{"id":"2308.01126","title":"Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model","url":"https://codeofpaper.com/paper/2308.01126","arxiv_url":"https://arxiv.org/abs/2308.01126","published":"2023-08-02","code":"official","best":{"full_name":"njucckevin/KnowCap","url":"https://github.com/njucckevin/KnowCap","tier":"official","stars":13,"license":null,"framework":null,"language":"Python","last_commit":"2024-02-15T02:00:51"},"most_starred_community":null,"implementations":[{"full_name":"njucckevin/KnowCap","url":"https://github.com/njucckevin/KnowCap","tier":"official","stars":13,"license":null,"framework":null,"language":"Python","last_commit":"2024-02-15T02:00:51"}],"possible_matches":1}