Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386869600> ?p ?o ?g. }
- W4386869600 endingPage "5295" @default.
- W4386869600 startingPage "5283" @default.
- W4386869600 abstract "Video frame interpolation (VFI) aims to generate predictive frames by motion-warping from bidirectional references. Most examples of VFI utilize spatiotemporal semantic information to realize motion estimation and interpolation. However, due to variable acceleration, irregular movement trajectories, and camera movement in real-world cases, they can not be sufficient to deal with non-linear middle frame estimation. In this paper, we present a reformulation of the VFI as a joint non-linear motion regression (JNMR) strategy to model the complicated inter-frame motions. Specifically, the motion trajectory between the target frame and multiple reference frames is regressed by a temporal concatenation of multi-stage quadratic models. Then, a comprehensive joint distribution is constructed to connect all temporal motions. Moreover, to reserve more contextual details for joint regression, the feature learning network is devised to explore clarified feature expressions with dense skip-connection. Later, a coarse-to-fine synthesis enhancement module is utilized to learn visual dynamics at different resolutions with multi-scale textures. The experimental VFI results show the effectiveness and significant improvement of joint motion regression over the state-of-the-art methods." @default.
- W4386869600 created "2023-09-20" @default.
- W4386869600 creator A5028127027 @default.
- W4386869600 creator A5047997849 @default.
- W4386869600 creator A5050402282 @default.
- W4386869600 creator A5070647495 @default.
- W4386869600 creator A5077780216 @default.
- W4386869600 date "2023-01-01" @default.
- W4386869600 modified "2023-10-15" @default.
- W4386869600 title "JNMR: Joint Non-linear Motion Regression for Video Frame Interpolation" @default.
- W4386869600 cites W2133665775 @default.
- W4386869600 cites W2324190721 @default.
- W4386869600 cites W2470139095 @default.
- W4386869600 cites W2560533888 @default.
- W4386869600 cites W2586480386 @default.
- W4386869600 cites W2738579427 @default.
- W4386869600 cites W2797683898 @default.
- W4386869600 cites W2877708277 @default.
- W4386869600 cites W2923834406 @default.
- W4386869600 cites W2949258649 @default.
- W4386869600 cites W2963093735 @default.
- W4386869600 cites W2963109922 @default.
- W4386869600 cites W2963741402 @default.
- W4386869600 cites W2963782415 @default.
- W4386869600 cites W2964156315 @default.
- W4386869600 cites W2964251418 @default.
- W4386869600 cites W2969260367 @default.
- W4386869600 cites W2972206791 @default.
- W4386869600 cites W2973673960 @default.
- W4386869600 cites W2997150500 @default.
- W4386869600 cites W2998645105 @default.
- W4386869600 cites W3012529009 @default.
- W4386869600 cites W3034921716 @default.
- W4386869600 cites W3035239272 @default.
- W4386869600 cites W3101403537 @default.
- W4386869600 cites W3102015846 @default.
- W4386869600 cites W3110612869 @default.
- W4386869600 cites W3128176988 @default.
- W4386869600 cites W3134680050 @default.
- W4386869600 cites W3138402025 @default.
- W4386869600 cites W3157035436 @default.
- W4386869600 cites W3168286621 @default.
- W4386869600 cites W3169457816 @default.
- W4386869600 cites W3173272744 @default.
- W4386869600 cites W3176148916 @default.
- W4386869600 cites W3184828860 @default.
- W4386869600 cites W3196358730 @default.
- W4386869600 cites W3197845860 @default.
- W4386869600 cites W3203041407 @default.
- W4386869600 cites W3210254606 @default.
- W4386869600 cites W4214602694 @default.
- W4386869600 cites W4214626557 @default.
- W4386869600 cites W4214761665 @default.
- W4386869600 cites W4226042183 @default.
- W4386869600 cites W4292793915 @default.
- W4386869600 cites W4308237661 @default.
- W4386869600 cites W4312324876 @default.
- W4386869600 cites W4312364368 @default.
- W4386869600 cites W4312409473 @default.
- W4386869600 cites W4312420501 @default.
- W4386869600 cites W4312546315 @default.
- W4386869600 cites W4312770027 @default.
- W4386869600 cites W4312852806 @default.
- W4386869600 cites W4312857869 @default.
- W4386869600 cites W4319301042 @default.
- W4386869600 cites W4386076420 @default.
- W4386869600 cites W764651262 @default.
- W4386869600 doi "https://doi.org/10.1109/tip.2023.3315122" @default.
- W4386869600 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37725732" @default.
- W4386869600 hasPublicationYear "2023" @default.
- W4386869600 type Work @default.
- W4386869600 citedByCount "0" @default.
- W4386869600 crossrefType "journal-article" @default.
- W4386869600 hasAuthorship W4386869600A5028127027 @default.
- W4386869600 hasAuthorship W4386869600A5047997849 @default.
- W4386869600 hasAuthorship W4386869600A5050402282 @default.
- W4386869600 hasAuthorship W4386869600A5070647495 @default.
- W4386869600 hasAuthorship W4386869600A5077780216 @default.
- W4386869600 hasConcept C10161872 @default.
- W4386869600 hasConcept C104114177 @default.
- W4386869600 hasConcept C121332964 @default.
- W4386869600 hasConcept C126042441 @default.
- W4386869600 hasConcept C1276947 @default.
- W4386869600 hasConcept C128840427 @default.
- W4386869600 hasConcept C13662910 @default.
- W4386869600 hasConcept C137800194 @default.
- W4386869600 hasConcept C138885662 @default.
- W4386869600 hasConcept C153180895 @default.
- W4386869600 hasConcept C154945302 @default.
- W4386869600 hasConcept C157202957 @default.
- W4386869600 hasConcept C167510206 @default.
- W4386869600 hasConcept C171836373 @default.
- W4386869600 hasConcept C172849965 @default.
- W4386869600 hasConcept C202474056 @default.
- W4386869600 hasConcept C2776401178 @default.
- W4386869600 hasConcept C31972630 @default.
- W4386869600 hasConcept C39394851 @default.
- W4386869600 hasConcept C41008148 @default.