Skip to main content
SpringerLink
Log in

Compound Prototype Matching for Few-Shot Action Recognition

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13664))

Included in the following conference series:

Abstract

Few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. In this work, we propose a novel approach that first summarizes each video into compound prototypes consisting of a group of global prototypes and a group of focused prototypes, and then compares video similarity based on the prototypes. Each global prototype is encouraged to summarize a specific aspect from the entire video, e.g., the start/evolution of the action. Since no clear annotation is provided for the global prototypes, we use a group of focused prototypes to focus on certain timestamps in the video. We compare video similarity by matching the compound prototypes between the support and query videos. The global prototypes are directly matched to compare videos from the same perspective, e.g., to compare whether two actions start similarly. For the focused prototypes, since actions have various temporal variations in the videos, we apply bipartite matching to allow the comparison of actions with different temporal positions and shifts. Experiments demonstrate that our proposed method achieves state-of-the-art results on multiple benchmarks.

Y. Huang and L. Yang—Equal contribution.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: NeurIPS (2016)

    Google Scholar 

  2. Antoniou, A., Edwards, H., Storkey, A.: How to train your MAML. In: ICML (2019)

    Google Scholar 

  3. Bishay, M., Zoumpourlis, G., Patras, I.: TARN: temporal attentive relation network for few-shot and zero-shot action recognition. In: BMVC (2019)

    Google Scholar 

  4. Cao, C., Li, Y., Lv, Q., Wang, P., Zhang, Y.: Few-shot action recognition with implicit temporal alignment and pair similarity optimization. In: CVIU (2021)

    Google Scholar 

  5. Cao, K., Ji, J., Cao, Z., Chang, C.Y., Niebles, J.C.: Few-shot video classification via temporal alignment. In: CVPR (2020)

    Google Scholar 

  6. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13

    Chapter  Google Scholar 

  7. Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)

    Google Scholar 

  8. Chang, C.Y., Huang, D.A., Sui, Y., Fei-Fei, L., Niebles, J.C.: D3TW: discriminative differentiable dynamic time warping for weakly supervised action alignment and segmentation. In: CVPR (2019)

    Google Scholar 

  9. Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. In: CVPR (2018)

    Google Scholar 

  10. Chowdhury, A., Jiang, M., Chaudhuri, S., Jermaine, C.: Few-shot image classification: just use a library of pre-trained feature extractors and a simple classifier. In: ICCV (2021)

    Google Scholar 

  11. Cong, Y., Liao, W., Ackermann, H., Rosenhahn, B., Yang, M.Y.: Spatial-temporal transformer for dynamic scene graph generation. In: ICCV (2021)

    Google Scholar 

  12. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)

    Google Scholar 

  13. Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: TransVG: end-to-end visual grounding with transformers. In: ICCV (2021)

    Google Scholar 

  14. Dhillon, G.S., Chaudhari, P., Ravichandran, A., Soatto, S.: A baseline for few-shot image classification. In: ICLR (2019)

    Google Scholar 

  15. Doersch, C., Gupta, A., Zisserman, A.: CrossTransformers: spatially-aware few-shot transfer. In: NeurIPS (2020)

    Google Scholar 

  16. Fan, Q., Zhuo, W., Tang, C.K., Tai, Y.W.: Few-shot object detection with attention-RPN and multi-relation detector. In: CVPR (2020)

    Google Scholar 

  17. Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning. PMLR (2017)

    Google Scholar 

  18. Fu, Y., Zhang, L., Wang, J., Fu, Y., Jiang, Y.G.: Depth guided adaptive meta-fusion network for few-shot video recognition. In: ACM MM (2020)

    Google Scholar 

  19. Goyal, R., et al.: The “something something” video database for learning and evaluating visual common sense. In: ICCV (2017)

    Google Scholar 

  20. Grauman, K., Westbury, A., Byrne, E., et al.: Ego4D: around the world in 3,000 hours of egocentric video. arXiv preprint arXiv:2110.07058 (2021)

  21. Gui, L.-Y., Wang, Y.-X., Ramanan, D., Moura, J.M.F.: Few-shot human motion prediction via meta-learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 441–459. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_27

    Chapter  Google Scholar 

  22. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)

    Google Scholar 

  23. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)

    Google Scholar 

  24. Hong, J., Fisher, M., Gharbi, M., Fatahalian, K.: Video pose distillation for few-shot, fine-grained sports action recognition. In: ICCV (2021)

    Google Scholar 

  25. Huang, Y., Cai, M., Li, Z., Sato, Y.: Predicting gaze in egocentric video by learning task-dependent attention transition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 789–804. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_46

    Chapter  Google Scholar 

  26. Kang, B., Liu, Z., Wang, X., Yu, F., Feng, J., Darrell, T.: Few-shot object detection via feature reweighting. In: ICCV (2019)

    Google Scholar 

  27. Kang, D., Kwon, H., Min, J., Cho, M.: Relational embedding for few-shot classification. In: ICCV (2021)

    Google Scholar 

  28. Kliper-Gross, O., Hassner, T., Wolf, L.: One shot similarity metric learning for action recognition. In: SIMBAD (2011)

    Google Scholar 

  29. Koch, G., Zemel, R., Salakhutdinov, R., et al.: Siamese neural networks for one-shot image recognition. In: ICML (2015)

    Google Scholar 

  30. Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: ICCV (2011)

    Google Scholar 

  31. Kuhn, H.W.: The Hungarian method for the assignment problem. Nav. Res. Logist. Q. 2, 83–97 (1955)

    Article  MathSciNet  MATH  Google Scholar 

  32. Kumar Dwivedi, S., Gupta, V., Mitra, R., Ahmed, S., Jain, A.: ProtoGAN: towards few shot learning for action recognition. In: CVPRW (2019)

    Google Scholar 

  33. Li, H., Eigen, D., Dodge, S., Zeiler, M., Wang, X.: Finding task-relevant features for few-shot learning by category traversal. In: CVPR (2019)

    Google Scholar 

  34. Li, S., et al.: TA2N: two-stage action alignment network for few-shot action recognition. arXiv preprint arXiv:2107.04782 (2021)

  35. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  36. Liu, W., Zhang, C., Lin, G., Liu, F.: CRNet: cross-reference networks for few-shot segmentation. In: CVPR (2020)

    Google Scholar 

  37. Liu, Y., Zhang, X., Zhang, S., He, X.: Part-aware prototype network for few-shot semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 142–158. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_9

    Chapter  Google Scholar 

  38. Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)

    Google Scholar 

  39. Lu, Z., He, S., Zhu, X., Zhang, L., Song, Y.Z., Xiang, T.: Simpler is better: few-shot semantic segmentation with classifier weight transformer. In: ICCV (2021)

    Google Scholar 

  40. Luo, Z., et al.: Weakly-supervised action localization with expectation-maximization multi-instance learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 729–745. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58526-6_43

    Chapter  Google Scholar 

  41. Ma, J., Gorti, S.K., Volkovs, M., Yu, G.: Weakly supervised action selection learning in video. In: CVPR (2021)

    Google Scholar 

  42. Mishra, A., Verma, V.K., Reddy, M.S.K., Arulkumar, S., Rai, P., Mittal, A.: A generative approach to zero-shot and few-shot action recognition. In: WACV (2018)

    Google Scholar 

  43. Patravali, J., Mittal, G., Yu, Y., Li, F., Chen, M.: Unsupervised few-shot action recognition via action-appearance aligned meta-adaptation. In: ICCV (2021)

    Google Scholar 

  44. Perrett, T., Masullo, A., Burghardt, T., Mirmehdi, M., Damen, D.: Temporal-relational crosstransformers for few-shot action recognition. In: CVPR (2021)

    Google Scholar 

  45. Qiao, S., Liu, C., Shen, W., Yuille, A.L.: Few-shot image recognition by predicting parameters from activations. In: CVPR (2018)

    Google Scholar 

  46. Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2017)

    Google Scholar 

  47. Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NeurIPS (2017)

    Google Scholar 

  48. Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)

  49. Sun, R., Li, Y., Zhang, T., Mao, Z., Wu, F., Zhang, Y.: Lesion-aware transformers for diabetic retinopathy grading. In: CVPR (2021)

    Google Scholar 

  50. Thatipelli, A., Narayan, S., Khan, S., Anwer, R.M., Khan, F.S., Ghanem, B.: Spatio-temporal relation modeling for few-shot action recognition. arXiv preprint arXiv:2112.05132 (2021)

  51. Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)

    Google Scholar 

  52. Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: NeurIPS (2016)

    Google Scholar 

  53. Wang, H., Zhang, X., Hu, Y., Yang, Y., Cao, X., Zhen, X.: Few-shot semantic segmentation with democratic attention networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 730–746. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58601-0_43

    Chapter  Google Scholar 

  54. Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: PANet: few-shot image semantic segmentation with prototype alignment. In: ICCV (2019)

