CoTeRe-Net: Discovering Collaborative Ternary Relations in Videos

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12351)


Modeling relations is crucial to understand videos for action and behavior recognition. Current relation models mainly reason about relations of invisibly implicit cues, while important relations of visually explicit cues are rarely considered, and the collaboration between them is usually ignored. In this paper, we propose a novel relation model that discovers relations of both implicit and explicit cues as well as their collaboration in videos. Our model concerns Collaborative Ternary Relations (CoTeRe), where the ternary relation involves channel (C, for implicit), temporal (T, for implicit), and spatial (S, for explicit) relation (R). We devise a flexible and effective CTSR module to collaborate ternary relations for 3D-CNNs, and then construct CoTeRe-Nets for action recognition. Extensive experiments on both ablation study and performance evaluation demonstrate that our CTSR module is significantly effective with approximate \(3\%\) gains and our CoTeRe-Nets outperform state-of-the-art approaches on three popular benchmarks. Boosts analysis and relations visualization also validate that relations of both implicit and explicit cues are discovered with efficacy by our method. Our code is available at


Video understanding Action recognition Relation model 



This work was supported by the National Natural Science Foundation of China under grant numbers 61771440 and 41776113.


  1. 1.
    Battaglia, P., Pascanu, R., Lai, M., Rezende, D.J., et al.: Interaction networks for learning about objects, relations and physics. In: NIPS, pp. 4502–4510 (2016)Google Scholar
  2. 2.
    Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the Kinetics dataset. In: CVPR, pp. 6299–6308 (2017)Google Scholar
  3. 3.
    Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: MARS: motion-augmented RGB stream for action recognition. In: CVPR, pp. 7882–7891 (2019)Google Scholar
  4. 4.
    Diba, A., et al.: Spatio-temporal channel correlation networks for action classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 299–315. Springer, Cham (2018). Scholar
  5. 5.
    Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV, pp. 6202–6211 (2019)Google Scholar
  6. 6.
    Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR, pp. 1933–1941 (2016)Google Scholar
  7. 7.
    Ghadiyaram, D., Tran, D., Mahajan, D.: Large-scale weakly-supervised pre-training for video action recognition. In: CVPR, pp. 12046–12055 (2019)Google Scholar
  8. 8.
    Gkioxari, G., Girshick, R., Dollár, P., He, K.: Detecting and recognizing human-object interactions. In: CVPR, pp. 8359–8367 (2018)Google Scholar
  9. 9.
    Gkioxari, G., Girshick, R., Malik, J.: Actions and attributes from wholes and parts. In: ICCV, pp. 2470–2478 (2015)Google Scholar
  10. 10.
    Goyal, R., et al.: The “something something" video database for learning and evaluating visual common sense. In: ICCV, pp. 5842–5850 (2017)Google Scholar
  11. 11.
    Gupta, A., Kembhavi, A., Davis, L.S.: Observing human-object interactions: using spatial and functional compatibility for recognition. IEEE TPAMI 31(10), 1775–1789 (2009)CrossRefGoogle Scholar
  12. 12.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  13. 13.
    Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: CVPR, pp. 3588–3597 (2018)Google Scholar
  14. 14.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  15. 15.
    Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE TPAMI 35(1), 221–231 (2013)CrossRefGoogle Scholar
  16. 16.
    Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: STM: spatiotemporal and motion encoding for action recognition. In: ICCV, pp. 2000–2008 (2019)Google Scholar
  17. 17.
    Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR, pp. 2901–2910 (2017)Google Scholar
  18. 18.
    Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR, pp. 1725–1732 (2014)Google Scholar
  19. 19.
    Kay, W., et al.: The Kinetics human action video dataset. arXiv preprint arXiv:1409.1556 (2017)
  20. 20.
    Kemp, C., Tenenbaum, J.B.: The discovery of structural form. PNAS 105(31), 10687–10692 (2008)CrossRefGoogle Scholar
  21. 21.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)Google Scholar
  22. 22.
    Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: ICCV, pp. 2556–2563 (2011)Google Scholar
  23. 23.
    Kumar, M.P., Koller, D.: Efficiently selecting regions for scene understanding. In: CVPR, pp. 3217–3224 (2010)Google Scholar
  24. 24.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  25. 25.
    Li, L., Gan, Z., Cheng, Y., Liu, J.: Relation-aware graph attention network for visual question answering. In: ICCV, pp. 10313–10322 (2019)Google Scholar
  26. 26.
    Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: ICCV, pp. 7083–7093 (2019)Google Scholar
  27. 27.
    Liu, X., Lee, J.Y., Jin, H.: Learning video representations from correspondence proposals. In: CVPR, pp. 4273–4281 (2019)Google Scholar
