Abstract
In this work, we consider the problem of weakly-supervised multi-step localization in instructional videos. An established approach to this problem is to rely on a given list of steps. However, in reality, there is often more than one way to execute a procedure successfully, by following the set of steps in slightly varying orders. Thus, for successful localization in a given video, recent works require the actual order of procedure steps in the video, to be provided by human annotators at both training and test times. Instead, here, we only rely on generic procedural text that is not tied to a specific video. We represent the various ways to complete the procedure by transforming the list of instructions into a procedure flow graph which captures the partial order of steps. Using the flow graphs reduces both training and test time annotation requirements. To this end, we introduce the new problem of flow graph to video grounding. In this setup, we seek the optimal step ordering consistent with the procedure flow graph and a given video. To solve this problem, we propose a new algorithm - Graph2Vid - that infers the actual ordering of steps in the video and simultaneously localizes them. To show the advantage of our proposed formulation, we extend the CrossTask dataset with procedure flow graph information. Our experiments show that Graph2Vid is both more efficient than the baselines and yields strong step localization results, without the need for step order annotation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The tSort graph is polynomial for an assumed subset of flow graphs with a fixed maximum number of threads.
- 2.
We find the procedure text of CrossTask in www.wikihow.com.
References
Bi, J., Luo, J., Xu, C.: Procedure planning in instructional videos via contextual modeling and model-based policy learning. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)
Cai, X., Xu, T., Yi, J., Huang, J., Rajasekaran, S.: DTWNet: A dynamic time warping network. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)
Cao, K., Ji, J., Cao, Z., Chang, C., Niebles, J.C.: Few-shot video classification via temporal alignment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Chang, C., Huang, D., Sui, Y., Fei-Fei, L., Niebles, J.C.: D3TW: Discriminative differentiable dynamic time warping for weakly supervised action alignment and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Chang, C.Y., Huang, D.A., Xu, D., Adeli, E., Fei-Fei, L., Niebles, J.C.: Procedure planning in instructional videos. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)
Chang, X., Tung, F., Mori, G.: Learning discriminative prototypes with dynamic time warping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
Cuturi, M., Blondel, M.: Soft-DTW: A differentiable loss function for time-series. In: International Conference on Machine Learning (ICML) (2017)
Ding, L., Xu, C.: Weakly-supervised action segmentation with iterative soft boundary assignment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Donatelli, L., Schmidt, T., Biswas, D., Köhn, A., Zhai, F., Koller, A.: Aligning actions across recipe graphs. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
Dvornik, N., Hadji, I., Derpanis, K.G., Garg, A., Jepson, A.: Drop-DTW: Aligning common signal between sequences while dropping outliers. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)
Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., Zisserman, A.: Temporal cycle-consistency learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Caba Heilbron, F., Victor Escorcia, B.G., Niebles, J.C.: ActivityNet: A large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Girdhar, R., Grauman, K.: Anticipative Video Transformer. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)
Hadji, I., Derpanis, K.G., Jepson, A.D.: Representation learning via global temporal alignment and cycle-consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
Huang, D., Fei-Fei, L., Niebles, J.C.: Connectionist temporal modeling for weakly supervised action labeling. In: Proceedings of the European Conference on Computer Vision (ECCV) (2016)
Jain, C., Zhang, H., Gao, Y., Aluru, S.: On the complexity of sequence to graph alignment. J. Comput. Biol. 27(4), 640–654 (2020)
Kavya, V.N.S., Tayal, K., Srinivasan, R., Sivadasan, N.: Sequence alignment on directed graphs. J. Comput. Biol. : J. Comput. Mol. Cell Biol. 261, 53–67 (2019)
Kiddon, C., Ponnuraj, G.T., Zettlemoyer, L., Choi, Y.: Mise en place: Unsupervised interpretation of instructional recipes. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2015)
Lee, C., Grasso, C., Sharlow, M.F.: Multiple sequence alignment using partial order graphs. Bioinformatics 18(3), 452–464 (2002)
Luo, H., et al.: UniVL: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)
Ma, M., Fan, H., Kitani, K.M.: Going deeper into first-person activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-End Learning of Visual Representations from Uncurated Instructional Videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips. In: Proceedings of the International Conference on Computer Vision (ICCV) (2019)
Müller, M.: Information Retrieval for Music and Motion. Springer-Verlag, Berlin, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74048-3
Nakatsu, N., Kambayashi, Y., Yajima, S.: A longest common subsequence algorithm suitable for similar text strings. Acta Inf. 18(2), 17–19 (1982)
Navarro, G.: Improved approximate pattern matching on hypertext. Theoret. Comput. Sci. 237(1), 455–463 (2000)
Needleman, S.B., Wunsch, C.D.: A general method applicable to the search for similarities in the amino acid sequence of two proteins. J. Mol. Biol. 48(3), 443–453 (1970)
Rautiainen, M., Mäkinen, V., Marschall, T.: Bit-parallel sequence-to-graph alignment. Bioinformatics 35(19), 3599–3607 (2019)
Richard, A., Kuehne, H., Iqbal, A., Gall, J.: NeuralNetwork-Viterbi: A framework for weakly supervised video learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken processing recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol.26, pp. 43–49 (1978)
Sakurai, Y., Faloutsos, C., Yamamuro, M.: Stream monitoring under the time warping distance. In: International Conference on Data Engineering (ICDE) (2007)
Schumacher, P., Minor, M., Walter, K., Bergmann, R.: Extraction of procedural knowledge from the web: A comparison of two workflow extraction approaches. In: Proceedings of the 21st International Conference on World Wide Web (2012)
Senner, F., Yao, A.: Zero-shot anticipation for instructional activities (2019)
Sermanet, P., et al.: Time-contrastive networks: Self-supervised learning from video. In: IEEE International Conference on Robotics and Automation (ICRA) (2018)
Smith, T.F., Waterman, M.S.: Identification of common molecular subsequences. J. Mol. Biol. 147(1), 195–197 (1981)
Tang, Y., et al.: COIN: A large-scale dataset for comprehensive instructional video analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Wikipedia: Topological sorting – Wikipedia, the free encyclopedia. https://en.wikipedia.org/w/index.php?title=Topological%20sorting &oldid=1062117596. Accessed 07 Mar 2022
Yamakata, Y., Mori, S., Carroll, J.: English recipe flow graph corpus. In: Proceedings of the 12th Language Resources and Evaluation Conference (2020)
Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Just Ask: Learning to Answer Questions from Millions of Narrated Videos. In: Proceedings of the International Conference on Computer Vision (ICCV), (2021)
Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. In: AAAI Conference on Artificial Intelligence (2018)
Zhukov, D., Alayrac, J.B., Cinbis, R.G., Fouhey, D., Laptev, I., Sivic, J.: Cross-task weakly supervised learning from instructional videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Acknowledgements
We thank Ran Zhang for the help with flow graph creation and processing.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dvornik, N. et al. (2022). Flow Graph to Video Grounding for Weakly-Supervised Multi-step Localization. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13695. Springer, Cham. https://doi.org/10.1007/978-3-031-19833-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-19833-5_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19832-8
Online ISBN: 978-3-031-19833-5
eBook Packages: Computer ScienceComputer Science (R0)