Filters








28,419 Hits in 5.4 sec

Pemodelan Karakter Animasi Wayang Orang Berbasis Motion Capture

Didit Prasetyo, Rabendra Yudistira Alamin
2017 Jurnal Desain Idea Jurnal Desain Produk Industri Institut Teknologi Sepuluh Nopember Surabaya  
The result of modeling stylized character animation based motion capture is expected to give the animator reference to working more effectively and efficiently.  ...  The character of puppet animation used in this study is the human character that is disproportionately designed the shape and size of the limbs while maintaining the main characteristics of human form.  ...  The result of modeling stylized character animation based motion capture is expected to give the animator reference to working more effectively and efficiently.  ... 
doi:10.12962/iptek_desain.v16i2.3591 fatcat:4aujitnagvddvcifjmowuasuym

Spectral style transfer for human motion between independent actions

M. Ersin Yumer, Niloy J. Mitra
2016 ACM Transactions on Graphics  
Automatic style transfer to transform the mood or identity of a character's motion is a key technology for increasing the value of already synthesized or captured motion data.  ...  Abstract Human motion is complex and difficult to synthesize realistically.  ...  Acknowledgements We thank the authors of for sharing their data.  ... 
doi:10.1145/2897824.2925955 fatcat:qbitoja4obfkxbmcyas3v3cssq

The impact of stylization on face recognition

Nicolas Olivier, Ludovic Hoyet, Fabien Danieau, Ferran Argelaguet, Quentin Avril, Anatole Lecuyer, Philippe Guillotel, Franck Multon
2020 ACM Symposium on Applied Perception 2020  
human model to capture the particularities of each specific face.  ...  Non-Human model.  ... 
doi:10.1145/3385955.3407930 fatcat:gbjavppuoncingkvzgbzr526r4

Synthesis and Control of High Resolution Facial Expressions for Visual Interactions

Chan-su Lee, Ahmed Elgammal, Dimitris Metaxas
2006 2006 IEEE International Conference on Multimedia and Expo  
The generative model provides control of expressiveness preserving nonlinear deformation in the expressions with simple parameters and allows synthesis of stylized facial geometry.  ...  The synthesis of facial expression with control of intensity and personal styles is important in intelligent and affective human-computer interaction, especially in face-to-face interaction between human  ...  of human face and bodies.  ... 
doi:10.1109/icme.2006.262551 dblp:conf/icmcs/LeeEM06 fatcat:rh7jamaz5vabhgcgw2vrcv4tde

A virtual reality setup for controllable, stylized real-time interactions between humans and avatars with sparse Gaussian process dynamical models

Nick Taubert, Martin Löffler, Nicolas Ludolph, Andrea Christensen, Dominik Endres, Martin A. Giese
2013 Proceedings of the ACM Symposium on Applied Perception - SAP '13  
We generate reactive motions by a dynamical extension of a hierarchical Gaussian process latent variable model, including latent dimensions for emotional style variation and target positions.  ...  Building on our previous work [Taubert et al. 2012 ], we present an approach for real-time interaction between a real human and an avatar.  ...  Introduction The probabilistic modeling of stylized interactive human motion is useful in technical fields like computer animation, but also for conducting experiments in psychology and neuroscience.  ... 
doi:10.1145/2492494.2492515 dblp:conf/apgv/TaubertLLCEG13 fatcat:ya2vdobipzabhbttnngzhz5hp4

Exploring the structure of a real-time, arbitrary neural artistic stylization network [article]

Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur, Vincent Dumoulin, Jonathon Shlens
2017 arXiv   pre-print
The model is successfully trained on a corpus of roughly 80,000 paintings and is able to generalize to paintings previously unobserved.  ...  In this paper, we present a method which combines the flexibility of the neural algorithm of artistic style with the speed of fast style transfer networks to allow real-time stylization using any content  ...  The stylizations from the grid captures two axis of style variations and correspond well to the neighboring embeddings of actual paintings.  ... 
arXiv:1705.06830v2 fatcat:ql4owqjjifbhbgalhcas3khdly

Stylized Dialogue Response Generation Using Stylized Unpaired Texts [article]

Yinhe Zheng, Zikai Chen, Rongsheng Zhang, Shilei Huang, Xiaoxi Mao, Minlie Huang
2020 arXiv   pre-print
This paper proposes a stylized dialogue generation method that can capture stylistic features embedded in unpaired texts.  ...  In this study, an inverse dialogue model is first introduced to predict possible posts for the input responses, and then this inverse model is used to generate stylized pseudo dialogue pairs based on these  ...  In this paper, we propose to build a stylized dialogue generation model that can capture stylistic features embedded in a set of unpaired texts D s .  ... 
arXiv:2009.12719v2 fatcat:rss7usvtl5a53j3cfzqrjqmbzm

Guess who? Multilingual approach for the automated generation of author-stylized poetry [article]

Alexey Tikhonov, Ivan P. Yamshchikov
2018 arXiv   pre-print
A version of a language model based on a long short-term memory (LSTM) artificial neural network with extended phonetic and semantic embeddings is used for stylized poetry generation.  ...  The experiments show that the proposed model consistently outperforms random sample and vanilla-LSTM baselines, humans also tend to associate machine generated texts with the target author.  ...  One can see that alongside with individual styles the model captures the style of the time mentioned earlier.  ... 
arXiv:1807.07147v3 fatcat:briyi3sjijel7e4vleru33jkhu

CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes [article]

Kim Youwang, Kim Ji-Yeon, Tae-Hyun Oh
2022 arXiv   pre-print
We propose CLIP-Actor, a text-driven motion recommendation and neural mesh stylization system for human mesh animation.  ...  We demonstrate that CLIP-Actor produces plausible and human-recognizable style 3D human mesh in motion with detailed geometry and texture solely from a natural language prompt.  ...  Texture and geometric stylization of human mesh in motion. Aside from 3D mesh pose, recent work has added different levels of details to bare human meshes, e.g., cloth modeling or texture color.  ... 
arXiv:2206.04382v2 fatcat:txb5tg5fbjdp7jtebhb2cc4e6e

Stylized and Performative Gaze for Character Animation

Tomislav Pejsa, Bilge Mutlu, Michael Gleicher
2013 Computer graphics forum (Print)  
Existing models of gaze motion for character animation simulate human movements, incorporating anatomical, neurophysiological, and functional constraints.  ...  In this paper, we extend a state-ofthe-art parametric model of human gaze motion with control parameters for specifying character geometry, gaze dynamics, and performative characteristics in order to create  ...  Pairwise contrasts showed no differences between the baseline and baseline stylized conditions, Overall, the results suggest that our gaze model does not change the communicative accuracy and the subjective  ... 
doi:10.1111/cgf.12034 fatcat:phqcrvgrkjgqrng5gt25o7hlu4

Learning Literary Style End-to-end with Artificial Neural Networks

Ivan P. Yamshchikov, Alexey Tikhonov
2019 Advances in Science, Technology and Engineering Systems  
A long short-term memory (LSTM) language model with extended phonetic and semantic embeddings is shown to capture poetic style when trained end-to-end without any expert knowledge.  ...  When a style of target author is recognized by the humans, they do not seem to distinguish generated texts and originals.  ...  The model clearly captures the style of the time mentioned earlier alongside the individual styles.  ... 
doi:10.25046/aj040614 fatcat:bebrh4kc2jex7bw6dfug2tjuem

Learning and transferring motion style using Sparse PCA

Khac Phong Do, Nguyen Xuan Thanh, Hongchuan Yu
2019 VNU Journal of Science Computer Science and Communication Engineering  
Myriads approaches have been developed to perform this task, however, the majority of them are data-driven, which require a large dataset and a time-consuming period for training a model in order to achieve  ...  Motion style transfer is a primary problem in computer animation, allowing us to convert the motion of an actor to that of another one.  ...  This work was supported by EU H2020 project-AniAge (No.691215), and by the project named "Multimedia application tools for intangible cultural heritage conservation and promotion" (No.  ... 
doi:10.25073/2588-1086/vnucsce.206 fatcat:imbhblaewbafziajxvv37nagqa

Appealing Female Avatars from 3D Body Scans: Perceptual Effects of Stylization

Reuben Fleming, Betty J. Mohler, Javier Romero, Michael J. Black, Martin Breidt
2016 Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
Using styles derived from existing popular character designs, we present a novel automatic stylization technique for body shape and colour information based on a statistical 3D model of human bodies.  ...  The inclusion of colour information and improvements to render quality had no significant effect on the overall perceived appeal of the avatars, and we observe that the body shape primarily drives the  ...  Acknowledgments We would like to thank Chris Ferguson, Joe Smallwood, Anna Wellerdiek and Michael Geuss as well as all the participants of our experiments and the anonymous reviewers.  ... 
doi:10.5220/0005683903330343 dblp:conf/grapp/FlemingM0BB16 fatcat:lnftlo3avfepbinyek3yod66da

Emotion control of unstructured dance movements

Andreas Aristidou, Qiong Zeng, Efstathios Stavrakis, KangKang Yin, Daniel Cohen-Or, Yiorgos Chrysanthou, Baoquan Chen
2017 Proceedings of the ACM SIGGRAPH / Eurographics Symposium on Computer Animation - SCA '17  
Motion capture technology has enabled the acquisition of high quality human motions for animating digital characters with extremely high delity.  ...  However, despite all the advances in motion editing and synthesis, it remains an open problem to modify pre-captured motions that are highly expressive, such as contemporary dances, for stylization and  ...  and the European Regional Development Fund and the Republic of Cyprus Research Promotion Foundation (DIDAKTOR/0311/73).  ... 
doi:10.1145/3099564.3099566 dblp:conf/sca/AristidouZSYCCC17 fatcat:qjbuanuhyfdnplafps3hgqvmrm

Limited correspondence in visual representation between the human brain and convolutional neural networks [article]

Yaoda Xu, Maryam Vaziri-Pashkam
2020 bioRxiv   pre-print
It has increasingly become a common practice in human fMRI research to regard CNNs as working model of the human visual system.  ...  Moreover, the lower layers of some CNNs could fully capture the representational structure of human early visual areas for both the original and filtered real-world object images.  ...  If CNNs are to aid or replace human performance, they need to capture the nature of human vision and then improve upon it.  ... 
doi:10.1101/2020.03.12.989376 fatcat:zyemigsbeneo5izxzyztqhrwbi
« Previous Showing results 1 — 15 out of 28,419 results