Type
Company
Country
—
Documents
184
through any edge
Papers
184
authorship edges
Awards made
—
Named as funder
—
Identifiers
Papers
Documents in the 44B Library with Megvii (China) on the authorship, newest first.
2025-10-19 · 10 authors here
Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter
2025-10-19 · 12 authors here
MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving
2025-08-01 · 8 authors here
Advancing 3D Object Detection With Depth-Aware Spatial Knowledge Distillation
2025-06-30 · 10 authors here
PADriver: Towards Personalized Autonomous Driving
2025-06-10 · 17 authors here
UniScene: Unified Occupancy-centric Driving Scene Generation
2025-06-10 · 9 authors here
Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models
2025-04-11 · 6 authors here
Single Image Rolling Shutter Removal with Diffusion Models
2025-04-11 · 7 authors here
Language Prompt for Autonomous Driving
2025-04-09 · 7 authors here
Bootstrap Masked Visual Modeling via Hard Patch Mining
2024-12-31 · 7 authors here
Localization-Guided Track: A Deep Association Multiobject Tracking Framework Based on Localization Confidence of Camera Detections
2024-10-26 · 4 authors here
Self-Supervised Visual Preference Alignment
2024-10-26 · 9 authors here
Class Balance Matters to Active Class-Incremental Learning
2024-10-14 · 5 authors here
QTrack: Embracing Quality Clues for Robust 3D Multi-Object Tracking
2024-10-07 · 8 authors here
GroupLane: End-to-End 3D Lane Detection With Channel-Wise Grouping
2024-07-26 · 3 authors here
Noise Optimized Conditional Diffusion for Domain Adaptation
2024-06-16 · 10 authors here
Panacea: Panoramic and Controllable Video Generation for Autonomous Driving
2024-06-16 · 6 authors here
FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models
2024-06-06 · 8 authors here
Style Variable and Irrelevant Learning for Generalizable Person Re-identification
2024-05-15 · 9 authors here
Exploring Recurrent Long-Term Temporal Fusion for Multi-View 3D Perception
2024-04-09 · 5 authors here
PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-Based 3D Object Detection
2024-03-24 · 7 authors here
GigaHumanDet: Exploring Full-Body Detection on Gigapixel-Level Images
2024-03-24 · 8 authors here
Far3D: Expanding the Horizon for Surround-View 3D Object Detection
2024-03-24 · 3 authors here
Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning
2024-03-11 · 7 authors here
DMHomo: Learning Homography with Diffusion Models
2023-10-28 · 5 authors here
SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference
Funding
Read from the funding tables, never from the document count — that count includes authorship, so it ranks institutions, not funders.
Who funds this work
Funders named on the papers above. The record holds no recipient field, so this is reached through the documents themselves — and the two columns are two different claims, kept apart.
Under a named grant
funding_awards — the award carries a grant number
Listed as funder
doc_funder_links — named, with no grant number