Skip to main content
SpringerLink
Log in

AdaFocusV3: On Unified Spatial-Temporal Dynamic Video 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

Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e.g., allocating the majority of computation to a task-relevant subset of frames or the most valuable image regions of each frame. However, in most existing works, either type of redundancy is typically modeled with another absent. This paper explores the unified formulation of spatial-temporal dynamic computation on top of the recently proposed AdaFocusV2 algorithm, contributing to an improved AdaFocusV3 framework. Our method reduces the computational cost by activating the expensive high-capacity network only on some small but informative 3D video cubes. These cubes are cropped from the space formed by frame height, width, and video duration, while their locations are adaptively determined with a light-weighted policy network on a per-sample basis. At test time, the number of the cubes corresponding to each video is dynamically configured, i.e., video cubes are processed sequentially until a sufficiently reliable prediction is produced. Notably, AdaFocusV3 can be effectively trained by approximating the non-differentiable cropping operation with the interpolation of deep features. Extensive empirical results on six benchmark datasets (i.e., ActivityNet, FCVID, Mini-Kinetics, Something-Something V1 &V2 and Diving48) demonstrate that our model is considerably more efficient than competitive baselines.

Y. Wang and Y. Yue—Equal contributions.

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. Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lučić, M., Schmid, C.: ViViT: a video vision transformer. arXiv preprint arXiv:2103.15691 (2021)

  2. Bengio, Y., Mesnil, G., Dauphin, Y., Rifai, S.: Better mixing via deep representations. In: ICML, pp. 552–560. PMLR (2013)

    Google Scholar 

  3. Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR, pp. 961–970 (2015)

    Google Scholar 

  4. Carreira, J., Zisserman, A.: Quo Vadis, action recognition? a new model and the kinetics dataset. In: CVPR, pp. 6299–6308 (2017)

    Google Scholar 

  5. Chen, J., Li, K., Deng, Q., Li, K., Philip, S.Y.: Distributed deep learning model for intelligent video surveillance systems with edge computing. IEEE Trans. Ind. Inform. (2019)

    Google Scholar 

  6. Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP, pp. 1724–1734. Association for Computational Linguistics, Doha, October 2014. https://doi.org/10.3115/v1/D14-1179, www.aclweb.org/anthology/D14-1179

  7. Collins, R.T., et al.: A system for video surveillance and monitoring. VSAM Final Rep. 2000(1–68), 1 (2000)

    Google Scholar 

  8. Davidson, J., et al.: The Youtube video recommendation system. In: Proceedings of the Fourth ACM Conference on Recommender Systems, pp. 293–296 (2010)

    Google Scholar 

  9. Deldjoo, Y., Elahi, M., Cremonesi, P., Garzotto, F., Piazzolla, P., Quadrana, M.: Content-based video recommendation system based on stylistic visual features. J. Data Semant. 5(2), 99–113 (2016)

    Article  Google Scholar 

  10. Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR, pp. 2625–2634 (2015)

    Google Scholar 

  11. Fan, L., et al.: RubiksNet: learnable 3D-shift for efficient video action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 505–521. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58529-7_30

    Chapter  Google Scholar 

  12. Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: CVPR, pp. 203–213 (2020)

    Google Scholar 

  13. Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV, pp. 6202–6211 (2019)

    Google Scholar 

  14. Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4768–4777 (2017)

    Google Scholar 

  15. Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR, pp. 1933–1941 (2016)

    Google Scholar 

  16. Figurnov, M., et al.: Spatially adaptive computation time for residual networks. In: CVPR, pp. 1039–1048 (2017)

    Google Scholar 

  17. Gao, J., Zhang, T., Xu, C.: A unified personalized video recommendation via dynamic recurrent neural networks. In: ACM MM, pp. 127–135 (2017)

    Google Scholar 

  18. Gao, R., Oh, T.H., Grauman, K., Torresani, L.: Listen to look: action recognition by previewing audio. In: CVPR, pp. 10457–10467 (2020)

    Google Scholar 

  19. Ghodrati, A., Bejnordi, B.E., Habibian, A.: FrameExit: conditional early exiting for efficient video recognition. In: CVPR, pp. 15608–15618 (2021)

