Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204623367> ?p ?o ?g. }
- W3204623367 abstract "Recent progress in stochastic motion prediction, i.e., predicting multiple possible future human motions given a single past pose sequence, has led to producing truly diverse future motions and even providing control over the motion of some body parts. However, to achieve this, the state-of-the-art method requires learning several mappings for diversity and a dedicated model for controllable motion prediction. In this paper, we introduce a unified deep generative network for both diverse and controllable motion prediction. To this end, we leverage the intuition that realistic human motions consist of smooth sequences of valid poses, and that, given limited data, learning a pose prior is much more tractable than a motion one. We therefore design a generator that predicts the motion of different body parts sequentially, and introduce a normalizing flow based pose prior, together with a joint angle loss, to achieve motion realism. Our experiments on two standard benchmark datasets, Human3.6M and HumanEva-I, demonstrate that our approach outperforms the state-of-the-art baselines in terms of both sample diversity and accuracy. The code is available at https://github.com/wei-mao-2019/gsps" @default.
- W3204623367 created "2021-10-11" @default.
- W3204623367 creator A5038564277 @default.
- W3204623367 creator A5049300388 @default.
- W3204623367 creator A5049924712 @default.
- W3204623367 date "2021-10-01" @default.
- W3204623367 modified "2023-10-05" @default.
- W3204623367 title "Generating Smooth Pose Sequences for Diverse Human Motion Prediction" @default.
- W3204623367 cites W1735317348 @default.
- W3204623367 cites W1970565565 @default.
- W3204623367 cites W2012856192 @default.
- W3204623367 cites W2025647058 @default.
- W3204623367 cites W2097278008 @default.
- W3204623367 cites W2099333815 @default.
- W3204623367 cites W2101032778 @default.
- W3204623367 cites W2124609748 @default.
- W3204623367 cites W2293741035 @default.
- W3204623367 cites W2343568200 @default.
- W3204623367 cites W2469134594 @default.
- W3204623367 cites W2594167370 @default.
- W3204623367 cites W2611706523 @default.
- W3204623367 cites W2623550831 @default.
- W3204623367 cites W2793483732 @default.
- W3204623367 cites W2902149428 @default.
- W3204623367 cites W2963324990 @default.
- W3204623367 cites W2963669520 @default.
- W3204623367 cites W2964203186 @default.
- W3204623367 cites W2964290934 @default.
- W3204623367 cites W2978956737 @default.
- W3204623367 cites W2982573856 @default.
- W3204623367 cites W2983925976 @default.
- W3204623367 cites W2993797559 @default.
- W3204623367 cites W3004407381 @default.
- W3204623367 cites W3034938233 @default.
- W3204623367 cites W3048550213 @default.
- W3204623367 cites W3172615168 @default.
- W3204623367 doi "https://doi.org/10.1109/iccv48922.2021.01306" @default.
- W3204623367 hasPublicationYear "2021" @default.
- W3204623367 type Work @default.
- W3204623367 sameAs 3204623367 @default.
- W3204623367 citedByCount "16" @default.
- W3204623367 countsByYear W32046233672021 @default.
- W3204623367 countsByYear W32046233672022 @default.
- W3204623367 countsByYear W32046233672023 @default.
- W3204623367 crossrefType "proceedings-article" @default.
- W3204623367 hasAuthorship W3204623367A5038564277 @default.
- W3204623367 hasAuthorship W3204623367A5049300388 @default.
- W3204623367 hasAuthorship W3204623367A5049924712 @default.
- W3204623367 hasBestOaLocation W32046233672 @default.
- W3204623367 hasConcept C104114177 @default.
- W3204623367 hasConcept C111472728 @default.
- W3204623367 hasConcept C119857082 @default.
- W3204623367 hasConcept C121332964 @default.
- W3204623367 hasConcept C132010649 @default.
- W3204623367 hasConcept C13280743 @default.
- W3204623367 hasConcept C138885662 @default.
- W3204623367 hasConcept C153083717 @default.
- W3204623367 hasConcept C154945302 @default.
- W3204623367 hasConcept C163258240 @default.
- W3204623367 hasConcept C185798385 @default.
- W3204623367 hasConcept C205649164 @default.
- W3204623367 hasConcept C2780992000 @default.
- W3204623367 hasConcept C2986578859 @default.
- W3204623367 hasConcept C31972630 @default.
- W3204623367 hasConcept C41008148 @default.
- W3204623367 hasConcept C48007421 @default.
- W3204623367 hasConcept C62520636 @default.
- W3204623367 hasConceptScore W3204623367C104114177 @default.
- W3204623367 hasConceptScore W3204623367C111472728 @default.
- W3204623367 hasConceptScore W3204623367C119857082 @default.
- W3204623367 hasConceptScore W3204623367C121332964 @default.
- W3204623367 hasConceptScore W3204623367C132010649 @default.
- W3204623367 hasConceptScore W3204623367C13280743 @default.
- W3204623367 hasConceptScore W3204623367C138885662 @default.
- W3204623367 hasConceptScore W3204623367C153083717 @default.
- W3204623367 hasConceptScore W3204623367C154945302 @default.
- W3204623367 hasConceptScore W3204623367C163258240 @default.
- W3204623367 hasConceptScore W3204623367C185798385 @default.
- W3204623367 hasConceptScore W3204623367C205649164 @default.
- W3204623367 hasConceptScore W3204623367C2780992000 @default.
- W3204623367 hasConceptScore W3204623367C2986578859 @default.
- W3204623367 hasConceptScore W3204623367C31972630 @default.
- W3204623367 hasConceptScore W3204623367C41008148 @default.
- W3204623367 hasConceptScore W3204623367C48007421 @default.
- W3204623367 hasConceptScore W3204623367C62520636 @default.
- W3204623367 hasLocation W32046233671 @default.
- W3204623367 hasLocation W32046233672 @default.
- W3204623367 hasOpenAccess W3204623367 @default.
- W3204623367 hasPrimaryLocation W32046233671 @default.
- W3204623367 hasRelatedWork W2002677354 @default.
- W3204623367 hasRelatedWork W2029249305 @default.
- W3204623367 hasRelatedWork W2144792299 @default.
- W3204623367 hasRelatedWork W2158695420 @default.
- W3204623367 hasRelatedWork W2159319861 @default.
- W3204623367 hasRelatedWork W2159704977 @default.
- W3204623367 hasRelatedWork W2169902574 @default.
- W3204623367 hasRelatedWork W2624451073 @default.
- W3204623367 hasRelatedWork W2649637180 @default.
- W3204623367 hasRelatedWork W2997897143 @default.
- W3204623367 isParatext "false" @default.