Abstract
The growing popularity of video content for acquiring knowledge highlights the need for efficient methods to extract relevant information from videos. Visual Answer Localization (VAL) is a solution to this challenge, as it identifies video clips that can provide answers to user questions. In this paper, we explore the VAL task using the Chinese Medical instructional video dataset as part of the CMIVQA track1 shared task. However, VAL encounters difficulties due to differences between visual and textual modalities. Existing VAL methods use separate video and text encoding streams, as well as cross encoders, to align and predict relevant video clips. To address this issue, we adopt prompt-based learning, a successful paradigm in Natural Language Processing (NLP). Prompt-based learning reformulates downstream tasks to simulate the masked language modeling task used in pre-training, using a textual prompt. In our work, we develop a prompt template for the VAL task and employ the prompt learning approach. Additionally, we integrate an asymmetric co-attention module to enhance the integration of video and text modalities and facilitate their mutual interaction. Through comprehensive experiments, we demonstrate the effectiveness of our proposed methods, achieving first place in the CMIVQA track1 leaderboard with a total score of 0.3891 in testB.
Z. Zhou, J. Liu and S. Cheng—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Temporal sentence grounding in videos: a survey and future directions. arXiv preprint arXiv:2201.08071 (2022)
Tang, H., Zhu, J., Liu, M., Gao, Z., Cheng, Z.: Frame-wise cross-modal matching for video moment retrieval. IEEE Trans. Multimedia 24, 1338–1349 (2021)
Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. arXiv preprint arXiv:1809.01696 (2018)
Li, B., Weng, Y., Sun, B., Li, S.: Towards visual-prompt temporal answering grounding in medical instructional video. arXiv preprint arXiv:2203.06667 (2022)
Weng, Y., Li, B.: Visual answer localization with cross-modal mutual knowledge transfer. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5. IEEE (2023)
Anne Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5803–5812 (2017)
Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Span-based localizing network for natural language video localization. arXiv preprint arXiv:2004.13931 (2020)
Li, B., Weng, Y., Sun, B., Li, S.: Learning to locate visual answer in video corpus using question. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5. IEEE (2023)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)
Radford, A., Jeffrey, W., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)
Petroni, F., et al.: Language models as knowledge bases? arXiv preprint arXiv:1909.01066 (2019)
Talmor, A., Elazar, Y., Goldberg, Y., Berant, J.: oLMpics-on what language model pre-training captures. Trans. Assoc. Comput. Linguist. 8, 743–758 (2020)
Liu, J., Cheng, S., Zhou, Z., Gu, Y., Ye, J., Luo, H.: Enhancing multilingual document-grounded dialogue using cascaded prompt-based post-training models. In: Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, Toronto, Canada, pp. 44–51. Association for Computational Linguistics (2023)
Schick, T., Schütze, H.: Exploiting cloze questions for few shot text classification and natural language inference. arXiv preprint arXiv:2001.07676 (2020)
Li, C., et al.: mPLUG: effective and efficient vision-language learning by cross-modal skip-connections. arXiv preprint arXiv:2205.12005 (2022)
Zhang, J., et al.: Fengshenbang 1.0: being the foundation of Chinese cognitive intelligence. CoRR, abs/2209.02970 (2022)
Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 305–321 (2018)
Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)
Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299–6308 (2017)
Gupta, D., Attal, K., Demner-Fushman, D.: A dataset for medical instructional video classification and question answering. Sci. Data 10(1), 158 (2023)
Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., Hu, G.: Revisiting pre-trained models for Chinese natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, pp. 657–668. Association for Computational Linguistics (2020)
Cui, Y., Che, W., Liu, T., Qin, B., Yang, Z.: Pre-training with whole word masking for Chinese BERT. arXiv preprint arXiv:1906.08101 (2019)
Acknowledgement
This work was supported in part by the National Key Research and Development Program under Grant 2020YFB2104200 the National Natural Science Foundation of China under Grant 62261042 and 62002026, the Key Research Projects of the Joint Research Fund for Beijing Natural Science Foundation and the Fengtai Rail Transit Frontier Research Joint Fund under Grant L221003, the Strategic Priority Research Program of Chinese Academy of Sciences under Grant XDA28040500, and the Key Research and Development Project from Hebei Province under Grant 21310102D.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, Z., Liu, J., Cheng, S., Luo, H., Gu, Y., Ye, J. (2023). Improving Cross-Modal Visual Answer Localization in Chinese Medical Instructional Video Using Language Prompts. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2023. Lecture Notes in Computer Science(), vol 14304. Springer, Cham. https://doi.org/10.1007/978-3-031-44699-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-44699-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44698-6
Online ISBN: 978-3-031-44699-3
eBook Packages: Computer ScienceComputer Science (R0)