Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963173685> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2963173685 endingPage "80" @default.
- W2963173685 startingPage "71" @default.
- W2963173685 abstract "Abstract When you see a person in a crowd, occluded by other persons, you miss visual information that can be used to recognize, re-identify or simply classify him or her. You can imagine its appearance given your experience, nothing more. Similarly, AI solutions can try to hallucinate missing information with specific deep learning architectures, suitably trained with people with and without occlusions. The goal of this work is to generate a complete image of a person, given an occluded version in input, that should be a) without occlusion b) similar at pixel level to a completely visible people shape c) capable to conserve similar visual attributes (e.g. male/female) of the original one. For the purpose, we propose a new approach by integrating the state-of-the-art of neural network architectures, namely U-nets and GANs, as well as discriminative attribute classification nets, with an architecture specifically designed to de-occlude people shapes. The network is trained to optimize a Loss function which could take into account the aforementioned objectives. As well we propose two datasets for testing our solution: the first one, occluded RAP, created automatically by occluding real shapes of the RAP dataset created by Li et al. (2016) (which collects also attributes of the people aspect); the second is a large synthetic dataset, AiC, generated in computer graphics with data extracted from the GTA video game, that contains 3D data of occluded objects by construction. Results are impressive and outperform any other previous proposal. This result could be an initial step to many further researches to recognize people and their behavior in an open crowded world." @default.
- W2963173685 created "2019-07-30" @default.
- W2963173685 creator A5030948871 @default.
- W2963173685 creator A5035698273 @default.
- W2963173685 creator A5036461417 @default.
- W2963173685 creator A5046832330 @default.
- W2963173685 creator A5075481810 @default.
- W2963173685 date "2019-05-01" @default.
- W2963173685 modified "2023-09-24" @default.
- W2963173685 title "Can adversarial networks hallucinate occluded people with a plausible aspect?" @default.
- W2963173685 cites W1915485278 @default.
- W2963173685 cites W2051425894 @default.
- W2963173685 cites W2108598243 @default.
- W2963173685 cites W2111025459 @default.
- W2963173685 cites W2129100877 @default.
- W2963173685 cites W2331128040 @default.
- W2963173685 cites W2344132218 @default.
- W2963173685 cites W2410968923 @default.
- W2963173685 cites W2550580161 @default.
- W2963173685 cites W2731516742 @default.
- W2963173685 cites W2796867881 @default.
- W2963173685 cites W2963073614 @default.
- W2963173685 cites W2963097270 @default.
- W2963173685 cites W2963218601 @default.
- W2963173685 cites W2963365374 @default.
- W2963173685 cites W2963420272 @default.
- W2963173685 cites W2963470893 @default.
- W2963173685 cites W2963917315 @default.
- W2963173685 cites W2964238416 @default.
- W2963173685 cites W2964337551 @default.
- W2963173685 cites W2315889990 @default.
- W2963173685 doi "https://doi.org/10.1016/j.cviu.2019.03.007" @default.
- W2963173685 hasPublicationYear "2019" @default.
- W2963173685 type Work @default.
- W2963173685 sameAs 2963173685 @default.
- W2963173685 citedByCount "9" @default.
- W2963173685 countsByYear W29631736852020 @default.
- W2963173685 countsByYear W29631736852021 @default.
- W2963173685 countsByYear W29631736852022 @default.
- W2963173685 countsByYear W29631736852023 @default.
- W2963173685 crossrefType "journal-article" @default.
- W2963173685 hasAuthorship W2963173685A5030948871 @default.
- W2963173685 hasAuthorship W2963173685A5035698273 @default.
- W2963173685 hasAuthorship W2963173685A5036461417 @default.
- W2963173685 hasAuthorship W2963173685A5046832330 @default.
- W2963173685 hasAuthorship W2963173685A5075481810 @default.
- W2963173685 hasBestOaLocation W29631736851 @default.
- W2963173685 hasConcept C119857082 @default.
- W2963173685 hasConcept C154945302 @default.
- W2963173685 hasConcept C2911011789 @default.
- W2963173685 hasConcept C31972630 @default.
- W2963173685 hasConcept C37736160 @default.
- W2963173685 hasConcept C41008148 @default.
- W2963173685 hasConceptScore W2963173685C119857082 @default.
- W2963173685 hasConceptScore W2963173685C154945302 @default.
- W2963173685 hasConceptScore W2963173685C2911011789 @default.
- W2963173685 hasConceptScore W2963173685C31972630 @default.
- W2963173685 hasConceptScore W2963173685C37736160 @default.
- W2963173685 hasConceptScore W2963173685C41008148 @default.
- W2963173685 hasFunder F4320321873 @default.
- W2963173685 hasLocation W29631736851 @default.
- W2963173685 hasLocation W29631736852 @default.
- W2963173685 hasLocation W29631736853 @default.
- W2963173685 hasOpenAccess W2963173685 @default.
- W2963173685 hasPrimaryLocation W29631736851 @default.
- W2963173685 hasRelatedWork W1891287906 @default.
- W2963173685 hasRelatedWork W1969923398 @default.
- W2963173685 hasRelatedWork W2122243982 @default.
- W2963173685 hasRelatedWork W2134545995 @default.
- W2963173685 hasRelatedWork W2772917594 @default.
- W2963173685 hasRelatedWork W2951343759 @default.
- W2963173685 hasRelatedWork W2961085424 @default.
- W2963173685 hasRelatedWork W2963173685 @default.
- W2963173685 hasRelatedWork W3130912106 @default.
- W2963173685 hasRelatedWork W3175382666 @default.
- W2963173685 hasVolume "182" @default.
- W2963173685 isParatext "false" @default.
- W2963173685 isRetracted "false" @default.
- W2963173685 magId "2963173685" @default.
- W2963173685 workType "article" @default.