Advertisement

Hierarchical Visual-Textual Graph for Temporal Activity Localization via Language

Conference paper
  • 554 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12365)

Abstract

Temporal Activity Localization via Language (TALL) in video is a recently proposed challenging vision task, and tackling it requires fine-grained understanding of the video content, however, this is overlooked by most of the existing works. In this paper, we propose a novel TALL method which builds a Hierarchical Visual-Textual Graph to model interactions between the objects and words as well as among the objects to jointly understand the video contents and the language. We also design a convolutional network with cross-channel communication mechanism to further encourage the information passing between the visual and textual modalities. Finally, we propose a loss function that enforces alignment of the visual representation of the localized activity and the sentence representation, so that the model can predict more accurate temporal boundaries. We evaluated our proposed method on two popular benchmark datasets: Charades-STA and ActivityNet Captions, and achieved state-of-the-art performances on both datasets. Code is available at https://github.com/forwchen/HVTG.

Keywords

Temporal Activity Localization via Language Hierarchical Visual-Textual Graph Visual-textual alignment 

Supplementary material

504476_1_En_36_MOESM1_ESM.pdf (119 kb)
Supplementary material 1 (pdf 119 KB)

References

  1. 1.
    Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR (2018)Google Scholar
  2. 2.
    Ba, L.J., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
  3. 3.
    Buch, S., Escorcia, V., Ghanem, B., Fei-Fei, L., Niebles, J.C.: End-to-end, single-stream temporal action detection in untrimmed videos. In: BMVC (2017)Google Scholar
  4. 4.
    Buch, S., Escorcia, V., Shen, C., Ghanem, B., Niebles, J.C.: SST: single-stream temporal action proposals. In: CVPR (2017)Google Scholar
  5. 5.
    Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)Google Scholar
  6. 6.
    Chen, J., Chen, X., Ma, L., Jie, Z., Chua, T.: Temporally grounding natural sentence in video. In: EMNLP (2018)Google Scholar
  7. 7.
    Chen, S., Jiang, Y.: Semantic proposal for activity localization in videos via sentence query. In: AAAI (2019)Google Scholar
  8. 8.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: NIPS Workshop on Deep Learning (2014)Google Scholar
  9. 9.
    Dai, X., Singh, B., Zhang, G., Davis, L.S., Chen, Y.Q.: Temporal context network for activity localization in videos. In: ICCV (2017)Google Scholar
  10. 10.
    Escorcia, V., Caba Heilbron, F., Niebles, J.C., Ghanem, B.: DAPs: deep action proposals for action understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 768–784. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46487-9_47CrossRefGoogle Scholar
  11. 11.
    Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: BMVC (2018)Google Scholar
  12. 12.
    Gao, J., Sun, C., Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: ICCV (2017)Google Scholar
  13. 13.
    Ge, R., Gao, J., Chen, K., Nevatia, R.: MAC: mining activity concepts for language-based temporal localization. In: WACV (2019)Google Scholar
  14. 14.
    Hahn, M., Kadav, A., Rehg, J.M., Graf, H.P.: Tripping through time: efficient localization of activities in videos. arXiv preprint arXiv:1904.09936 (2019)
  15. 15.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.B.: Mask R-CNN. In: ICCV (2017)Google Scholar
  16. 16.
    Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.C.: Localizing moments in video with natural language. In: ICCV (2017)Google Scholar
  17. 17.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  18. 18.
    Jiang, B., Huang, X., Yang, C., Yuan, J.: Cross-modal video moment retrieval with spatial and language-temporal attention. In: ICMR (2019)Google Scholar
  19. 19.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)Google Scholar
  20. 20.
    Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: ICCV (2017)Google Scholar
  21. 21.
    Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32–73 (2017).  https://doi.org/10.1007/s11263-016-0981-7MathSciNetCrossRefGoogle Scholar
  22. 22.
    Lin, D., Fidler, S., Kong, C., Urtasun, R.: Visual semantic search: retrieving videos via complex textual queries. In: CVPR (2014)Google Scholar
  23. 23.
    Lin, T., Zhao, X., Shou, Z.: Single shot temporal action detection. In: ACM MM (2017)Google Scholar
  24. 24.
    Liu, M., Wang, X., Nie, L., He, X., Chen, B., Chua, T.: Attentive moment retrieval in videos. In: ACM SIGIR (2018)Google Scholar
  25. 25.
    Liu, M., Wang, X., Nie, L., Tian, Q., Chen, B., Chua, T.: Cross-modal moment localization in videos. In: ACM MM (2018)Google Scholar
  26. 26.
    Lu, C., Chen, L., Tan, C., Li, X., Xiao, J.: DEBUG: a dense bottom-up grounding approach for natural language video localization. In: EMNLP-IJCNLP (2019)Google Scholar
