Skip to main content
SpringerLink
Log in

TallFormer: Temporal Action Localization with a Long-Memory Transformer

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13694))

Included in the following conference series:

Abstract

Most modern approaches in temporal action localization divide this problem into two parts: (i) short-term feature extraction and (ii) long-range temporal boundary localization. Due to the high GPU memory cost caused by processing long untrimmed videos, many methods sacrifice the representational power of the short-term feature extractor by either freezing the backbone or using a small spatial video resolution. This issue becomes even worse with the recent video transformer models, many of which have quadratic memory complexity. To address these issues, we propose TallFormer, a memory-efficient and end-to-end trainable Temporal Action Localization transformer with Long-term memory. Our long-term memory mechanism eliminates the need for processing hundreds of redundant video frames during each training iteration, thus, significantly reducing the GPU memory consumption and training time. These efficiency savings allow us (i) to use a powerful video transformer feature extractor without freezing the backbone or reducing the spatial video resolution, while (ii) also maintaining long-range temporal boundary localization capability. With only RGB frames as input and no external action recognition classifier, TallFormer outperforms previous state-of-the-arts by a large margin, achieving an average mAP of 59.1% on THUMOS14 and 35.6% on ActivityNet-1.3. The code is public available (https://github.com/klauscc/TALLFormer.)

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

Access this chapter

Log in via an institution
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

References

  1. Bagchi, A., Mahmood, J., Fernandes, D., Sarvadevabhatla, R.K.: Hear me out: fusional approaches for audio augmented temporal action localization. arXiv preprint arXiv:2106.14118 (2021)

  2. Bai, Y., Wang, Y., Tong, Y., Yang, Y., Liu, Q., Liu, J.: Boundary content graph neural network for temporal action proposal generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 121–137. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58604-1_8

    Chapter  Google Scholar 

  3. Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding, vol. 2, no. p. 4. arXiv preprint arXiv:2102.05095 (2021)

  4. Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961–970 (2015)

    Google Scholar 

  5. 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)

    Google Scholar 

  6. 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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1130–1139 (2018)

    Google Scholar 

  7. Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. arXiv:1604.06174 (2016)

  8. Cheng, F., et al.: Stochastic backpropagation: a memory efficient strategy for training video models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8301–8310 (2022)

    Google Scholar 

  9. Choromanski, K., et al.: Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020)

  10. Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6824–6835 (2021)

    Google Scholar 

  11. Feichtenhofer, C.: X3d: expanding architectures for efficient video recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 203–213 (2020)

    Google Scholar 

  12. Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6202–6211 (2019)

    Google Scholar 

  13. Gao, J., et al.: Accurate temporal action proposal generation with relation-aware pyramid network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10810–10817 (2020)

    Google Scholar 

  14. Gao, J., Chen, K., Nevatia, R.: Ctap: complementary temporal action proposal generation. In: Proceedings of the European conference on computer vision (ECCV), pp. 68–83 (2018)

    Google Scholar 

  15. Goyal, R., et al.: The “something something" video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5842–5850 (2017)

    Google Scholar 

  16. He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729–9738 (2020)

    Google Scholar 

  17. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  18. Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)

  19. Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646–661. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_39

    Chapter  Google Scholar 

  20. Idrees, H., et al.: The thumos challenge on action recognition for videos “in the wild". Comput. Vision Image Underst. 155, 1–23 (2017)

    Article  Google Scholar 

  21. Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: Stm: spatiotemporal and motion encoding for action recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2000–2009 (2019)

    Google Scholar 

  22. Kwon, H., Kim, M., Kwak, S., Cho, M.: MotionSqueeze: neural motion feature learning for video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 345–362. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_21

    Chapter  Google Scholar 

  23. Lin, C., et al.: Learning salient boundary feature for anchor-free temporal action localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3320–3329 (2021)

    Google Scholar 

  24. Lin, J., Gan, C., Han, S.: Tsm: temporal shift module for efficient video understanding. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7083–7093 (2019)

    Google Scholar 

  25. Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: Bmn: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3889–3898 (2019)

    Google Scholar 

  26. Lin, T., Zhao, X., Shou, Z.: Single shot temporal action detection. In: Proceedings of the 25th ACM international conference on Multimedia, pp. 988–996 (2017)

    Google Scholar 

  27. Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: Bsn: boundary sensitive network for temporal action proposal generation. In: Proceedings of the European Conference on Computer Vision (ECCV ), pp. 3–19 (2018)

    Google Scholar 

  28. Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

    Google Scholar 

  29. Liu, Q., Wang, Z.: Progressive boundary refinement network for temporal action detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11612–11619 (2020)

    Google Scholar 

  30. Liu, Y., Ma, L., Zhang, Y., Liu, W., Chang, S.F.: Multi-granularity generator for temporal action proposal. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3604–3613 (2019)

