Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313056154> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4313056154 abstract "This paper presents a high-quality human motion pre-diction method that accurately predicts future human poses given observed ones. Our method is based on the observation that a good “initial guess” of the future poses is very helpful in improving the forecasting accuracy. This mo-tivates us to propose a novel two-stage prediction frame-work, including an init-prediction network that just computes the good guess and then a formal-prediction network that predicts the target future poses based on the guess. More importantly, we extend this idea further and design a multi-stage prediction framework where each stage pre-dicts initial guess for the next stage, which brings more performance gain. To fulfill the prediction task at each stage, we propose a network comprising Spatial Dense Graph Convolutional Networks (S-DGCN) and Temporal Dense Graph Convolutional Networks (T-DGCN). Alternatively executing the two networks helps extract spatiotem-poral features over the global receptive field of the whole pose sequence. All the above design choices cooperating together make our method outperform previous approaches by large margins: 6%-7% on Human3.6M, 5%-10% on CMU-MoCap, and 13%-16% on 3DPW. Code is available at https://github.com/705062791/PGBIG." @default.
- W4313056154 created "2023-01-06" @default.
- W4313056154 creator A5025851882 @default.
- W4313056154 creator A5027540915 @default.
- W4313056154 creator A5060829494 @default.
- W4313056154 creator A5067363489 @default.
- W4313056154 creator A5083221103 @default.
- W4313056154 date "2022-06-01" @default.
- W4313056154 modified "2023-10-14" @default.
- W4313056154 title "Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction" @default.
- W4313056154 cites W1735317348 @default.
- W4313056154 cites W1990429558 @default.
- W4313056154 cites W2064675550 @default.
- W4313056154 cites W2101032778 @default.
- W4313056154 cites W2594167370 @default.
- W4313056154 cites W2606517404 @default.
- W4313056154 cites W2802025241 @default.
- W4313056154 cites W2894846593 @default.
- W4313056154 cites W2963076818 @default.
- W4313056154 cites W2963158576 @default.
- W4313056154 cites W2963165299 @default.
- W4313056154 cites W2963548793 @default.
- W4313056154 cites W2964203186 @default.
- W4313056154 cites W2979930345 @default.
- W4313056154 cites W2982573856 @default.
- W4313056154 cites W2983925976 @default.
- W4313056154 cites W2993797559 @default.
- W4313056154 cites W2994175816 @default.
- W4313056154 cites W3034423770 @default.
- W4313056154 cites W3034696014 @default.
- W4313056154 cites W3035545045 @default.
- W4313056154 cites W3085920015 @default.
- W4313056154 cites W3101017148 @default.
- W4313056154 cites W3107501854 @default.
- W4313056154 cites W3109174848 @default.
- W4313056154 cites W3174292795 @default.
- W4313056154 cites W3203785074 @default.
- W4313056154 cites W3205071568 @default.
- W4313056154 cites W4230178929 @default.
- W4313056154 cites W4283800873 @default.
- W4313056154 doi "https://doi.org/10.1109/cvpr52688.2022.00633" @default.
- W4313056154 hasPublicationYear "2022" @default.
- W4313056154 type Work @default.
- W4313056154 citedByCount "20" @default.
- W4313056154 countsByYear W43130561542022 @default.
- W4313056154 countsByYear W43130561542023 @default.
- W4313056154 crossrefType "proceedings-article" @default.
- W4313056154 hasAuthorship W4313056154A5025851882 @default.
- W4313056154 hasAuthorship W4313056154A5027540915 @default.
- W4313056154 hasAuthorship W4313056154A5060829494 @default.
- W4313056154 hasAuthorship W4313056154A5067363489 @default.
- W4313056154 hasAuthorship W4313056154A5083221103 @default.
- W4313056154 hasBestOaLocation W43130561542 @default.
- W4313056154 hasConcept C119857082 @default.
- W4313056154 hasConcept C132525143 @default.
- W4313056154 hasConcept C154945302 @default.
- W4313056154 hasConcept C162324750 @default.
- W4313056154 hasConcept C177264268 @default.
- W4313056154 hasConcept C187736073 @default.
- W4313056154 hasConcept C199360897 @default.
- W4313056154 hasConcept C202444582 @default.
- W4313056154 hasConcept C2776760102 @default.
- W4313056154 hasConcept C2780451532 @default.
- W4313056154 hasConcept C33923547 @default.
- W4313056154 hasConcept C41008148 @default.
- W4313056154 hasConcept C80444323 @default.
- W4313056154 hasConcept C9652623 @default.
- W4313056154 hasConceptScore W4313056154C119857082 @default.
- W4313056154 hasConceptScore W4313056154C132525143 @default.
- W4313056154 hasConceptScore W4313056154C154945302 @default.
- W4313056154 hasConceptScore W4313056154C162324750 @default.
- W4313056154 hasConceptScore W4313056154C177264268 @default.
- W4313056154 hasConceptScore W4313056154C187736073 @default.
- W4313056154 hasConceptScore W4313056154C199360897 @default.
- W4313056154 hasConceptScore W4313056154C202444582 @default.
- W4313056154 hasConceptScore W4313056154C2776760102 @default.
- W4313056154 hasConceptScore W4313056154C2780451532 @default.
- W4313056154 hasConceptScore W4313056154C33923547 @default.
- W4313056154 hasConceptScore W4313056154C41008148 @default.
- W4313056154 hasConceptScore W4313056154C80444323 @default.
- W4313056154 hasConceptScore W4313056154C9652623 @default.
- W4313056154 hasFunder F4320321001 @default.
- W4313056154 hasFunder F4320321921 @default.
- W4313056154 hasLocation W43130561541 @default.
- W4313056154 hasLocation W43130561542 @default.
- W4313056154 hasOpenAccess W4313056154 @default.
- W4313056154 hasPrimaryLocation W43130561541 @default.
- W4313056154 hasRelatedWork W2081647779 @default.
- W4313056154 hasRelatedWork W2961085424 @default.
- W4313056154 hasRelatedWork W3046775127 @default.
- W4313056154 hasRelatedWork W3170094116 @default.
- W4313056154 hasRelatedWork W4205958290 @default.
- W4313056154 hasRelatedWork W4285260836 @default.
- W4313056154 hasRelatedWork W4286629047 @default.
- W4313056154 hasRelatedWork W4306321456 @default.
- W4313056154 hasRelatedWork W4306674287 @default.
- W4313056154 hasRelatedWork W4224009465 @default.
- W4313056154 isParatext "false" @default.
- W4313056154 isRetracted "false" @default.
- W4313056154 workType "article" @default.