Kunyu Peng
19 papers · 2022–2026 · 8 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (43) π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π€ Dynamic Duo (14) π Grand Slam
π
Trend Setter
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(88)
π₯
Unstoppable Β· Bronze
β
The Questioner
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(6)
Top co-authors
Research topics
Computer Vision
(13)
Analysis
(12)
Deep Learning
(8)
Machine Learning
(7)
Artificial Intelligence
(6)
Core AI Β· Artificial Intelligence
(6)
Application Areas
(4)
Architectures
(4)
Learning Types Β· Machine Learning
(4)
Domain-Specific
(3)
Learning Types Β· Deep Learning
(3)
Interdisciplinary
(2)
Core AI Β· Computer Vision
(2)
Optimization & Theory
(2)
Science
(2)
Keywords
semantic segmentation
(7)
document layout analysis
(3)
domain adaptation
(3)
panoramic image
(3)
scene understanding
(2)
bird's eye view
(2)
open-set recognition
(2)
anomaly detection
(2)
prototype learning
(1)
action recognition
(1)
zero-shot learning
(1)
object detection
(1)
visual perception
(1)
model robustness
(1)
feature extraction
(1)
vision transformer
(1)
autonomous driving
(1)
multimodal learning
(1)
depth estimation
(1)
source-free domain adaptation
(1)
Papers
HybriDLA: Hybrid Generation for Document Layout Analysis
AAAI 2026
ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction
CVPR 2026
RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization
CVPR 2026
Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentation
CVPR 2026
Graph-based Document Structure Analysis
ICLR 2025
MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data
ICML 2025
Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation
ICCV 2025
360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye View
WACV 2024
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
NeurIPS 2024
Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations
NeurIPS 2024
Navigating Open Set Scenarios for Skeleton-Based Action Recognition
AAAI 2024
Occlusion-Aware Seamless Segmentation
ECCV 2024
Open Panoramic Segmentation
ECCV 2024
Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?
ICML 2024
Referring Atomic Video Action Recognition
ECCV 2024
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
CVPR 2024
Delivering Arbitrary-Modal Semantic Segmentation
CVPR 2023
Trans4Map: Revisiting Holistic Bird's-Eye-View Mapping From Egocentric Images to Allocentric Semantics With Vision Transformers
WACV 2023
Bending Reality: Distortion-Aware Transformers for Adapting to Panoramic Semantic Segmentation
CVPR 2022