id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_tceqre6zufbqtbs622wyplrr6a	Shiry Ginosar	Detecting people in Cubist art	2015	16	.pdf	application/pdf	6074	456	58	Most evaluations of object detection methods focus on robustness to natural form deformations such as people's pose changes. current object detection methods perform on these distorted images, and present an evaluation comparing human annotators to four stateof-the-art object detectors on Cubist paintings. in object detection, human perception and part-based models exhibit To this end, we compare human annotations of person figures in Picasso paintings to the detections of several object study the human and algorithm performance on person detection over a corpus of Cubist paintings. human perception and detectors as the distortion of person figures in the paintings increases. We compare the human recognition performance we measured during the perception study to four object detection methods. and the four methods at detecting human figures in Picasso paintings. evaluate object detection performance as image distortion increases. methods, trained on natural images, and human perception on Cubist paintings	./cache/work_tceqre6zufbqtbs622wyplrr6a.pdf	./txt/work_tceqre6zufbqtbs622wyplrr6a.txt