Junwei Zheng
12 papers · 2023–2026 · 5 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (29) 🤝 Dynamic Duo (11) 💎 Century Club · Bronze
🗃️
Keyword Collector
(54)
Top co-authors
Research topics
Computer Vision
(10)
Analysis
(8)
Machine Learning
(5)
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI · Artificial Intelligence
(4)
Core Methods
(4)
Processing
(3)
Techniques
(3)
Core AI · Computer Vision
(2)
Computer Science
(1)
Natural Language Processing
(1)
Application Areas · Machine Learning
(1)
Application Areas · Deep Learning
(1)
Applications
(1)
Keywords
document layout analysis
(3)
sparse attention
(2)
point cloud sampling
(2)
visual localization
(2)
vision-language model
(2)
object detection
(1)
shape analysis
(1)
action recognition
(1)
depth estimation
(1)
attention mechanism
(1)
3d vision
(1)
image retrieval
(1)
model robustness
(1)
edge detection
(1)
distance metric learning
(1)
perturbation analysis
(1)
performance evaluation
(1)
diffusion model
(1)
autoregressive model
(1)
visual question answering
(1)
Papers
HybriDLA: Hybrid Generation for Document Layout Analysis
AAAI 2026
More than the Sum: Panorama-Language Models for Adverse Omni-Scenes
CVPR 2026
RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization
CVPR 2026
@BENCH: Benchmarking Vision-Language Models for Human-Centered Assistive Technology
WACV 2025
Graph-based Document Structure Analysis
ICLR 2025
SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity
CVPR 2025
Scene-agnostic Pose Regression for Visual Localization
CVPR 2025
Navigating Open Set Scenarios for Skeleton-Based Action Recognition
AAAI 2024
Open Panoramic Segmentation
ECCV 2024
Referring Atomic Video Action Recognition
ECCV 2024
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
CVPR 2024
Attention-Based Point Cloud Edge Sampling
CVPR 2023