FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197828681> ?p ?o ?g. }

• W3197828681 endingPage "7902" @default.
• W3197828681 startingPage "7889" @default.
• W3197828681 abstract "Moving object segmentation (MOS) in videos received considerable attention because of its broad security-based applications like robotics, outdoor video surveillance, self-driving cars, etc. The current prevailing algorithms highly depend on additional trained modules for other applications or complicated training procedures or neglect the inter-frame spatio-temporal structural dependencies. To address these issues, a simple, robust, and effective unified recurrent edge aggregation approach is proposed for MOS, in which additional trained modules or fine-tuning on a test video frame(s) are not required. Here, a recurrent edge aggregation module (REAM) is proposed to extract effective foreground relevant features capturing spatio-temporal structural dependencies with encoder and respective decoder features connected recurrently from previous frame. These REAM features are then connected to a decoder through skip connections for comprehensive learning named as temporal information propagation. Further, the motion refinement block with multi-scale dense residual is proposed to combine the features from the optical flow encoder stream and the last REAM module for holistic feature learning. Finally, these holistic features and REAM features are given to the decoder block for segmentation. To guide the decoder block, previous frame output with respective scales is utilized. The different configurations of training-testing techniques are examined to evaluate the performance of the proposed method. Specifically, outdoor videos often suffer from constrained visibility due to different environmental conditions and other small particles in the air that scatter the light in the atmosphere. Thus, comprehensive result analysis is conducted on six benchmark video datasets with different surveillance environments. We demonstrate that the proposed method outperforms the state-of-the-art methods for MOS without any pre-trained module, fine-tuning on the test video frame(s) or complicated training." @default.
• W3197828681 created "2021-09-13" @default.
• W3197828681 creator A5005888460 @default.
• W3197828681 creator A5011012522 @default.
• W3197828681 creator A5014376368 @default.
• W3197828681 creator A5022197727 @default.
• W3197828681 creator A5032409915 @default.
• W3197828681 creator A5050348715 @default.
• W3197828681 date "2021-01-01" @default.
• W3197828681 modified "2023-10-15" @default.
• W3197828681 title "An Unified Recurrent Video Object Segmentation Framework for Various Surveillance Environments" @default.
• W3197828681 cites W1994634851 @default.
• W3197828681 cites W2062520372 @default.
• W3197828681 cites W2116076678 @default.
• W3197828681 cites W2127070222 @default.
• W3197828681 cites W2138682569 @default.
• W3197828681 cites W2293332611 @default.
• W3197828681 cites W2339830253 @default.
• W3197828681 cites W2470139095 @default.
• W3197828681 cites W2511363568 @default.
• W3197828681 cites W2730874440 @default.
• W3197828681 cites W2745150820 @default.
• W3197828681 cites W2755190242 @default.
• W3197828681 cites W2759692151 @default.
• W3197828681 cites W2767970498 @default.
• W3197828681 cites W2792215676 @default.
• W3197828681 cites W2794847483 @default.
• W3197828681 cites W2799239273 @default.
• W3197828681 cites W2903118147 @default.
• W3197828681 cites W2911873662 @default.
• W3197828681 cites W2911981226 @default.
• W3197828681 cites W2916797271 @default.
• W3197828681 cites W2921997090 @default.
• W3197828681 cites W2925327970 @default.
• W3197828681 cites W2955084925 @default.
• W3197828681 cites W2957408986 @default.
• W3197828681 cites W2963073614 @default.
• W3197828681 cites W2963362118 @default.
• W3197828681 cites W2963395775 @default.
• W3197828681 cites W2963503215 @default.
• W3197828681 cites W2963823251 @default.
• W3197828681 cites W2964343881 @default.
• W3197828681 cites W2964486184 @default.
• W3197828681 cites W2964665981 @default.
• W3197828681 cites W2967043539 @default.
• W3197828681 cites W2967622921 @default.
• W3197828681 cites W2969435864 @default.
• W3197828681 cites W2970828071 @default.
• W3197828681 cites W2978122847 @default.
• W3197828681 cites W2986050084 @default.
• W3197828681 cites W2986056979 @default.
• W3197828681 cites W2987391422 @default.
• W3197828681 cites W2987878306 @default.
• W3197828681 cites W2989035356 @default.
• W3197828681 cites W2990205821 @default.
• W3197828681 cites W2995633856 @default.
• W3197828681 cites W3009499989 @default.
• W3197828681 cites W3016796243 @default.
• W3197828681 cites W3020334921 @default.
• W3197828681 cites W3034263000 @default.
• W3197828681 cites W3034538699 @default.
• W3197828681 cites W3034578106 @default.
• W3197828681 cites W3034731255 @default.
• W3197828681 cites W3035295069 @default.
• W3197828681 cites W3035646552 @default.
• W3197828681 cites W3042841817 @default.
• W3197828681 cites W3049318984 @default.
• W3197828681 cites W3087299940 @default.
• W3197828681 cites W3088227529 @default.
• W3197828681 cites W3112318124 @default.
• W3197828681 cites W3132368316 @default.
• W3197828681 cites W4300179783 @default.
• W3197828681 doi "https://doi.org/10.1109/tip.2021.3108405" @default.
• W3197828681 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34478367" @default.
• W3197828681 hasPublicationYear "2021" @default.
• W3197828681 type Work @default.
• W3197828681 sameAs 3197828681 @default.
• W3197828681 citedByCount "19" @default.
• W3197828681 countsByYear W31978286812022 @default.
• W3197828681 countsByYear W31978286812023 @default.
• W3197828681 crossrefType "journal-article" @default.
• W3197828681 hasAuthorship W3197828681A5005888460 @default.
• W3197828681 hasAuthorship W3197828681A5011012522 @default.
• W3197828681 hasAuthorship W3197828681A5014376368 @default.
• W3197828681 hasAuthorship W3197828681A5022197727 @default.
• W3197828681 hasAuthorship W3197828681A5032409915 @default.
• W3197828681 hasAuthorship W3197828681A5050348715 @default.
• W3197828681 hasConcept C111919701 @default.
• W3197828681 hasConcept C115961682 @default.
• W3197828681 hasConcept C118505674 @default.
• W3197828681 hasConcept C120665830 @default.
• W3197828681 hasConcept C121332964 @default.
• W3197828681 hasConcept C123403432 @default.
• W3197828681 hasConcept C124504099 @default.
• W3197828681 hasConcept C126042441 @default.
• W3197828681 hasConcept C13280743 @default.
• W3197828681 hasConcept C138885662 @default.
• W3197828681 hasConcept C153180895 @default.

• next