Abstract
Extracting structured information from videos is critical for numerous downstream applications in the industry. In this paper, we define a significant task of extracting hierarchical key information from visual texts on videos. To fulfill this task, we decouple it into four subtasks and introduce two implementation solutions called PipVKIE and UniVKIE. PipVKIE sequentially completes the four subtasks in continuous stages, while UniVKIE is improved by unifying all the subtasks into one backbone. Both PipVKIE and UniVKIE leverage multimodal information from vision, text, and coordinates for feature representation. Extensive experiments on one well-defined dataset demonstrate that our solutions can achieve remarkable performance and efficient inference speed.- Anthology ID:
- 2023.emnlp-industry.51
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Mingxuan Wang, Imed Zitouni
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 532–540
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-industry.51
- DOI:
- 10.18653/v1/2023.emnlp-industry.51
- Cite (ACL):
- Siyu An, Ye Liu, Haoyuan Peng, and Di Yin. 2023. VKIE: The Application of Key Information Extraction on Video Text. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 532–540, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- VKIE: The Application of Key Information Extraction on Video Text (An et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-industry.51.pdf