{"id":"2305.12767","title":"D$^2$TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization","url":"https://codeofpaper.com/paper/2305.12767","arxiv_url":"https://arxiv.org/abs/2305.12767","published":"2023-05-22","code":"community","best":{"full_name":"XL2248/D2TV","url":"https://github.com/XL2248/D2TV","tier":"high_confidence_community","stars":3,"license":null,"framework":null,"language":"Python","last_commit":"2023-10-26T02:11:54"},"most_starred_community":null,"implementations":[{"full_name":"XL2248/D2TV","url":"https://github.com/XL2248/D2TV","tier":"high_confidence_community","stars":3,"license":null,"framework":null,"language":"Python","last_commit":"2023-10-26T02:11:54"}],"possible_matches":0}