Articles in topic: Computer Vision
Page 1
TAPe detection: 100k parameters vs SOTA models
VOID: Netflix AI model for video editing with physics
VOID: object removal from video using diffusion
Virtual Try-On with AI: hybrid IDM-VTON and Leffa
Bbox augmentation in Albumentations: formats and errors
YOLOE: object detection without fine-tuning
Superframe in YOLOv11: detection in video
TAPe without transformers: patch associations
TAPe embeddings: 74% on COCO without transformers
TAPe on COCO: 98% accuracy with boxes
Perspective Extraction from Images: Sobel + Hough
JPEG and visual neurophysiology: how the format deceives the eye