    Google Scholar 

  31. Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022 (2021)

    Google Scholar 

  32. Liu, Z., et al.: Video swin transformer. arXiv preprint arXiv:2106.13230 (2021)

  33. Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Gaussian temporal awareness networks for action localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 344–353 (2019)

    Google Scholar 

  34. Micikevicius, P., et al.: Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)

  35. Patrick, M., et al.: Keeping your eye on the ball: trajectory attention in video transformers. Adv. Neural Inf. Process. Syst. 34, 12493–12506 (2021)

    Google Scholar 

  36. Qing, Z., et al.: Temporal context aggregation network for temporal action proposal refinement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 485–494 (2021)

    Google Scholar 

  37. Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: proceedings of the IEEE International Conference on Computer Vision, pp. 5533–5541 (2017)

    Google Scholar 

  38. Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.F.: Cdc: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5734–5743 (2017)

    Google Scholar 

  39. Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 27, 1–9 (2014)

    Google Scholar 

  40. Su, H., Gan, W., Wu, W., Qiao, Y., Yan, J.: Bsn++: complementary boundary regressor with scale-balanced relation modeling for temporal action proposal generation. arXiv preprint arXiv:2009.07641 (2020)

  41. Tan, J., Tang, J., Wang, L., Wu, G.: Relaxed transformer decoders for direct action proposal generation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 13526–13535 (2021)

    Google Scholar 

  42. Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489–4497 (2015)

    Google Scholar 

  43. Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450–6459 (2018)

    Google Scholar 

  44. Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 1–11 (2017)

    Google Scholar 

  45. Wang, C., Cai, H., Zou, Y., Xiong, Y.: Rgb stream is enough for temporal action detection. arXiv preprint arXiv:2107.04362 (2021)

  46. Wang, L., Li, W., Li, W., Van Gool, L.: Appearance-and-relation networks for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1430–1439 (2018)

    Google Scholar 

  47. 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 

  48. Wang, L., et al.: Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2740–2755 (2018)

    Article  Google Scholar 

  49. Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)

  50. Wang, X., Gao, C., Zhang, S., Sang, N.: Multi-level temporal pyramid network for action detection. In: Peng, Y., et al. (eds.) PRCV 2020. LNCS, vol. 12306, pp. 41–54. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60639-8_4

    Chapter  Google Scholar 

  51. Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 284–293 (2019)

    Google Scholar 

  52. Xiong, Y., et al.: Cuhk & ethz & siat submission to activitynet challenge 2016. arXiv preprint arXiv:1608.00797 (2016)

  53. Xu, M., Zhao, C., Rojas, D.S., Thabet, A., Ghanem, B.: G-tad: sub-graph localization for temporal action detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10156–10165 (2020)

    Google Scholar 

  54. Xu, M., et al.: Long short-term transformer for online action detection. Adv. Neural Inf. Process. Syst. 34, 1086–1099 (2021)

    Google Scholar 

  55. You, C., Han, L., Feng, A., Zhao, R., Tang, H., Fan, W.: Megan: memory enhanced graph attention network for space-time video super-resolution. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1401–1411 (2022)

    Google Scholar 

  56. You, C., et al.: Class-aware generative adversarial transformers for medical image segmentation. arXiv preprint arXiv:2201.10737 (2022)

  57. Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7094–7103 (2019)

    Google Scholar 

  58. Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4486–4496 (2021)

    Google Scholar 

  59. Zhang, D., Dai, X., Wang, X., Wang, Y.F.: S3d: single shot multi-span detector via fully 3d convolutional networks. arXiv preprint arXiv:1807.08069 (2018)

  60. Zhao, C., Thabet, A.K., Ghanem, B.: Video self-stitching graph network for temporal action localization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 13658–13667 (2021)

    Google Scholar 

  61. Zhao, H., Torralba, A., Torresani, L., Yan, Z.: Hacs: human action clips and segments dataset for recognition and temporal localization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8668–8678 (2019)

    Google Scholar 

  62. Zhao, P., Xie, L., Ju, C., Zhang, Y., Wang, Y., Tian, Q.: Bottom-up temporal action localization with mutual regularization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 539–555. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_32

    Chapter  Google Scholar 

  63. Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2914–2923 (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, USA

    Feng Cheng & Gedas Bertasius

Authors
  1. Feng Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gedas Bertasius
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gedas Bertasius .

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 2953 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

Cheng, F., Bertasius, G. (2022). TallFormer: Temporal Action Localization with a Long-Memory Transformer. 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 13694. Springer, Cham. https://doi.org/10.1007/978-3-031-19830-4_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19830-4_29

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19829-8

  • Online ISBN: 978-3-031-19830-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation