Dong Tian
5 papers · 2018–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (2) π Academic Marathon (7) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
CVPR (4)
ICLR (1)
Top co-authors
Keywords
point cloud
(4)
representation learning
(2)
3d reconstruction
(2)
3d vision
(1)
geometric deep learning
(1)
topology learning
(1)
generative model
(1)
local structure
(1)
feature aggregation
(1)
graph pooling
(1)
flow estimation
(1)
point cloud reconstruction
(1)
scene flow
(1)
semantic learning
(1)
graph neural network
(1)
spatial-temporal attention
(1)
depth sensing
(1)
point cloud autoencoder
(1)
kernel correlation
(1)
unsupervised learning
(1)
Papers
TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
ICLR 2025
FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
CVPR 2021
TearingNet: Point Cloud Autoencoder To Learn Topology-Friendly Representations
CVPR 2021
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
CVPR 2018
Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
CVPR 2018