SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.04514 · CVPR · 2023

DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment

Zhenguo Li, Wei Zhang, Xiaodan Liang, Hang Xu, Jianhua Han, Lewei Yao, Dan Xu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Abstract

Hand drawn black and white illustration, flying eagle with a snake in claws. (c) Curator looks on as we consider paintings in a shared studio space (b) Fried egg on a frying pan with cherry tomatoes and parsley (e) Little girl witch with black cat, owl, the witch's cauldron, ghost spirits and text on violet background. The concept of Halloween. (h) Dark eyed juvenile perched in a conifer (g) Playa Esmeralda in Holguin, Cuba. The view from the top of the beach. Beautiful Caribbean sea turquoise. (d) A SCUBA diver looks over his shoulder towards a sea lion (f) The Vibrant Tattoos Figure 1. Visualizations of DetCLIPv2 for open-vocabulary word-region alignment. DetCLIPv2 is able to detect broad concepts.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2304.04514")
get_code_for_paper("2304.04514")
have("2304.04514")

Connect an agent — have() is free.