  27. 27.
    Mettes, P., van Gemert, J.C., Cappallo, S., Mensink, T., Snoek, C.G.M.: Bag-of-fragments: selecting and encoding video fragments for event detection and recounting. In: ICMR (2015)Google Scholar
  28. 28.
    Miech, A., Laptev, I., Sivic, J.: Learning a text-video embedding from incomplete and heterogeneous data. arXiv preprint arXiv:1804.02516 (2018)
  29. 29.
    Mithun, N.C., Li, J., Metze, F., Roy-Chowdhury, A.K.: Learning joint embedding with multimodal cues for cross-modal video-text retrieval. In: ICMR (2018)Google Scholar
  30. 30.
    Otani, M., Nakashima, Y., Rahtu, E., Heikkilä, J., Yokoya, N.: Learning joint representations of videos and sentences with web image search. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9913, pp. 651–667. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46604-0_46CrossRefGoogle Scholar
  31. 31.
    Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP (2014)Google Scholar
  32. 32.
    Pont-Tuset, J., Arbelaez, P., Barron, J.T., Marqués, F., Malik, J.: Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE TPAMI 39(1), 128–140 (2017)CrossRefGoogle Scholar
  33. 33.
    Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)Google Scholar
  34. 34.
    Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: CVPR (2017)Google Scholar
  35. 35.
    Shou, Z., Wang, D., Chang, S.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: CVPR (2016)Google Scholar
  36. 36.
    Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510–526. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_31CrossRefGoogle Scholar
  37. 37.
    Song, X., Han, Y.: VAL: visual-attention action localizer. In: PCM (2018)Google Scholar
  38. 38.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: AAAI (2017)Google Scholar
  39. 39.
    Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)Google Scholar
  40. 40.
    Ulyanov, D., Vedaldi, A., Lempitsky, V.S.: Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)
  41. 41.
    Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)Google Scholar
  42. 42.
    Wang, J., Ma, L., Jiang, W.: Temporally grounding language queries in videos by contextual boundary-aware prediction. In: AAAI (2020)Google Scholar
  43. 43.
    Wang, W., Huang, Y., Wang, L.: Language-driven temporal activity localization: a semantic matching reinforcement learning model. In: CVPR (2019)Google Scholar
  44. 44.
    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, Cham (2018).  https://doi.org/10.1007/978-3-030-01228-1_25CrossRefGoogle Scholar
  45. 45.
    Wray, M., Larlus, D., Csurka, G., Damen, D.: Fine-grained action retrieval through multiple parts-of-speech embeddings. arXiv preprint arXiv:1908.03477 (2019)
  46. 46.
    Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)
  47. 47.
    Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3D network for temporal activity detection. In: ICCV (2017)Google Scholar
  48. 48.
    Xu, H., He, K., Plummer, B.A., Sigal, L., Sclaroff, S., Saenko, K.: Multilevel language and vision integration for text-to-clip retrieval. In: AAAI (2019)Google Scholar
  49. 49.
    Xu, H., He, K., Sigal, L., Sclaroff, S., Saenko, K.: Text-to-clip video retrieval with early fusion and re-captioning. arXiv preprint arXiv:1804.05113 (2018)
  50. 50.
    Xu, R., Xiong, C., Chen, W., Corso, J.J.: Jointly modeling deep video and compositional text to bridge vision and language in a unified framework. In: AAAI (2015)Google Scholar
  51. 51.
    Yang, J., Ren, Z., Gan, C., Zhu, H., Parikh, D.: Cross-channel communication networks. In: NeurIPS (2019)Google Scholar
  52. 52.
    Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 487–503. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01234-2_29CrossRefGoogle Scholar
  53. 53.
    Yuan, Y., Mei, T., Zhu, W.: To find where you talk: temporal sentence localization in video with attention based location regression. In: AAAI (2019)Google Scholar
  54. 54.
    Zhang, B., Hu, H., Sha, F.: Cross-modal and hierarchical modeling of video and text. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 385–401. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01261-8_23CrossRefGoogle Scholar
  55. 55.
    Zhang, D., Dai, X., Wang, X., Wang, Y.: S3D: single shot multi-span detector via fully 3D convolutional networks. In: BMVC (2018)Google Scholar
  56. 56.
    Zhang, D., Dai, X., Wang, X., Wang, Y., Davis, L.S.: MAN: moment alignment network for natural language moment retrieval via iterative graph adjustment. In: CVPR (2019)Google Scholar
  57. 57.
    Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: ICCV (2017)Google Scholar
  58. 58.
    Zheng, Y., Pal, D.K., Savvides, M.: Ring loss: convex feature normalization for face recognition. In: CVPR (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan UniversityShanghaiChina

Personalised recommendations