FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950809610> ?p ?o ?g. }

• W2950809610 abstract "We propose a new self-supervised CNN pre-training technique based on a novel auxiliary task called learning. In this task, the machine is asked to identify the unrelated or odd element from a set of otherwise related elements. We apply this technique to self-supervised video representation learning where we sample subsequences from videos and ask the network to learn to predict the odd video subsequence. The odd video subsequence is sampled such that it has wrong temporal order of frames while the even ones have the correct temporal order. Therefore, to generate a odd-one-out question no manual annotation is required. Our learning machine is implemented as multi-stream convolutional neural network, which is learned end-to-end. Using odd-one-out networks, we learn temporal representations for videos that generalizes to other related tasks such as action recognition. On action classification, our method obtains 60.3% on the UCF101 dataset using only UCF101 data for training which is approximately 10% better than current state-of-the-art self-supervised learning methods. Similarly, on HMDB51 dataset we outperform self-supervised state-of-the art methods by 12.7% on action classification task." @default.
• W2950809610 created "2019-06-27" @default.
• W2950809610 creator A5002625178 @default.
• W2950809610 creator A5042584066 @default.
• W2950809610 creator A5056977175 @default.
• W2950809610 creator A5090467618 @default.
• W2950809610 date "2016-11-21" @default.
• W2950809610 modified "2023-09-27" @default.
• W2950809610 title "Self-Supervised Video Representation Learning With Odd-One-Out Networks" @default.
• W2950809610 cites W1570662310 @default.
• W2950809610 cites W1926645898 @default.
• W2950809610 cites W1983364832 @default.
• W2950809610 cites W2017257315 @default.
• W2950809610 cites W2018068650 @default.
• W2950809610 cites W2102409316 @default.
• W2950809610 cites W2105101328 @default.
• W2950809610 cites W2107789863 @default.
• W2950809610 cites W2108598243 @default.
• W2950809610 cites W2112796928 @default.
• W2950809610 cites W2117539524 @default.
• W2950809610 cites W2126579184 @default.
• W2950809610 cites W2138621090 @default.
• W2950809610 cites W2145038566 @default.
• W2950809610 cites W2146444479 @default.
• W2950809610 cites W2148349024 @default.
• W2950809610 cites W2163202312 @default.
• W2950809610 cites W2168345951 @default.
• W2950809610 cites W2190635018 @default.
• W2950809610 cites W2193384753 @default.
• W2950809610 cites W2219193941 @default.
• W2950809610 cites W2308045930 @default.
• W2950809610 cites W2321739425 @default.
• W2950809610 cites W24089286 @default.
• W2950809610 cites W2462996230 @default.
• W2950809610 cites W2464235600 @default.
• W2950809610 cites W2465313502 @default.
• W2950809610 cites W2471775118 @default.
• W2950809610 cites W2507009361 @default.
• W2950809610 cites W2524365899 @default.
• W2950809610 cites W2949888546 @default.
• W2950809610 cites W2950187998 @default.
• W2950809610 cites W2950551233 @default.
• W2950809610 cites W2951590555 @default.
• W2950809610 cites W2952453038 @default.
• W2950809610 cites W2952633803 @default.
• W2950809610 cites W2953066166 @default.
• W2950809610 cites W2953259386 @default.
• W2950809610 cites W2953360861 @default.
• W2950809610 cites W2963218601 @default.
• W2950809610 cites W2964227963 @default.
• W2950809610 hasPublicationYear "2016" @default.
• W2950809610 type Work @default.
• W2950809610 sameAs 2950809610 @default.
• W2950809610 citedByCount "7" @default.
• W2950809610 countsByYear W29508096102017 @default.
• W2950809610 countsByYear W29508096102018 @default.
• W2950809610 countsByYear W29508096102020 @default.
• W2950809610 countsByYear W29508096102021 @default.
• W2950809610 crossrefType "posted-content" @default.
• W2950809610 hasAuthorship W2950809610A5002625178 @default.
• W2950809610 hasAuthorship W2950809610A5042584066 @default.
• W2950809610 hasAuthorship W2950809610A5056977175 @default.
• W2950809610 hasAuthorship W2950809610A5090467618 @default.
• W2950809610 hasConcept C119857082 @default.
• W2950809610 hasConcept C121332964 @default.
• W2950809610 hasConcept C134306372 @default.
• W2950809610 hasConcept C136389625 @default.
• W2950809610 hasConcept C137877099 @default.
• W2950809610 hasConcept C153180895 @default.
• W2950809610 hasConcept C154945302 @default.
• W2950809610 hasConcept C162324750 @default.
• W2950809610 hasConcept C177264268 @default.
• W2950809610 hasConcept C17744445 @default.
• W2950809610 hasConcept C187736073 @default.
• W2950809610 hasConcept C199360897 @default.
• W2950809610 hasConcept C199539241 @default.
• W2950809610 hasConcept C2776321320 @default.
• W2950809610 hasConcept C2776359362 @default.
• W2950809610 hasConcept C2780451532 @default.
• W2950809610 hasConcept C2780791683 @default.
• W2950809610 hasConcept C33923547 @default.
• W2950809610 hasConcept C34388435 @default.
• W2950809610 hasConcept C41008148 @default.
• W2950809610 hasConcept C50644808 @default.
• W2950809610 hasConcept C59404180 @default.
• W2950809610 hasConcept C62520636 @default.
• W2950809610 hasConcept C81363708 @default.
• W2950809610 hasConcept C94625758 @default.
• W2950809610 hasConceptScore W2950809610C119857082 @default.
• W2950809610 hasConceptScore W2950809610C121332964 @default.
• W2950809610 hasConceptScore W2950809610C134306372 @default.
• W2950809610 hasConceptScore W2950809610C136389625 @default.
• W2950809610 hasConceptScore W2950809610C137877099 @default.
• W2950809610 hasConceptScore W2950809610C153180895 @default.
• W2950809610 hasConceptScore W2950809610C154945302 @default.
• W2950809610 hasConceptScore W2950809610C162324750 @default.
• W2950809610 hasConceptScore W2950809610C177264268 @default.
• W2950809610 hasConceptScore W2950809610C17744445 @default.
• W2950809610 hasConceptScore W2950809610C187736073 @default.
• W2950809610 hasConceptScore W2950809610C199360897 @default.

• next