    Google Scholar 

  20. Gong, X., Wang, H., Shou, M.Z., Feiszli, M., Wang, Z., Yan, Z.: Searching for two-stream models in multivariate space for video recognition. In: ICCV, pp. 8033–8042 (2021)

    Google Scholar 

  21. Goyal, R., et al.: The “something something” video database for learning and evaluating visual common sense. In: ICCV, pp. 5842–5850 (2017)

    Google Scholar 

  22. Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2021)

    Google Scholar 

  23. Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: CVPR, pp. 6546–6555 (2018)

    Google Scholar 

  24. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)

    Google Scholar 

  25. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  26. Huang, G., Chen, D., Li, T., Wu, F., van der Maaten, L., Weinberger, K.Q.: Multi-scale dense networks for resource efficient image classification. In: ICLR (2018)

    Google Scholar 

  27. Ikizler, N., Forsyth, D.: Searching video for complex activities with finite state models. In: CVPR, pp. 1–8. IEEE (2007)

    Google Scholar 

  28. Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: STM: spatiotemporal and motion encoding for action recognition. In: ICCV, pp. 2000–2009 (2019)

    Google Scholar 

  29. Jiang, Y.G., Wu, Z., Wang, J., Xue, X., Chang, S.F.: Exploiting feature and class relationships in video categorization with regularized deep neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 352–364 (2018)

    Article  Google Scholar 

  30. Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)

  31. Kim, H., Jain, M., Lee, J.T., Yun, S., Porikli, F.: Efficient action recognition via dynamic knowledge propagation. In: ICCV, pp. 13719–13728 (2021)

    Google Scholar 

  32. Korbar, B., Tran, D., Torresani, L.: ScSampler: sampling salient clips from video for efficient action recognition. In: ICCV, pp. 6232–6242 (2019)

    Google Scholar 

  33. Li, D., Qiu, Z., Dai, Q., Yao, T., Mei, T.: Recurrent tubelet proposal and recognition networks for action detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 306–322. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_19

    Chapter  Google Scholar 

  34. Li, Y., Li, Y., Vasconcelos, N.: RESOUND: towards action recognition without representation bias. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 520–535. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_32

    Chapter  Google Scholar 

  35. Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: ICCV, pp. 7083–7093 (2019)

    Google Scholar 

  36. Lin, J., Duan, H., Chen, K., Lin, D., Wang, L.: OcSampler: compressing videos to one clip with single-step sampling. In: CVPR (2022)

    Google Scholar 

  37. Liu, Z., et al.: TeiNet: towards an efficient architecture for video recognition. In: AAAI, pp. 11669–11676 (2020)

    Google Scholar 

  38. Liu, Z., Wang, L., Wu, W., Qian, C., Lu, T.: Tam: temporal adaptive module for video recognition. In: ICCV, pp. 13708–13718 (2021)

    Google Scholar 

  39. Luo, C., Yuille, A.L.: Grouped spatial-temporal aggregation for efficient action recognition. In: ICCV, pp. 5512–5521 (2019)

    Google Scholar 

  40. Materzynska, J., Berger, G., Bax, I., Memisevic, R.: The jester dataset: a large-scale video dataset of human gestures. In: ICCVW (2019)

    Google Scholar 

  41. Meng, Y., et al.: AR-Net: adaptive frame resolution for efficient action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 86–104. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58571-6_6

    Chapter  Google Scholar 

  42. Meng, Y., et al.: AdaFuse: adaptive temporal fusion network for efficient action recognition. In: ICLR (2021)

    Google Scholar 

  43. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: CVPR, pp. 4510–4520 (2018)

    Google Scholar 

  44. Sudhakaran, S., Escalera, S., Lanz, O.: Gate-shift networks for video action recognition. In: CVPR, pp. 1102–1111 (2020)

    Google Scholar 

  45. Sun, X., Panda, R., Chen, C.F.R., Oliva, A., Feris, R., Saenko, K.: Dynamic network quantization for efficient video inference. In: ICCV, pp. 7375–7385 (2021)

    Google Scholar 

  46. Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp. 4489–4497 (2015)

