Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048306538> ?p ?o ?g. }
- W3048306538 endingPage "2007" @default.
- W3048306538 startingPage "1995" @default.
- W3048306538 abstract "Existing sketch-analysis work studies sketches depicting static objects or scenes. In this work, we propose a novel cross-modal retrieval problem of fine-grained instance-level sketch-based video retrieval (FG-SBVR), where a sketch sequence is used as a query to retrieve a specific target video instance. Compared with sketch-based still image retrieval, and coarse-grained category-level video retrieval, this is more challenging as both visual appearance and motion need to be simultaneously matched at a fine-grained level. We contribute the first FG-SBVR dataset with rich annotations. We then introduce a novel multi-stream multi-modality deep network to perform FG-SBVR under both strong and weakly supervised settings. The key component of the network is a relation module, designed to prevent model overfitting given scarce training data. We show that this model significantly outperforms a number of existing state-of-the-art models designed for video analysis." @default.
- W3048306538 created "2020-08-13" @default.
- W3048306538 creator A5014436524 @default.
- W3048306538 creator A5039812471 @default.
- W3048306538 creator A5046046128 @default.
- W3048306538 creator A5050501022 @default.
- W3048306538 creator A5077532535 @default.
- W3048306538 creator A5079650655 @default.
- W3048306538 creator A5087823932 @default.
- W3048306538 date "2021-05-01" @default.
- W3048306538 modified "2023-10-16" @default.
- W3048306538 title "Fine-Grained Instance-Level Sketch-Based Video Retrieval" @default.
- W3048306538 cites W1522734439 @default.
- W3048306538 cites W1788540011 @default.
- W3048306538 cites W1926243429 @default.
- W3048306538 cites W1947481528 @default.
- W3048306538 cites W1959016151 @default.
- W3048306538 cites W1972420097 @default.
- W3048306538 cites W1984314602 @default.
- W3048306538 cites W2021226554 @default.
- W3048306538 cites W2083118758 @default.
- W3048306538 cites W2108523493 @default.
- W3048306538 cites W2115328784 @default.
- W3048306538 cites W2119061765 @default.
- W3048306538 cites W2148953314 @default.
- W3048306538 cites W2183341477 @default.
- W3048306538 cites W2411243951 @default.
- W3048306538 cites W2461621749 @default.
- W3048306538 cites W2466618734 @default.
- W3048306538 cites W2496271548 @default.
- W3048306538 cites W2507009361 @default.
- W3048306538 cites W2588534625 @default.
- W3048306538 cites W2588651547 @default.
- W3048306538 cites W2600707098 @default.
- W3048306538 cites W2786585376 @default.
- W3048306538 cites W2808399042 @default.
- W3048306538 cites W2809562466 @default.
- W3048306538 cites W2882991827 @default.
- W3048306538 cites W2883117970 @default.
- W3048306538 cites W2883429621 @default.
- W3048306538 cites W2883534172 @default.
- W3048306538 cites W2938500406 @default.
- W3048306538 cites W2962934715 @default.
- W3048306538 cites W2963091558 @default.
- W3048306538 cites W2963307918 @default.
- W3048306538 cites W2963524571 @default.
- W3048306538 cites W2963645879 @default.
- W3048306538 cites W2963820951 @default.
- W3048306538 cites W2964105864 @default.
- W3048306538 cites W2964266708 @default.
- W3048306538 cites W2974319653 @default.
- W3048306538 cites W3014565582 @default.
- W3048306538 cites W3036435328 @default.
- W3048306538 cites W3099206234 @default.
- W3048306538 cites W2092639952 @default.
- W3048306538 doi "https://doi.org/10.1109/tcsvt.2020.3014491" @default.
- W3048306538 hasPublicationYear "2021" @default.
- W3048306538 type Work @default.
- W3048306538 sameAs 3048306538 @default.
- W3048306538 citedByCount "20" @default.
- W3048306538 countsByYear W30483065382020 @default.
- W3048306538 countsByYear W30483065382022 @default.
- W3048306538 countsByYear W30483065382023 @default.
- W3048306538 crossrefType "journal-article" @default.
- W3048306538 hasAuthorship W3048306538A5014436524 @default.
- W3048306538 hasAuthorship W3048306538A5039812471 @default.
- W3048306538 hasAuthorship W3048306538A5046046128 @default.
- W3048306538 hasAuthorship W3048306538A5050501022 @default.
- W3048306538 hasAuthorship W3048306538A5077532535 @default.
- W3048306538 hasAuthorship W3048306538A5079650655 @default.
- W3048306538 hasAuthorship W3048306538A5087823932 @default.
- W3048306538 hasBestOaLocation W30483065382 @default.
- W3048306538 hasConcept C11413529 @default.
- W3048306538 hasConcept C119857082 @default.
- W3048306538 hasConcept C13280743 @default.
- W3048306538 hasConcept C154945302 @default.
- W3048306538 hasConcept C185798385 @default.
- W3048306538 hasConcept C205649164 @default.
- W3048306538 hasConcept C22019652 @default.
- W3048306538 hasConcept C23123220 @default.
- W3048306538 hasConcept C26517878 @default.
- W3048306538 hasConcept C2779231336 @default.
- W3048306538 hasConcept C38652104 @default.
- W3048306538 hasConcept C41008148 @default.
- W3048306538 hasConcept C50644808 @default.
- W3048306538 hasConceptScore W3048306538C11413529 @default.
- W3048306538 hasConceptScore W3048306538C119857082 @default.
- W3048306538 hasConceptScore W3048306538C13280743 @default.
- W3048306538 hasConceptScore W3048306538C154945302 @default.
- W3048306538 hasConceptScore W3048306538C185798385 @default.
- W3048306538 hasConceptScore W3048306538C205649164 @default.
- W3048306538 hasConceptScore W3048306538C22019652 @default.
- W3048306538 hasConceptScore W3048306538C23123220 @default.
- W3048306538 hasConceptScore W3048306538C26517878 @default.
- W3048306538 hasConceptScore W3048306538C2779231336 @default.
- W3048306538 hasConceptScore W3048306538C38652104 @default.
- W3048306538 hasConceptScore W3048306538C41008148 @default.
- W3048306538 hasConceptScore W3048306538C50644808 @default.