Kunyu Peng
16 papers · 2022–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Conference Polyglot (8) π Cross-Pollinator (7) π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (5)
π
Cross-Pollinator
(7)
π€
Dynamic Duo
(12)
π
Grand Slam
π
Century Club
(15)
π₯
Unstoppable
(5)
β‘
Prolific Year
(9)
β
The Questioner
ποΈ
Keyword Collector
(63)
Conferences
CVPR (3)
ECCV (3)
AAAI (2)
ICML (2)
NIPS (2)
WACV (2)
ICCV (1)
ICLR (1)
Top co-authors
Research topics
Keywords
semantic segmentation
(6)
document layout analysis
(2)
bird's eye view
(2)
domain adaptation
(2)
scene understanding
(2)
panoramic image
(2)
source-free domain adaptation
(1)
action recognition
(1)
zero-shot learning
(1)
feature extraction
(1)
object detection
(1)
model robustness
(1)
vision transformer
(1)
multimodal learning
(1)
egocentric vision
(1)
pose estimation
(1)
feature embedding
(1)
human pose estimation
(1)
image translation
(1)
depth estimation
(1)
Papers
HybriDLA: Hybrid Generation for Document Layout Analysis
AAAI 2026
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
Graph-based Document Structure Analysis
ICLR 2025
Occlusion-Aware Seamless Segmentation
ECCV 2024
Referring Atomic Video Action Recognition
ECCV 2024
Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations
NIPS 2024
Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?
ICML 2024
Open Panoramic Segmentation
ECCV 2024
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
NIPS 2024
Navigating Open Set Scenarios for Skeleton-Based Action Recognition
AAAI 2024
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
CVPR 2024
360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye View
WACV 2024
Trans4Map: Revisiting Holistic Bird's-Eye-View Mapping From Egocentric Images to Allocentric Semantics With Vision Transformers
WACV 2023
Delivering Arbitrary-Modal Semantic Segmentation
CVPR 2023
Bending Reality: Distortion-Aware Transformers for Adapting to Panoramic Semantic Segmentation
CVPR 2022