Zi-Hang Jiang
5 papers · 2019–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
Venues
Top co-authors
Research topics
Computer Vision
(3)
Deep Learning
(3)
Machine Learning
(3)
Architectures
(3)
Artificial Intelligence
(2)
Core AI · Artificial Intelligence
(2)
Natural Language Processing
(1)
Analysis
(1)
Application Areas
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Processing
(1)
Keywords
image classification
(2)
vision transformer
(2)
semantic segmentation
(1)
feature learning
(1)
self-attention mechanism
(1)
knowledge distillation
(1)
model architecture
(1)
human pose estimation
(1)
neural architecture
(1)
computational efficiency
(1)
occlusion handling
(1)
disentangled representation
(1)
pre-trained language model
(1)
token representation
(1)
patch token
(1)
pose token
(1)
3d human mesh recovery
(1)
3d human mesh
(1)
mesh transformer
(1)
3d face shape
(1)
Papers
PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery
WACV 2025
All Tokens Matter: Token Labeling for Training Better Vision Transformers
NeurIPS 2021
Tokens-to-Token ViT: Training Vision Transformers From Scratch on ImageNet
ICCV 2021
ConvBERT: Improving BERT with Span-based Dynamic Convolution
NeurIPS 2020
Disentangled Representation Learning for 3D Face Shape
CVPR 2019