Zigang Geng
6 papers · 2021–2024 · 3 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
Top co-authors
Research topics
Computer Vision
(6)
Deep Learning
(5)
Analysis
(4)
Machine Learning
(3)
Learning Types · Deep Learning
(3)
Core AI · Computer Vision
(2)
Core Methods
(2)
Processing
(2)
Artificial Intelligence
(1)
Architectures
(1)
Core AI · Artificial Intelligence
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Techniques
(1)
Keywords
discrete token
(2)
human pose estimation
(2)
representation learning
(2)
transfer learning
(1)
computer vision
(1)
self-supervised learning
(1)
model pretraining
(1)
point cloud
(1)
depth estimation
(1)
instance segmentation
(1)
instruction following
(1)
task generalization
(1)
token classification
(1)
occlusion handling
(1)
3d object detection
(1)
diffusion model
(1)
convolutional neural network
(1)
disentangled representation
(1)
position encoding
(1)
image manipulation
(1)
Papers
InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
CVPR 2024
V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
ICLR 2024
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
ICCV 2023
Human Pose As Compositional Tokens
CVPR 2023
Revealing the Dark Secrets of Masked Image Modeling
CVPR 2023
Bottom-Up Human Pose Estimation via Disentangled Keypoint Regression
CVPR 2021