385 @default.
• W3201541489 hasConceptScore W3201541489C199539241 @default.
• W3201541489 hasConceptScore W3201541489C205649164 @default.
• W3201541489 hasConceptScore W3201541489C2776359362 @default.
• W3201541489 hasConceptScore W3201541489C2776401178 @default.
• W3201541489 hasConceptScore W3201541489C41008148 @default.
• W3201541489 hasConceptScore W3201541489C41895202 @default.
• W3201541489 hasConceptScore W3201541489C59404180 @default.
• W3201541489 hasConceptScore W3201541489C94625758 @default.
• W3201541489 hasConceptScore W3201541489C97931131 @default.
• W3201541489 hasIssue "6" @default.
• W3201541489 hasLocation W32015414891 @default.
• W3201541489 hasLocation W32015414892 @default.
• W3201541489 hasOpenAccess W3201541489 @default.
• W3201541489 hasPrimaryLocation W32015414891 @default.
• W3201541489 hasRelatedWork W1971623867 @default.
• W3201541489 hasRelatedWork W1982770690 @default.

• next