EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation
Paper • 2603.18739 • Published • 11
AI & ML interests
Real-time Visual Understanding and Perception Reliability and Robustness in Computer Vision Edge-centric AI for Efficient and Secure Visual Computing
Recent Activity
View all activity
Papers
View all Papers
Xiiiiii0220
authored 10
papers 15 days ago
SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
Paper • 2511.20157 • Published • 3
HTR-VT: Handwritten Text Recognition with Vision Transformer
Paper • 2409.08573 • Published
Real-Time Object Detection Meets DINOv3
Paper • 2509.20787 • Published • 11
VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning
Paper • 2505.23504 • Published • 8
SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements
Paper • 2503.07101 • Published • 2
Boosting Co-teaching with Compression Regularization for Label Noise
Paper • 2104.13766 • Published
Compressing Features for Learning with Noisy Labels
Paper • 2206.13140 • Published
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
Paper • 2301.06052 • Published
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
Paper • 2202.11539 • Published
Improve model card and add metadata
#1 opened 4 months ago
by 
nielsr
MrgicBook
updated 9
models 5 months ago
Intellindust/ECDet_S
9.94M • Updated • 45 • 2
Intellindust/ECDet_M
19.5M • Updated • 73 • 2
Intellindust/ECDet_L
Object Detection • 33M • Updated • 17 • 3
Intellindust/ECDet_X
50M • Updated • 19 • 2
Intellindust/ECSeg_S
10.5M • Updated • 9 • 2
Intellindust/ECSeg_M
20.4M • Updated • 18 • 2
Intellindust/ECSeg_L
34M • Updated • 26 • 2
Intellindust/ECSeg_X
51M • Updated • 4 • 2
Intellindust/ECPose_S
10M • Updated • 3 • 2