Abstract
We introduce the novel problem of anticipating a time series of future hand masks from egocentric video. A key challenge is to model the stochasticity of future head motions, which globally impact the head-worn camera video analysis. To this end, we propose a novel deep generative model – EgoGAN. Our model first utilizes a 3D Fully Convolutional Network to learn a spatio-temporal video representation for pixel-wise visual anticipation. It then generates future head motion using the Generative Adversarial Network (GAN), and predicts the future hand masks based on both the encoded video representation and the generated future head motion. We evaluate our method on both the EPIC-Kitchens and the EGTEA Gaze+ datasets. We conduct detailed ablation studies to validate the design choices of our approach. Furthermore, we compare our method with previous state-of-the-art methods on future image segmentation and provide extensive analysis to show that our method can more accurately predict future hand masks. Project page: https://vjwq.github.io/EgoGAN/.
W. Jia and M. Liu—Equal contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cai, M., Lu, F., Sato, Y.: Generalizing hand segmentation in egocentric videos with uncertainty-guided model adaptation. In: CVPR (2020)
Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: CVPR (2017)
Chandra, S., Couprie, C., Kokkinos, I.: Deep spatio-temporal random fields for efficient video segmentation. In: CVPR (2018)
Chiu, H.K., Adeli, E., Niebles, J.C.: Segmenting the future. In: ICRA-L (2020)
Damen, D., et al.: Scaling egocentric vision: the dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 753–771. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_44
Dessalene, E., Devaraj, C., Maynord, M., Fermuller, C., Aloimonos, Y.: Forecasting action through contact representations from first person video. TPAMI (2021)
Fathi, A., Hodgins, J.K., Rehg, J.M.: Social interactions: a first-person perspective. In: CVPR (2012)
Fathi, A., Farhadi, A., Rehg, J.M.: Understanding egocentric activities. In: ICCV (2011)
Fathi, A., Li, Y., Rehg, J.M.: Learning to recognize daily actions using gaze. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 314–327. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33718-5_23
Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: ICCV (2015)
Furnari, A., Farinella, G.M.: What would you expect? anticipating egocentric actions with rolling-unrolling lstms and modality attention. In: ICCV (2019)
Gao, J., Yang, Z., Nevatia, R.: Red: reinforced encoder-decoder networks for action anticipation. In: BMVC (2017)
Girdhar, R., Grauman, K.: Anticipative video transformer. In: ICCV (2021)
Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)
Gregor, K., Danihelka, I., Graves, A., Rezende, D., Wierstra, D.: Draw: a recurrent neural network for image generation. In: International Conference on Machine Learning, pp. 1462–1471. PMLR (2015)
Guan, J., Yuan, Y., Kitani, K.M., Rhinehart, N.: Generative hybrid representations for activity forecasting with no-regret learning. In: CVPR (2020)
Gui, L.-Y., Wang, Y.-X., Liang, X., Moura, J.M.F.: Adversarial geometry-aware human motion prediction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 823–842. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_48
Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., Alahi, A.: Social gan: socially acceptable trajectories with generative adversarial networks. In: CVPR (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)
Jin, X., et al.: Predicting scene parsing and motion dynamics in the future. In: NeurIPS (2017)
Kataoka, H., Miyashita, Y., Hayashi, M., Iwata, K., Satoh, Y.: Recognition of transitional action for short-term action prediction using discriminative temporal cnn feature. In: BMVC (2016)
Ke, Q., Fritz, M., Schiele, B.: Time-conditioned action anticipation in one shot. In: CVPR (2019)
Kitani, K.M., Ziebart, B.D., Bagnell, J.A., Hebert, M.: Activity forecasting. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 201–214. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33765-9_15
Li, Y.: Learning embodied models of actions from first person video. Ph.D. thesis, Georgia Institute of Technology (2017)
Li, Y., Fathi, A., Rehg, J.M.: Learning to predict gaze in egocentric video. In: ICCV (2013)
Li, Y., Liu, M., Rehg, J.M.: In the eye of beholder: joint learning of gaze and actions in first person video. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 639–655. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_38