    Google Scholar 

  55. Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20–36. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_2

    Chapter  Google Scholar 

  56. Wang, X., et al.: Semantic-guided relation propagation network for few-shot action recognition. In: ACM MM (2021)

    Google Scholar 

  57. Wang, X., Huang, T.E., Darrell, T., Gonzalez, J.E., Yu, F.: Frustratingly simple few-shot object detection. In: ICML (2020)

    Google Scholar 

  58. Wei, X.S., Wang, P., Liu, L., Shen, C., Wu, J.: Piecewise classifier mappings: learning fine-grained learners for novel categories with few examples. TIP 28, 6116–6125 (2019)

    MathSciNet  MATH  Google Scholar 

  59. Xian, Y., Korbar, B., Douze, M., Schiele, B., Akata, Z., Torresani, L.: Generalized many-way few-shot video classification. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12540, pp. 111–127. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-65414-6_10

    Chapter  Google Scholar 

  60. Xian, Y., Korbar, B., Douze, M., Torresani, L., Schiele, B., Akata, Z.: Generalized few-shot video classification with video retrieval and feature generation. In: TPAMI (2021)

    Google Scholar 

  61. Xu, B., Ye, H., Zheng, Y., Wang, H., Luwang, T., Jiang, Y.G.: Dense dilated network for few shot action recognition. In: ICMR (2018)

    Google Scholar 

  62. Xu, C., et al.: Learning dynamic alignment via meta-filter for few-shot learning. In: CVPR (2021)

    Google Scholar 

  63. Xu, M., Zhao, C., Rojas, D.S., Thabet, A., Ghanem, B.: G-TAD: sub-graph localization for temporal action detection. In: CVPR (2020)

    Google Scholar 

  64. Yang, J., et al.: Focal self-attention for local-global interactions in vision transformers. In: NeurIPS (2021)

    Google Scholar 

  65. Ye, H.J., Hu, H., Zhan, D.C., Sha, F.: Few-shot learning via embedding adaptation with set-to-set functions. In: CVPR, pp. 8808–8817 (2020)

    Google Scholar 

  66. Zeng, R., Huang, W., Tan, M., Rong, Y., Zhao, P., Huang, J., Gan, C.: Graph convolutional networks for temporal action localization. In: ICCV (2019)

    Google Scholar 

  67. Zhang, C., Cai, Y., Lin, G., Shen, C.: DeepEMD: few-shot image classification with differentiable earth mover’s distance and structured classifiers. In: CVPR (2020)

    Google Scholar 

  68. Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: CVPR (2021)

    Google Scholar 

  69. Zhang, H., Zhang, L., Qi, X., Li, H., Torr, P.H.S., Koniusz, P.: Few-shot action recognition with permutation-invariant attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 525–542. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_31

    Chapter  Google Scholar 

  70. Zhang, S., Zhou, J., He, X.: Learning implicit temporal alignment for few-shot video classification. IJCAI (2021)

    Google Scholar 

  71. Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831–846. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_49

    Chapter  Google Scholar 

  72. Zhu, L., Yang, Y.: Compound memory networks for few-shot video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 782–797. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_46

    Chapter  Google Scholar 

  73. Zhu, L., Yang, Y.: Label independent memory for semi-supervised few-shot video classification. TPAMI 44, 273–285 (2020)

    Google Scholar 

  74. Zhu, X., Toisoul, A., Perez-Rua, J.M., Zhang, L., Martinez, B., Xiang, T.: Few-shot action recognition with prototype-centered attentive learning. BMVC (2021)

    Google Scholar 

  75. Zhu, Z., Wang, L., Guo, S., Wu, G.: A closer look at few-shot video classification: a new baseline and benchmark. BMVC (2021)

    Google Scholar 

Download references

Acknowledgement

This work is supported by JSPS KAKENHI Grant Number JP22K17905, JP20H04205 and JST AIP Acceleration Research Grant Number JPMJCR20U1.

Author information

Authors and Affiliations

  1. Institute of Industrial Science, The University of Tokyo, Tokyo, Japan

    Yifei Huang, Lijin Yang & Yoichi Sato

Authors
  1. Yifei Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lijin Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yoichi Sato
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yifei Huang .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1968 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Huang, Y., Yang, L., Sato, Y. (2022). Compound Prototype Matching for Few-Shot Action Recognition. 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 13664. Springer, Cham. https://doi.org/10.1007/978-3-031-19772-7_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19772-7_21

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19771-0

  • Online ISBN: 978-3-031-19772-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation