Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327956077> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4327956077 endingPage "3907" @default.
- W4327956077 startingPage "3907" @default.
- W4327956077 abstract "Most of the recent works on optical flow estimation focus on introducing more effective CNNs or even the Transformer architecture that is quite popular in today’s CV field, but they all still follow the traditional two-frame input structure. In this paper, we argue that optical flow estimation should be more focused on the dynamic information in the image sequence. To that end, we present a straightforward but effective streaming framework equipped with a novel prediction module for capturing optical flow trends, which is a point that has not yet been discussed in previous works. By employing the backbone of the strong baseline to extract the stream of features from three consecutive frames as inputs, this module can predict the current state and update the previous changing trend of optical flow for feature fusion at the next stage. Additionally, we redesign the training loss, providing two new cost functions, in particular, to measure the variations in the optical flow trend. At the forward stage, we deploy a historical buffer to maintain the inference speed so that it is unaffected by additional input frames. Compared with the strong baseline, our method improves the average end-point error by 21.12% on Sintel Clean and 12.94% on Sintel Final. In addition, it also outperforms existing methods in real-world scenarios with low brightness or fast-moving targets." @default.
- W4327956077 created "2023-03-21" @default.
- W4327956077 creator A5041642544 @default.
- W4327956077 creator A5069949625 @default.
- W4327956077 creator A5080308075 @default.
- W4327956077 date "2023-03-19" @default.
- W4327956077 modified "2023-10-14" @default.
- W4327956077 title "Estimating Optical Flow with Streaming Perception and Changing Trend Aiming to Complex Scenarios" @default.
- W4327956077 cites W1513100184 @default.
- W4327956077 cites W1578285471 @default.
- W4327956077 cites W1921093919 @default.
- W4327956077 cites W2033959528 @default.
- W4327956077 cites W2082186050 @default.
- W4327956077 cites W2492517581 @default.
- W4327956077 cites W2560474170 @default.
- W4327956077 cites W2565639579 @default.
- W4327956077 cites W2809335043 @default.
- W4327956077 cites W2963091558 @default.
- W4327956077 cites W2963210183 @default.
- W4327956077 cites W2963482775 @default.
- W4327956077 cites W2963608065 @default.
- W4327956077 cites W2963782415 @default.
- W4327956077 cites W2963925437 @default.
- W4327956077 cites W2967636939 @default.
- W4327956077 cites W2980116241 @default.
- W4327956077 cites W3109870774 @default.
- W4327956077 cites W3147597595 @default.
- W4327956077 cites W3174911623 @default.
- W4327956077 cites W3175558068 @default.
- W4327956077 cites W3187838476 @default.
- W4327956077 cites W4312500310 @default.
- W4327956077 cites W4312636847 @default.
- W4327956077 cites W4312790276 @default.
- W4327956077 doi "https://doi.org/10.3390/app13063907" @default.
- W4327956077 hasPublicationYear "2023" @default.
- W4327956077 type Work @default.
- W4327956077 citedByCount "0" @default.
- W4327956077 crossrefType "journal-article" @default.
- W4327956077 hasAuthorship W4327956077A5041642544 @default.
- W4327956077 hasAuthorship W4327956077A5069949625 @default.
- W4327956077 hasAuthorship W4327956077A5080308075 @default.
- W4327956077 hasBestOaLocation W43279560771 @default.
- W4327956077 hasConcept C111368507 @default.
- W4327956077 hasConcept C115961682 @default.
- W4327956077 hasConcept C124101348 @default.
- W4327956077 hasConcept C12725497 @default.
- W4327956077 hasConcept C127313418 @default.
- W4327956077 hasConcept C154945302 @default.
- W4327956077 hasConcept C155542232 @default.
- W4327956077 hasConcept C2776214188 @default.
- W4327956077 hasConcept C41008148 @default.
- W4327956077 hasConcept C79403827 @default.
- W4327956077 hasConceptScore W4327956077C111368507 @default.
- W4327956077 hasConceptScore W4327956077C115961682 @default.
- W4327956077 hasConceptScore W4327956077C124101348 @default.
- W4327956077 hasConceptScore W4327956077C12725497 @default.
- W4327956077 hasConceptScore W4327956077C127313418 @default.
- W4327956077 hasConceptScore W4327956077C154945302 @default.
- W4327956077 hasConceptScore W4327956077C155542232 @default.
- W4327956077 hasConceptScore W4327956077C2776214188 @default.
- W4327956077 hasConceptScore W4327956077C41008148 @default.
- W4327956077 hasConceptScore W4327956077C79403827 @default.
- W4327956077 hasIssue "6" @default.
- W4327956077 hasLocation W43279560771 @default.
- W4327956077 hasOpenAccess W4327956077 @default.
- W4327956077 hasPrimaryLocation W43279560771 @default.
- W4327956077 hasRelatedWork W2063765648 @default.
- W4327956077 hasRelatedWork W2101452068 @default.
- W4327956077 hasRelatedWork W2123374136 @default.
- W4327956077 hasRelatedWork W2171116555 @default.
- W4327956077 hasRelatedWork W2586366378 @default.
- W4327956077 hasRelatedWork W2798573714 @default.
- W4327956077 hasRelatedWork W2900363363 @default.
- W4327956077 hasRelatedWork W2998452266 @default.
- W4327956077 hasRelatedWork W3196628752 @default.
- W4327956077 hasRelatedWork W4281553171 @default.
- W4327956077 hasVolume "13" @default.
- W4327956077 isParatext "false" @default.
- W4327956077 isRetracted "false" @default.
- W4327956077 workType "article" @default.