I agree that this site is using cookies. You can find further informations
here
.
X
Login
Merkliste (
0
)
Home
About us
Home About us
Our history
Profile
Press & public relations
Friends
The library in figures
Exhibitions
Projects
Training, internships, careers
Films
Services & Information
Home Services & Information
Lending and interlibrary loans
Returns and renewals
Training and library tours
My Account
Library cards
New to the library?
Download Information
Opening hours
Learning spaces
PC, WLAN, copy, scan and print
Catalogs and collections
Home Catalogs and Collections
Rare books and manuscripts
Digital collections
Subject Areas
Our sites
Home Our sites
Central Library
Law Library (Juridicum)
BB Business and Economics (BB11)
BB Physics and Electrical Engineering
TB Engineering and Social Sciences
TB Economics and Nautical Sciences
TB Music
TB Art & Design
TB Bremerhaven
Contact the library
Home Contact the library
Staff Directory
Open access & publishing
Home Open access & publishing
Reference management: Citavi & RefWorks
Publishing documents
Open Access in Bremen
zur Desktop-Version
Toggle navigation
Merkliste
1 Ergebnisse
1
Bipartite Graph Diffusion Model for Human Interaction Gener..:
Chopin, Baptiste
;
Tang, Hao
;
Daoudi, Mohamed
hal-04274209. , 2024
Link:
https://hal.science/hal-04274209
RT Journal T1
Bipartite Graph Diffusion Model for Human Interaction Generation ; Bipartite Graph Diffusion Model for Human Interaction Generation: The generation of natural human motion interactions is a hot topic in computer vision and computer animation. It is a challenging task due to the diversity of possible human motion interactions. Diffusion models, which have already shown remarkable generative capabilities in other domains, are a good candidate for this task. In this paper, we introduce a novel bipartite graph diffusion method (BiGraphDiff) to generate human motion interactions between two persons. Specifically, bipartite node sets are constructed to model the inherent geometric constraints between skeleton nodes during interactions. The interaction graph diffusion model is transformer-based, combining some state-of-the-art motion methods. We show that the proposed achieves new state-of-the-art results on leading benchmarks for the human interaction generation task
UL https://suche.suub.uni-bremen.de/peid=base-ftunivlille:oai:HAL:hal-04274209v1&Exemplar=1&LAN=DE A1 Chopin, Baptiste A1 Tang, Hao A1 Daoudi, Mohamed PB HAL CCSD YR 2024 K1 [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] JF hal-04274209 LK http://dx.doi.org/https://hal.science/hal-04274209 DO https://hal.science/hal-04274209 SF ELIB - SuUB Bremen
Export
RefWorks (nur Desktop-Version!)
Flow
(Zuerst in
Flow
einloggen, dann importieren)