    Google Scholar 

  47. Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: ICCV, pp. 5552–5561 (2019)

    Google Scholar 

  48. Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR, pp. 6450–6459 (2018)

    Google Scholar 

  49. Upchurch, P., et al.: Deep feature interpolation for image content changes. In: CVPR, pp. 7064–7073 (2017)

    Google Scholar 

  50. Verelst, T., Tuytelaars, T.: Dynamic convolutions: exploiting spatial sparsity for faster inference. In: CVPR, pp. 2320–2329 (2020)

    Google Scholar 

  51. 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 

  52. Wang, Y., Chen, Z., Jiang, H., Song, S., Han, Y., Huang, G.: Adaptive focus for efficient video recognition. In: ICCV, October 2021

    Google Scholar 

  53. Wang, Y., Huang, R., Song, S., Huang, Z., Huang, G.: Not all images are worth 16x16 words: dynamic transformers for efficient image recognition. In: NeurIPS (2021)

    Google Scholar 

  54. Wang, Y., Lv, K., Huang, R., Song, S., Yang, L., Huang, G.: Glance and focus: a dynamic approach to reducing spatial redundancy in image classification. In: NeurIPS (2020)

    Google Scholar 

  55. Wang, Y., Pan, X., Song, S., Zhang, H., Huang, G., Wu, C.: Implicit semantic data augmentation for deep networks. In: NeurIPS, vol. 32 (2019)

    Google Scholar 

  56. Wang, Y., et al.: AdaFocus v2: end-to-end training of spatial dynamic networks for video recognition. In: CVPR (2022)

    Google Scholar 

  57. Wu, W., He, D., Tan, X., Chen, S., Wen, S.: Multi-agent reinforcement learning based frame sampling for effective untrimmed video recognition. In: ICCV, pp. 6222–6231 (2019a)

    Google Scholar 

  58. Wu, Z., Li, H., Xiong, C., Jiang, Y.G., Davis, L.S.: A dynamic frame selection framework for fast video recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2020b)

    Google Scholar 

  59. Wu, Z., Xiong, C., Jiang, Y.G., Davis, L.S.: LiteEval: acoarse-to-fine framework for resource efficient video recognition. In: NeurIPS (2019b)

    Google Scholar 

  60. Xie, Z., Zhang, Z., Zhu, X., Huang, G., Lin, S.: Spatially adaptive inference with stochastic feature sampling and interpolation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 531–548. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_31

    Chapter  Google Scholar 

  61. Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.: End-to-end learning of action detection from frame glimpses in videos. In: CVPR, pp. 2678–2687 (2016)

    Google Scholar 

  62. Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: CVPR, pp. 4694–4702 (2015)

    Google Scholar 

  63. 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 

  64. Zolfaghari, M., Singh, K., Brox, T.: ECO: efficient convolutional network for online video understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 695–712. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_43

    Chapter  Google Scholar 

Download references

Acknowledgements

This work is supported in part by National Key R &D Program of China(2020AAA0105200), the National Natural Science Foundation of China under Grants 62022048, Guoqiang Institute of Tsinghua University and Beijing Academy of Artificial Intelligence. We also appreciate the generous donation of computing resources by High-Flyer AI.

Author information

Authors and Affiliations

  1. Department of Automation, BNRist, Tsinghua University, Beijing, China

    Yulin Wang, Yang Yue, Xinhong Xu, Shiji Song & Gao Huang

  2. University of Oregon, Eugene, USA

    Ali Hassani & Humphrey Shi

  3. Picsart AI Research (PAIR), Miami, USA

    Victor Kulikov, Nikita Orlov & Humphrey Shi

  4. Beijing Academy of Artificial Intelligence (BAAI), Beijing, China

    Gao Huang

Authors
  1. Yulin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yang Yue
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xinhong Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ali Hassani
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Victor Kulikov
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Nikita Orlov
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Shiji Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Humphrey Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Gao Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Humphrey Shi or Gao 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 313 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

Wang, Y. et al. (2022). AdaFocusV3: On Unified Spatial-Temporal Dynamic Video 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_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19772-7_14

  • 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