-
-
Real-time YOLOv5 + Intel RealSense D435 pipeline for depth-aware object detection and 3D coordinate extraction, enabling precise robotic arm grasping.
-
MiTPose Public
[INDIN25] Multi-granularity guided Vision Transformer for efficient 2D human pose estimation, combining refined-SCConv features with ViT-based local–global guidance.
-
VidTailor Public
Intelligent video-learning platform that analyzes viewing behavior to generate personalized questions, track errors, and enable social, feedback-rich learning.
-
Efficient-LLaDA-V Public
VisionZip-enhanced LLaDA-V for DLM inference, compressing visual tokens for faster, plug-and-play vision-aware reasoning with minimal quality loss.
-
FreeSwim Public
FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation
-
-
-
-
-
mmpose Public
Forked from open-mmlab/mmposeOpenMMLab Pose Estimation Toolbox and Benchmark.
-
mmdetection Public
Forked from open-mmlab/mmdetectionOpenMMLab Detection Toolbox and Benchmark
-
openpose Public
Forked from CMU-Perceptual-Computing-Lab/openposeOpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
{{ message }}