FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035254087> ?p ?o ?g. }

• W3035254087 abstract "Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) proposes one solution to this problem. ZSL trains a model once, and generalizes to new tasks whose classes are not present in the training dataset. We propose the first end-to-end algorithm for ZSL in video classification. Our training procedure builds on insights from recent video classification literature and uses a trainable 3D CNN to learn the visual features. This is in contrast to previous video ZSL methods, which use pretrained feature extractors. We also extend the current benchmarking paradigm: Previous techniques aim to make the test task unknown at training time but fall short of this goal. We encourage domain shift across training and test data and disallow tailoring a ZSL model to a specific test dataset. We outperform the state-of-the-art by a wide margin. Our code, evaluation procedure and model weights are available online github.com/bbrattoli/ZeroShotVideoClassification." @default.
• W3035254087 created "2020-06-19" @default.
• W3035254087 creator A5002114219 @default.
• W3035254087 creator A5026825380 @default.
• W3035254087 creator A5053016380 @default.
• W3035254087 creator A5074576698 @default.
• W3035254087 creator A5083440236 @default.
• W3035254087 date "2020-06-01" @default.
• W3035254087 modified "2023-10-14" @default.
• W3035254087 title "Rethinking Zero-Shot Video Classification: End-to-End Training for Realistic Applications" @default.
• W3035254087 cites W1522734439 @default.
• W3035254087 cites W1805946669 @default.
• W3035254087 cites W2016053056 @default.
• W3035254087 cites W2017814585 @default.
• W3035254087 cites W2064675550 @default.
• W3035254087 cites W2108598243 @default.
• W3035254087 cites W2117539524 @default.
• W3035254087 cites W2126579184 @default.
• W3035254087 cites W2163922914 @default.
• W3035254087 cites W2194775991 @default.
• W3035254087 cites W2289324734 @default.
• W3035254087 cites W2336403884 @default.
• W3035254087 cites W2346746376 @default.
• W3035254087 cites W2463762378 @default.
• W3035254087 cites W2507611421 @default.
• W3035254087 cites W2560023338 @default.
• W3035254087 cites W2560129302 @default.
• W3035254087 cites W2596142952 @default.
• W3035254087 cites W2618530766 @default.
• W3035254087 cites W2625366777 @default.
• W3035254087 cites W2724511873 @default.
• W3035254087 cites W2745436507 @default.
• W3035254087 cites W2948077755 @default.
• W3035254087 cites W2962914678 @default.
• W3035254087 cites W2962931121 @default.
• W3035254087 cites W2962934715 @default.
• W3035254087 cites W2963037989 @default.
• W3035254087 cites W2963150697 @default.
• W3035254087 cites W2963152432 @default.
• W3035254087 cites W2963155035 @default.
• W3035254087 cites W2963524571 @default.
• W3035254087 cites W2963608065 @default.
• W3035254087 cites W2963689837 @default.
• W3035254087 cites W2984192355 @default.
• W3035254087 cites W3034403061 @default.
• W3035254087 cites W3099206234 @default.
• W3035254087 cites W639708223 @default.
• W3035254087 doi "https://doi.org/10.1109/cvpr42600.2020.00467" @default.
• W3035254087 hasPublicationYear "2020" @default.
• W3035254087 type Work @default.
• W3035254087 sameAs 3035254087 @default.
• W3035254087 citedByCount "50" @default.
• W3035254087 countsByYear W30352540872019 @default.
• W3035254087 countsByYear W30352540872020 @default.
• W3035254087 countsByYear W30352540872021 @default.
• W3035254087 countsByYear W30352540872022 @default.
• W3035254087 countsByYear W30352540872023 @default.
• W3035254087 crossrefType "proceedings-article" @default.
• W3035254087 hasAuthorship W3035254087A5002114219 @default.
• W3035254087 hasAuthorship W3035254087A5026825380 @default.
• W3035254087 hasAuthorship W3035254087A5053016380 @default.
• W3035254087 hasAuthorship W3035254087A5074576698 @default.
• W3035254087 hasAuthorship W3035254087A5083440236 @default.
• W3035254087 hasBestOaLocation W30352540872 @default.
• W3035254087 hasConcept C119857082 @default.
• W3035254087 hasConcept C121332964 @default.
• W3035254087 hasConcept C134306372 @default.
• W3035254087 hasConcept C138885662 @default.
• W3035254087 hasConcept C144133560 @default.
• W3035254087 hasConcept C153180895 @default.
• W3035254087 hasConcept C153294291 @default.
• W3035254087 hasConcept C154945302 @default.
• W3035254087 hasConcept C162324750 @default.
• W3035254087 hasConcept C162853370 @default.
• W3035254087 hasConcept C16910744 @default.
• W3035254087 hasConcept C177264268 @default.
• W3035254087 hasConcept C178790620 @default.
• W3035254087 hasConcept C185592680 @default.
• W3035254087 hasConcept C187736073 @default.
• W3035254087 hasConcept C199360897 @default.
• W3035254087 hasConcept C2776401178 @default.
• W3035254087 hasConcept C2776760102 @default.
• W3035254087 hasConcept C2777211547 @default.
• W3035254087 hasConcept C2778344882 @default.
• W3035254087 hasConcept C2780451532 @default.
• W3035254087 hasConcept C33923547 @default.
• W3035254087 hasConcept C36503486 @default.
• W3035254087 hasConcept C41008148 @default.
• W3035254087 hasConcept C41895202 @default.
• W3035254087 hasConcept C51632099 @default.
• W3035254087 hasConcept C74296488 @default.
• W3035254087 hasConcept C774472 @default.
• W3035254087 hasConcept C86251818 @default.
• W3035254087 hasConceptScore W3035254087C119857082 @default.
• W3035254087 hasConceptScore W3035254087C121332964 @default.
• W3035254087 hasConceptScore W3035254087C134306372 @default.
• W3035254087 hasConceptScore W3035254087C138885662 @default.
• W3035254087 hasConceptScore W3035254087C144133560 @default.
• W3035254087 hasConceptScore W3035254087C153180895 @default.
• W3035254087 hasConceptScore W3035254087C153294291 @default.

• next