Jun Wang, Trung Bui, Bo He, Abhinav Shrivastava, Jielin Qiu, Zhaowen Wang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The goal of multimodal summarization is to extract the most important information from different modalities to form summaries. Unlike unimodal summarization, the multimodal summarization task explicitly leverages crossmodal information to help generate more reliable and highquality summaries. However, existing methods fail to leverage the temporal correspondence between different modalities and ignore the intrinsic correlation between different samples. To address this issue, we introduce Align and Attend Multimodal Summarization (A2Summ), a unified multimodal transformer-based model which can effectively align and attend the multimodal input. In addition, we propose two novel contrastive losses to model both inter-sample and intra-sample correlations. Extensive experiments on two standard video summarization datasets (TVSum and SumMe) and two multimodal summarization datasets (Daily Mail and CNN) demonstrate the superiority of A2Summ, achieving state-of-the-art performances on all datasets. Moreover, we collected a large-scale multimodal summarization dataset BLiSS, which contains livestream videos and transcribed texts with annotated summaries. Our code and dataset are publicly available at https://boheumd.github.io/A2Summ/.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.07284")
get_code_for_paper("2303.07284")
have("2303.07284")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.07284.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.07284)
Connect an agent — have() is free.