Florence2_table_by_Lihi_Gur_Arie.md

Task Category	Task Prompt	Description	Inputs	Outputs
Image Captioning	<CAPTION>	Generate a basic caption for an image	Image	Text
	<DETAILED_CAPTION>	Generate a detailed caption for an image	Image	Text
	<MORE_DETAILED_CAPTION>	Generate a very detailed caption for an image	Image	Text
	<REGION_TO_CATEGORY>	Generate a category label for a specified bounding box	Image, Bounding box	Text
	<REGION_TO_DESCRIPTION>	Generate a description for a specified bounding box	Image, Bounding box	Text
Object Detection	<OD>	Detect objects and generate bounding boxes with labels	Image	Bounding boxes, Text
	<DENSE_REGION_CAPTION>	Detect objects and generate bounding boxes with their captions	Image	Bounding boxes, Text
	<CAPTION_TO_PHRASE_GROUNDING>	Detect and ground phrases from the caption with bounding boxes	Image, Text	Bounding boxes, Text
	<OPEN_VOCABULARY_DETECTION>	Detect objects based on provided text (open vocabulary)	Image, Text	Bounding boxes, Text
	<REGION_PROPOSAL>	Propose regions of interest with bounding boxes	Image	Bounding boxes
Segmentation	<REFERRING_EXPRESSION_SEGMENTATION>	Generate a segmentation polygon based on text description	Image, Text	Polygon
	<REGION_TO_SEGMENTATION>	Generate a segmentation polygon for a given bounding box	Image, Bounding box	Polygon
OCR	<OCR>	Extract text from the entire image	Image	Text
	<OCR_WITH_REGION>	Extract text with location (bounding boxes or quadrilateral boxes)	Image	Text, Bounding boxes