1 |
Still I Aspire: Graduate Degree Aspirations for Community College Transfer Students of Color
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Machine-readable Finnish-Livvi bilingual translation dictionary ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Machine-readable Finnish-Karelian bilingual translation dictionary ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Machine-readable Finnish-Karelian bilingual translation dictionary ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Machine-readable Northern Karelian Proper-Livvi bilingual translation dictionary ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Machine-readable Finnish-Livvi bilingual translation dictionary ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Machine-readable Northern Karelian Proper-Livvi bilingual translation dictionary ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
ETHNOCULTURAL AND SOCIOLINGUISTIC FACTORS IN TEACHING RUSSIAN AS A FOREIGN LANGUAGE ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Toward an Epistemic Web
|
|
|
|
In: 197 ; RatSWD Working Paper Series ; 22 (2022)
|
|
BASE
|
|
Show details
|
|
12 |
FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks
|
|
|
|
In: https://hal.inria.fr/hal-03462778 ; 2021 (2021)
|
|
Abstract:
In this paper, we present FaceTuneGAN, a new 3D face model representation decomposing and encoding separately facial identity and facial expression. We propose a first adaptation of image-toimage translation networks, that have successfully been used in the 2D domain, to 3D face geometry. Leveraging recently released large face scan databases, a neural network has been trained to decouple factors of variations with a better knowledge of the face, enabling facial expressions transfer and neutralization of expressive faces. Specifically, we design an adversarial architecture adapting the base architecture of FUNIT and using SpiralNet++ for our convolutional and sampling operations. Using two publicly available datasets (FaceScape and CoMA), FaceTuneGAN has a better identity decomposition and face neutralization than state-of-the-art techniques. It also outperforms classical deformation transfer approach by predicting blendshapes closer to ground-truth data and with less of undesired artifacts due to too different facial morphologies between source and target.
|
|
Keyword:
3D face; [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM]; Deep learning; Digital double; Expression transfer
|
|
URL: https://hal.inria.fr/hal-03462778 https://hal.inria.fr/hal-03462778/document https://hal.inria.fr/hal-03462778/file/2112.00532.pdf
|
|
BASE
|
|
Hide details
|
|
13 |
Phylogenetic Perspectives on the Relative Importance of Identity by Descent versus Borrowing in the Lexica of Altaic Languages
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03241668 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
14 |
Cross-lingual Representation Learning for Natural Language Processing
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Science research writing: for native and non-native speakers of English
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Fostering teacher language awareness in a primary English-language immersion school in France: supporting teachers on the road to engaging students’ bilingual competencies
|
|
|
|
In: ISSN: 0965-8416 ; Language Awareness ; https://hal.univ-lorraine.fr/hal-03573322 ; In press (2021)
|
|
BASE
|
|
Show details
|
|
17 |
Правовая природа передачи коносамента третьему лицу ... : Legal Nature of Transferring a Bill of Lading to a Third Party ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Bidirectional Transfer in the Emergence of Contact Varieties in Nagpur India ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Spanish-Catalan linguistic transfers: A study of lexical availability in Lleida ; Transferències lingüístiques castellà-català: un estudi de disponibilitat lèxica a Lleida
|
|
|
|
In: Treballs de Sociolingüística Catalana; Núm. 31 (2021): L’estandardologia comparada: teoria i pràctica; 149-164 (2021)
|
|
BASE
|
|
Show details
|
|
20 |
Flipping journals to open: Rethinking publishing infrastructure
|
|
|
|
In: 251 ; RatSWD Working Paper Series ; 9 (2021)
|
|
BASE
|
|
Show details
|
|
|
|