FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3192845000> ?p ?o ?g. }

• W3192845000 endingPage "1781" @default.
• W3192845000 startingPage "1773" @default.
• W3192845000 abstract "We introduce the task of open-vocabulary visual instance search (OVIS). Given an arbitrary textual search query, Open-vocabulary Visual Instance Search (OVIS) aims to return a ranked list of visual instances, i.e., image patches, that satisfies the search intent from an image database. The term ``open vocabulary'' means that there are neither restrictions to the visual instance to be searched nor restrictions to the word that can be used to compose the textual search query. We propose to address such a search challenge via visual-semantic aligned representation learning (ViSA). ViSA leverages massive image-caption pairs as weak image-level (not instance-level) supervision to learn a rich cross-modal semantic space where the representations of visual instances (not images) and those of textual queries are aligned, thus allowing us to measure the similarities between any visual instance and an arbitrary textual query. To evaluate the performance of ViSA, we build two datasets named OVIS40 and OVIS1600 and also introduce a pipeline for error analysis. Through extensive experiments on the two datasets, we demonstrate ViSA's ability to search for visual instances in images not available during training given a wide range of textual queries including those composed of uncommon words. Experimental results show that ViSA achieves an mAP@50 of 27.8% on OVIS40 and achieves a recall@30 of 21.3% on OVIS1400 dataset under the most challenging settings." @default.
• W3192845000 created "2021-08-16" @default.
• W3192845000 creator A5001916762 @default.
• W3192845000 creator A5015207417 @default.
• W3192845000 creator A5048295582 @default.
• W3192845000 creator A5074764224 @default.
• W3192845000 creator A5085245110 @default.
• W3192845000 date "2022-06-28" @default.
• W3192845000 modified "2023-09-25" @default.
• W3192845000 title "OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning" @default.
• W3192845000 cites W1861492603 @default.
• W3192845000 cites W1994488211 @default.
• W3192845000 cites W2007807439 @default.
• W3192845000 cites W2077069816 @default.
• W3192845000 cites W2088049833 @default.
• W3192845000 cites W2109424811 @default.
• W3192845000 cites W2109586012 @default.
• W3192845000 cites W2123024445 @default.
• W3192845000 cites W2131082717 @default.
• W3192845000 cites W2165558283 @default.
• W3192845000 cites W2194775991 @default.
• W3192845000 cites W2277195237 @default.
• W3192845000 cites W2295107390 @default.
• W3192845000 cites W2520774990 @default.
• W3192845000 cites W2575904063 @default.
• W3192845000 cites W2737244074 @default.
• W3192845000 cites W2755721434 @default.
• W3192845000 cites W2774267535 @default.
• W3192845000 cites W2798834175 @default.
• W3192845000 cites W2886641317 @default.
• W3192845000 cites W2889119508 @default.
• W3192845000 cites W2908510526 @default.
• W3192845000 cites W2920852583 @default.
• W3192845000 cites W2948672349 @default.
• W3192845000 cites W2954203194 @default.
• W3192845000 cites W2963341956 @default.
• W3192845000 cites W2963403868 @default.
• W3192845000 cites W2963603913 @default.
• W3192845000 cites W2970231061 @default.
• W3192845000 cites W2981613027 @default.
• W3192845000 cites W2991023920 @default.
• W3192845000 cites W2991662170 @default.
• W3192845000 cites W2995460200 @default.
• W3192845000 cites W2997591391 @default.
• W3192845000 cites W3018658244 @default.
• W3192845000 cites W3024464497 @default.
• W3192845000 cites W3035552787 @default.
• W3192845000 cites W3035712793 @default.
• W3192845000 cites W3090449556 @default.
• W3192845000 cites W3091588028 @default.
• W3192845000 cites W3093220398 @default.
• W3192845000 cites W3105232955 @default.
• W3192845000 cites W3155860693 @default.
• W3192845000 cites W7746136 @default.
• W3192845000 doi "https://doi.org/10.1609/aaai.v36i2.20070" @default.
• W3192845000 hasPublicationYear "2022" @default.
• W3192845000 type Work @default.
• W3192845000 sameAs 3192845000 @default.
• W3192845000 citedByCount "1" @default.
• W3192845000 countsByYear W31928450002022 @default.
• W3192845000 crossrefType "journal-article" @default.
• W3192845000 hasAuthorship W3192845000A5001916762 @default.
• W3192845000 hasAuthorship W3192845000A5015207417 @default.
• W3192845000 hasAuthorship W3192845000A5048295582 @default.
• W3192845000 hasAuthorship W3192845000A5074764224 @default.
• W3192845000 hasAuthorship W3192845000A5085245110 @default.
• W3192845000 hasBestOaLocation W31928450001 @default.
• W3192845000 hasConcept C138885662 @default.
• W3192845000 hasConcept C153180895 @default.
• W3192845000 hasConcept C154945302 @default.
• W3192845000 hasConcept C158495155 @default.
• W3192845000 hasConcept C166423231 @default.
• W3192845000 hasConcept C17744445 @default.
• W3192845000 hasConcept C199539241 @default.
• W3192845000 hasConcept C204321447 @default.
• W3192845000 hasConcept C23123220 @default.
• W3192845000 hasConcept C2776359362 @default.
• W3192845000 hasConcept C2777601683 @default.
• W3192845000 hasConcept C41008148 @default.
• W3192845000 hasConcept C41895202 @default.
• W3192845000 hasConcept C94625758 @default.
• W3192845000 hasConcept C97854310 @default.
• W3192845000 hasConceptScore W3192845000C138885662 @default.
• W3192845000 hasConceptScore W3192845000C153180895 @default.
• W3192845000 hasConceptScore W3192845000C154945302 @default.
• W3192845000 hasConceptScore W3192845000C158495155 @default.
• W3192845000 hasConceptScore W3192845000C166423231 @default.
• W3192845000 hasConceptScore W3192845000C17744445 @default.
• W3192845000 hasConceptScore W3192845000C199539241 @default.
• W3192845000 hasConceptScore W3192845000C204321447 @default.
• W3192845000 hasConceptScore W3192845000C23123220 @default.
• W3192845000 hasConceptScore W3192845000C2776359362 @default.
• W3192845000 hasConceptScore W3192845000C2777601683 @default.
• W3192845000 hasConceptScore W3192845000C41008148 @default.
• W3192845000 hasConceptScore W3192845000C41895202 @default.
• W3192845000 hasConceptScore W3192845000C94625758 @default.
• W3192845000 hasConceptScore W3192845000C97854310 @default.
• W3192845000 hasIssue "2" @default.

• next