CASA 2025: COMPUTER ANIMATION AND SOCIAL AGENTS 2025
TALK KEYWORD INDEX

This page contains an index consisting of author-provided keywords.

3
3D computer animation
3D Gaussian Splatting
3D head reconstruction
3D Human Motion
3D mesh Reconstruction
3D scene editing
A
Action unit
Action-role playing game
adaptive grids
adaptive sample selection
AI
AI Image Generation
AI Speech Recognition
ai-agent
Air stream
anisotropic L1-regularization
AR
Artificial Agents
Assets
Augmented reality
Avatar Reconstruction
avatar-based interactions
B
Ball levitating
BIM product
C
character animation
ChatGPT
Children’s education
Chinese character animation generation、
Chinese character culture
Chinese Landscape Painting
Chinese painting
CLIP
Co Speech Gestures
Coal Mine Safety
Coanda effect
computer animation
computer vision
contextual interaction
Contrastive Learning
Contrastive Regularization
Conversational agent
ConvNeXt
Craniofacial landmark detection
Cross-Modal Retrieval
Crowd simulation
CSPMotifsGAN
Cultural Heritage
cultural heritage  文化多样性
CycleGAN
D
dataset、
deep learning
Defocus Blur
demo
density-conditioned convolution
Dialogue Agent
Diffusion Model
diffusion models
Diverse feature extraction
dual-network framework
Dynamic Selection
E
Educational
Educational Games
EEG
EEG  脑电图
Embodied Conversational Agents
Evacuation Decision-Making
F
face morphing
FEM
Finite Element Method
Five-factor personality
Flexible Needle Steering
fluid simulation
Full-body interaction
Fuzzy sampling
G
Game companion
Game Design
Game experience
game-based learning
Gaussian splatting
Generative AI
Generative Model
Generative Models
Geometry processing
GPU
granular materials
Graphics
H
Haptic experience
Haptic streaming media
HCI
heat kernel
heat regression
High-level relation
high-order elements
Historical Analysis
hugs
human computer interaction
Human Motion
Human NeRF
I
Image Dehazing
image denoising
Image-Music Alignment
Immersion
immersive experience
Implicit surface
interaction
Interactivity
interface energy
J
joint label correction
K
keyframe animation
Knowledge Representation
L
L-system
label noise
Lagrangian simulation
Large Language Model
Large Language Models
Large-scale virtual scene
Latent common information
Lip and Identity Priors
literature survey
LLM
Local Feature Enhancement
M
machine learning
Marangoni effect
Mask R- CNN
material point method
medical reports
Medical Robotics
mesh extraction
mesh segmentation
Metaverse
Micro expression recognition
Mixed and Augmented Reality
mixed traffic
Modality difference
modeling
monitoring
Motif generation
Motion Capture & Retargeting
motion generation
motion in-betweening
motion inbetweening
Motion Style Transfer
multi-material coupling
multi-phase fluid dynamics
Multimodal Conversations
Multimodal interaction
Multimodal Learning
multiview segmentation
Music-driven
N
natural language processing
Navier-Stokes equations
NeRF
Neural painting
neural particle methods
Neural rendering
Non-player Character
Novel View Synthesis
Nurse Training
P
Painting generation
pedestrian simulation
Peridynamics
Personality perception
physically-based simulation
Piano Performance Animation
Pixel Art
Point cloud
point cloud segmentation
polygonizer
Pose and shape estimation
Pseudo-Labels
R
radiance fields
Railroad track
real-time rendering
real-time simulation
Real-time virtual-reality fusion
regional attention
Registration
reinforcement learning
Rendering
Representation
Retrieval Augmented Generation
Risk assessment
risk-aware assessment
robustness
S
Salient Object Detection
scene generation  场景生成
Scientific Illustration
Serious Game
serious games
shadow mitigation
shape control
Simulation
situational
sleep aid
Small Object Detection
soap bubble simulation
Social VR
sparse embedding
Spatial controller
Spatial-temporal
Spatial-Temporal Adapter
Speech-Driven
Speech-Driven 3D face animation
SPH
sphere approximation
Stroke renderer
strong-noise
style
Style Transfer
surface reconstruction
Surface sampling
surface tension
Swin Transformer
T
Talking Face Generation
target-driven control
Technology Acceptance Model
Technology Classroom Implementation
Temporal Action Detection
text-driven generation
textual narratives
Transformer-based
tree model
U
U-Net
Uniformity property
unsignalized environments
Unsupervised
User interface
V
Vertex Block Descent (VBD)
VI-ReID
Virtual Agents
Virtual Cinematography
Virtual Reality
virtual worlds
Virus Visualization
viscoelastic simulation
ViT
Volumetric Rendering
VR Education
VR Health Applications
VR relaxation
VR-based ASMR
VSLAM
W
Weisfeiler-Lehman kernel
wetting
Y
YOLOv8n
Z
zen cultural  禅宗文化
zero-shot generation