FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309353854> ?p ?o ?g. }

• W4309353854 endingPage "36" @default.
• W4309353854 startingPage "19" @default.
• W4309353854 abstract "Computer vision is a rapidly growing segment of artificial intelligence, comprising diverse practical applications and practices. The interest and growth of computer vision are becoming sky-high nowadays due to its significant role in building a smart and autonomous society. The accumulated significance in the field of autonomous cars, smart buildings, video-surveillance systems, augmented-reality tools, and last not the least, fashion recommender system enforce human society to pay their keen interest in analyzing 1D, 2D, and 3D signals like speech, images, and videos, respectively. The hidden efforts become harder while stepping from speech to video due to dimensionality increment. But computer vision and its applications are mostly centered around the analysis of images and videos. Spatial interpretation plays a pivotal role in image analysis and both spatial and temporal understanding make things easier for video analysis. We can interpret the image as a stepping stone while analyzing video signals. A video signal carries greater significance among all three due to deeper situational understanding, as it has an extra-temporal dimension compared to an image signal. The introduction of deep learning makes the rest of things easier and has pushed the limits of possibility in the sphere of digital image and video processing. The deep-learning technique is nothing but all about “credit assignment” over multiple neural-network layers effectively and without supervision and is of current interest due to supporting evolutions in processing hardware. The self-organization and the collaborative management between atomic units of the network have been recognized to perform better than central control, especially for the complicated non-linear process. Improved fault tolerance and new data adaptability can be achieved through this technique. So, this chapter summarizes the significance of deep learning in digital-image processing that, in turn, leverages the processing of 3D video data." @default.
• W4309353854 created "2022-11-26" @default.
• W4309353854 creator A5070891194 @default.
• W4309353854 creator A5071873981 @default.
• W4309353854 date "2022-11-18" @default.
• W4309353854 modified "2023-09-24" @default.
• W4309353854 title "Image Segmentation and Classification Using Deep Learning" @default.
• W4309353854 cites W1969608379 @default.
• W4309353854 cites W2108305494 @default.
• W4309353854 cites W2112796928 @default.
• W4309353854 cites W2221079897 @default.
• W4309353854 cites W2412782625 @default.
• W4309353854 cites W2565516711 @default.
• W4309353854 cites W2592939477 @default.
• W4309353854 cites W2772752821 @default.
• W4309353854 cites W2791006446 @default.
• W4309353854 cites W2959397617 @default.
• W4309353854 cites W2962914239 @default.
• W4309353854 cites W2963300546 @default.
• W4309353854 cites W2963881378 @default.
• W4309353854 cites W2964115315 @default.
• W4309353854 cites W2964309882 @default.
• W4309353854 cites W3101639073 @default.
• W4309353854 cites W4288886033 @default.
• W4309353854 doi "https://doi.org/10.1002/9781119861850.ch2" @default.
• W4309353854 hasPublicationYear "2022" @default.
• W4309353854 type Work @default.
• W4309353854 citedByCount "1" @default.
• W4309353854 countsByYear W43093538542023 @default.
• W4309353854 crossrefType "other" @default.
• W4309353854 hasAuthorship W4309353854A5070891194 @default.
• W4309353854 hasAuthorship W4309353854A5071873981 @default.
• W4309353854 hasConcept C107457646 @default.
• W4309353854 hasConcept C108583219 @default.
• W4309353854 hasConcept C115961682 @default.
• W4309353854 hasConcept C154945302 @default.
• W4309353854 hasConcept C202444582 @default.
• W4309353854 hasConcept C31972630 @default.
• W4309353854 hasConcept C33923547 @default.
• W4309353854 hasConcept C41008148 @default.
• W4309353854 hasConcept C81363708 @default.
• W4309353854 hasConcept C89600930 @default.
• W4309353854 hasConcept C9417928 @default.
• W4309353854 hasConcept C9652623 @default.
• W4309353854 hasConceptScore W4309353854C107457646 @default.
• W4309353854 hasConceptScore W4309353854C108583219 @default.
• W4309353854 hasConceptScore W4309353854C115961682 @default.
• W4309353854 hasConceptScore W4309353854C154945302 @default.
• W4309353854 hasConceptScore W4309353854C202444582 @default.
• W4309353854 hasConceptScore W4309353854C31972630 @default.
• W4309353854 hasConceptScore W4309353854C33923547 @default.
• W4309353854 hasConceptScore W4309353854C41008148 @default.
• W4309353854 hasConceptScore W4309353854C81363708 @default.
• W4309353854 hasConceptScore W4309353854C89600930 @default.
• W4309353854 hasConceptScore W4309353854C9417928 @default.
• W4309353854 hasConceptScore W4309353854C9652623 @default.
• W4309353854 hasLocation W43093538541 @default.
• W4309353854 hasOpenAccess W4309353854 @default.
• W4309353854 hasPrimaryLocation W43093538541 @default.
• W4309353854 hasRelatedWork W2731899572 @default.
• W4309353854 hasRelatedWork W2795209768 @default.
• W4309353854 hasRelatedWork W3102253946 @default.
• W4309353854 hasRelatedWork W3133861977 @default.
• W4309353854 hasRelatedWork W3144574764 @default.
• W4309353854 hasRelatedWork W4226289457 @default.
• W4309353854 hasRelatedWork W4293211451 @default.
• W4309353854 hasRelatedWork W4308191152 @default.
• W4309353854 hasRelatedWork W4312417841 @default.
• W4309353854 hasRelatedWork W4321369474 @default.
• W4309353854 isParatext "false" @default.
• W4309353854 isRetracted "false" @default.
• W4309353854 workType "other" @default.