FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3157033490> ?p ?o ?g. }

• W3157033490 endingPage "278" @default.
• W3157033490 startingPage "265" @default.
• W3157033490 abstract "• We propose an end-to-end approach with a novel temporal-spatial pooling block (named STP) for action classification, which can learn pool discriminative frames and pixels in a certain clip. Our method achieves better performance than other state-of-the-art methods. • We propose a STP loss function, aiming to learn a sparse importance score in the temporal dimension, abandoning the redundant or invalid frames. • We present a ferryboat video database (named Ferryboat-4) for ferry action recognition. The database includes four action categories: Inshore, Offshore, Traffic, and Negative. We evaluate proposed STP and other state-of-the-art models on this database. Recently, deep convolutional neural networks have demonstrated great effectiveness in action recognition with both RGB and optical flow in the past decade. However, existing studies generally treat all frames and pixels equally, potentially leading to poor robustness of models. In this paper, we propose a novel parameter-free spatial–temporal pooling block (referred to as STP ) for action recognition in videos to address this challenge. STP is proposed to learn spatial and temporal weights, which are further used to guide information compression. Different from other temporal pooling layers, STP is more efficient as it discards the non-informative frames in a certain clip. In addition, STP applies a novel loss function that forces the model to learn information from sparse and discriminative frames. Moreover, we introduce a dataset for ferry action classification, named Ferryboat-4 , which includes four categories: Inshore , Offshore , Traffic , and Negative . This designed dataset can be used for the identification of ferries with abnormal behaviors, providing the essential information to support the supervision, management, and monitoring of ships. All the videos are acquired via real-world cameras. We perform extensive experiments on publicly available datasets as well as Ferryboat-4 and find that the proposed method outperforms several state-of-the-art methods in action classification. Source code and datasets are available at https://github.com/jiaming-wang/STP ." @default.
• W3157033490 created "2021-05-10" @default.
• W3157033490 creator A5015807909 @default.
• W3157033490 creator A5026947952 @default.
• W3157033490 creator A5030942549 @default.
• W3157033490 creator A5060706069 @default.
• W3157033490 creator A5070629154 @default.
• W3157033490 creator A5089404454 @default.
• W3157033490 date "2021-09-01" @default.
• W3157033490 modified "2023-10-07" @default.
• W3157033490 title "Spatial–temporal pooling for action recognition in videos" @default.
• W3157033490 cites W1595717062 @default.
• W3157033490 cites W1965718792 @default.
• W3157033490 cites W1983364832 @default.
• W3157033490 cites W2009285864 @default.
• W3157033490 cites W2065778157 @default.
• W3157033490 cites W2076225272 @default.
• W3157033490 cites W2086780859 @default.
• W3157033490 cites W2108333036 @default.
• W3157033490 cites W2109255472 @default.
• W3157033490 cites W2131842403 @default.
• W3157033490 cites W2193384753 @default.
• W3157033490 cites W2337252826 @default.
• W3157033490 cites W2507009361 @default.
• W3157033490 cites W2514167171 @default.
• W3157033490 cites W2548377017 @default.
• W3157033490 cites W2607408136 @default.
• W3157033490 cites W2751445731 @default.
• W3157033490 cites W2756464018 @default.
• W3157033490 cites W2797382244 @default.
• W3157033490 cites W2885291434 @default.
• W3157033490 cites W2913950831 @default.
• W3157033490 cites W2956093359 @default.
• W3157033490 cites W2963218601 @default.
• W3157033490 cites W2963246338 @default.
• W3157033490 cites W3000586902 @default.
• W3157033490 cites W3088979451 @default.
• W3157033490 cites W914561379 @default.
• W3157033490 doi "https://doi.org/10.1016/j.neucom.2021.04.071" @default.
• W3157033490 hasPublicationYear "2021" @default.
• W3157033490 type Work @default.
• W3157033490 sameAs 3157033490 @default.
• W3157033490 citedByCount "16" @default.
• W3157033490 countsByYear W31570334902021 @default.
• W3157033490 countsByYear W31570334902022 @default.
• W3157033490 countsByYear W31570334902023 @default.
• W3157033490 crossrefType "journal-article" @default.
• W3157033490 hasAuthorship W3157033490A5015807909 @default.
• W3157033490 hasAuthorship W3157033490A5026947952 @default.
• W3157033490 hasAuthorship W3157033490A5030942549 @default.
• W3157033490 hasAuthorship W3157033490A5060706069 @default.
• W3157033490 hasAuthorship W3157033490A5070629154 @default.
• W3157033490 hasAuthorship W3157033490A5089404454 @default.
• W3157033490 hasConcept C104317684 @default.
• W3157033490 hasConcept C119857082 @default.
• W3157033490 hasConcept C153180895 @default.
• W3157033490 hasConcept C154945302 @default.
• W3157033490 hasConcept C160633673 @default.
• W3157033490 hasConcept C185592680 @default.
• W3157033490 hasConcept C2524010 @default.
• W3157033490 hasConcept C2777210771 @default.
• W3157033490 hasConcept C33923547 @default.
• W3157033490 hasConcept C41008148 @default.
• W3157033490 hasConcept C55493867 @default.
• W3157033490 hasConcept C63479239 @default.
• W3157033490 hasConcept C70437156 @default.
• W3157033490 hasConcept C81363708 @default.
• W3157033490 hasConcept C82990744 @default.
• W3157033490 hasConcept C97931131 @default.
• W3157033490 hasConceptScore W3157033490C104317684 @default.
• W3157033490 hasConceptScore W3157033490C119857082 @default.
• W3157033490 hasConceptScore W3157033490C153180895 @default.
• W3157033490 hasConceptScore W3157033490C154945302 @default.
• W3157033490 hasConceptScore W3157033490C160633673 @default.
• W3157033490 hasConceptScore W3157033490C185592680 @default.
• W3157033490 hasConceptScore W3157033490C2524010 @default.
• W3157033490 hasConceptScore W3157033490C2777210771 @default.
• W3157033490 hasConceptScore W3157033490C33923547 @default.
• W3157033490 hasConceptScore W3157033490C41008148 @default.
• W3157033490 hasConceptScore W3157033490C55493867 @default.
• W3157033490 hasConceptScore W3157033490C63479239 @default.
• W3157033490 hasConceptScore W3157033490C70437156 @default.
• W3157033490 hasConceptScore W3157033490C81363708 @default.
• W3157033490 hasConceptScore W3157033490C82990744 @default.
• W3157033490 hasConceptScore W3157033490C97931131 @default.
• W3157033490 hasFunder F4320308448 @default.
• W3157033490 hasFunder F4320321001 @default.
• W3157033490 hasFunder F4320321106 @default.
• W3157033490 hasFunder F4320334924 @default.
• W3157033490 hasLocation W31570334901 @default.
• W3157033490 hasOpenAccess W3157033490 @default.
• W3157033490 hasPrimaryLocation W31570334901 @default.
• W3157033490 hasRelatedWork W2043075591 @default.
• W3157033490 hasRelatedWork W2136485282 @default.
• W3157033490 hasRelatedWork W2295107390 @default.
• W3157033490 hasRelatedWork W2514274290 @default.
• W3157033490 hasRelatedWork W2518599539 @default.
• W3157033490 hasRelatedWork W2546871836 @default.

• next