  28. 28.
    Long, X., Gan, C., de Melo, G., Wu, J., Liu, X., Wen, S.: Attention clusters: purely attention based local feature integration for video classification. In: CVPR, pp. 7834–7843 (2018)Google Scholar
  29. 29.
    Luo, C., Yuille, A.L.: Grouped spatial-temporal aggregation for efficient action recognition. In: ICCV, pp. 5512–5521 (2019)Google Scholar
  30. 30.
    Ma, C.Y., Kadav, A., Melvin, I., Kira, Z., AlRegib, G., Graf, H.P.: Attend and interact: Higher-order object interactions for video understanding. In: CVPR, pp. 6790–6800 (2018)Google Scholar
  31. 31.
    Martinez, B., Modolo, D., Xiong, Y., Tighe, J.: Action recognition with spatial-temporal discriminative filter banks. In: ICCV, pp. 5482–5491 (2019)Google Scholar
  32. 32.
    Ni, B., Yang, X., Gao, S.: Progressively parsing interactional objects for fine grained action detection. In: CVPR, pp. 1020–1028 (2016)Google Scholar
  33. 33.
    Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with Pseudo-3D residual networks. In: ICCV, pp. 5533–5541 (2017)Google Scholar
  34. 34.
    Qiu, Z., Yao, T., Ngo, C.W., Tian, X., Mei, T.: Learning spatio-temporal representation with local and global diffusion. In: CVPR, pp. 12056–12065 (2019)Google Scholar
  35. 35.
    Russell, B.C., Freeman, W.T., Efros, A.A., Sivic, J., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR, vol. 2, pp. 1605–1614 (2006)Google Scholar
  36. 36.
    Santoro, A., et al.: A simple neural network module for relational reasoning. In: NIPS, pp. 4967–4976 (2017)Google Scholar
  37. 37.
    Shou, Z., et al.: DMC-Net: generating discriminative motion cues for fast compressed video action recognition. In: CVPR, pp. 1268–1277 (2019)Google Scholar
  38. 38.
    Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568–576 (2014)Google Scholar
  39. 39.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  40. 40.
    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)
  41. 41.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: AAAI, pp. 4278–4284 (2017)Google Scholar
  42. 42.
    Szegedy, C., et al.: Going deeper with convolutions. In: CVPR, pp. 1–9 (2015)Google Scholar
  43. 43.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818–2826 (2016)Google Scholar
  44. 44.
    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
  45. 45.
    Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: ICCV, pp. 5552–5561 (2019)Google Scholar
  46. 46.
    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
  47. 47.
    Wang, F., et al.: Residual attention network for image classification. In: CVPR, pp. 3156–3164 (2017)Google Scholar
  48. 48.
    Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: CVPR, pp. 3169–3676 (2011)Google Scholar
  49. 49.
    Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV, pp. 3551–3558 (2013)Google Scholar
  50. 50.
    Wang, L., Li, W., Li, W., Van Gool, L.: Appearance-and-relation networks for video classification. In: CVPR, pp. 1430–1439 (2018)Google Scholar
  51. 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). Scholar
  52. 52.
    Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR, pp. 7794–7803 (2018)Google Scholar
  53. 53.
    Wang, X., Gupta, A.: Videos as space-time region graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 413–431. Springer, Videos as space-time region graphs (2018). Scholar
  54. 54.
    Watters, N., Zoran, D., Weber, T., Battaglia, P., Pascanu, R., Tacchetti, A.: Visual interaction networks: learning a physics simulator from video. In: NIPS, pp. 4539–4547 (2017)Google Scholar
  55. 55.
    Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). Scholar
  56. 56.
    Xiao, T., Fan, Q., Gutfreund, D., Monfort, M., Oliva, A., Zhou, B.: Reasoning about human-object interactions through dual attention networks. In: ICCV, pp. 3919–3928 (2019)Google Scholar
  57. 57.
    Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 318–335. Springer, Cham (2018). Scholar
  58. 58.
    Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: CVPR, pp. 17–24 (2010)Google Scholar
  59. 59.
    Yao, J., Fidler, S., Urtasun, R.: Describing the scene as a whole: joint object detection. In: CVPR. Citeseer (2012)Google Scholar
  60. 60.
    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
  61. 61.
    Zhao, Y., Xiong, Y., Lin, D.: Recognize actions by disentangling components of dynamics. In: CVPR, pp. 6566–6575 (2018)Google Scholar
  62. 62.
    Zhao, Y., Xiong, Y., Lin, D.: Trajectory convolution for action recognition. In: NeurIPS, pp. 2208–2219 (2018)Google Scholar
  63. 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). Scholar
  64. 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. 713–730. Springer, Cham (2018). Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Underwater Vision LabOcean University of ChinaQingdaoChina
  2. 2.Sanya Oceanographic InstitutionOcean University of ChinaSanyaChina

Personalised recommendations