Li, Y., Liu, M., Rehg, J.M.: In the eye of the beholder: gaze and actions in first person video. TPAMI (2021)
Li, Y., Ye, Z., Rehg, J.M.: Delving into egocentric actions. In: CVPR (2015)
Liu, M., et al.: Egocentric activity recognition and localization on a 3D map. arXiv preprint arXiv:2105.09544 (2021)
Liu, M., Tang, S., Li, Y., Rehg, J.M.: Forecasting human-object interaction: joint prediction of motor attention and actions in first person video. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 704–721. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_41
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)
Luc, P., Couprie, C., LeCun, Y., Verbeek, J.: Predicting future instance segmentation by forecasting convolutional features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 593–608. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_36
Luc, P., Neverova, N., Couprie, C., Verbeek, J., LeCun, Y.: Predicting deeper into the future of semantic segmentation. In: ICCV (2017)
Ma, M., Fan, H., Kitani, K.M.: Going deeper into first-person activity recognition. In: CVPR (2016)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
Moltisanti, D., Wray, M., Mayol-Cuevas, W., Damen, D.: Trespassing the boundaries: labeling temporal bounds for object interactions in egocentric video. In: ICCV (2017)
Nilsson, D., Sminchisescu, C.: Semantic video segmentation by gated recurrent flow propagation. In: CVPR (2018)
Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier gans. In: ICML (2017)
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)
Pelz, J., Hayhoe, M., Loeber, R.: The coordination of eye, head, and hand movements in a natural task. Exp. Brain Res. 139(3), 266–277 (2001)
Pérez, J.S., Meinhardt-Llopis, E., Facciolo, G.: TV-L1 optical flow estimation. In: IPOL (2013)
Poleg, Y., Arora, C., Peleg, S.: Temporal segmentation of egocentric videos. In: CVPR (2014)
Poleg, Y., Ephrat, A., Peleg, S., Arora, C.: Compact CNN for indexing egocentric videos. In: WACV (2016)
Rochan, M., et al.: Future semantic segmentation with convolutional lstm. In: BMVC (2018)
Rodriguez, C., Fernando, B., Li, H.: Action anticipation by predicting future dynamic images. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11131, pp. 89–105. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11015-4_10
Shan, D., Geng, J., Shu, M., Fouhey, D.: Understanding human hands in contact at internet scale. In: CVPR (2020)
Shen, Y., Ni, B., Li, Z., Zhuang, N.: Egocentric activity prediction via event modulated attention. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 202–217. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_13
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NeurIPS (2014)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Soo Park, H., Shi, J.: Social saliency prediction. In: CVPR (2015)
Soran, B., Farhadi, A., Shapiro, L.: Generating notifications for missing actions: Don’t forget to turn the lights off! In: ICCV (2015)
Tsai, Y.H., Yang, M.H., Black, M.J.: Video segmentation via object flow. In: CVPR (2016)
Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: Mocogan: decomposing motion and content for video generation. In: CVPR (2018)
Vondrick, C., Pirsiavash, H., Torralba, A.: Anticipating visual representations from unlabeled video. In: CVPR (2016)
Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: NeurIPS (2016)
Walker, J., Doersch, C., Gupta, A., Hebert, M.: An uncertain future: forecasting from static images using variational autoencoders. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 835–851. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_51
Walker, J., Marino, K., Gupta, A., Hebert, M.: The pose knows: video forecasting by generating pose futures. In: ICCV (2017)
Wang, W., Zhou, T., Porikli, F., Crandall, D., Van Gool, L.: A survey on deep learning technique for video segmentation. arXiv preprint arXiv:2107.01153 (2021)
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)
Xu, Y.S., Fu, T.J., Yang, H.K., Lee, C.Y.: Dynamic video segmentation network. In: CVPR (2018)
Yagi, T., Mangalam, K., Yonetani, R., Sato, Y.: Future person localization in first-person videos. In: CVPR (2018)
Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: ICCV (2019)
Yonetani, R., Kitani, K.M., Sato, Y.: Recognizing micro-actions and reactions from paired egocentric videos. In: CVPR (2016)
Zhang, H., et al.: Stackgan: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017)
Zhang, M., Teck Ma, K., Hwee Lim, J., Zhao, Q., Feng, J.: Deep future gaze: gaze anticipation on egocentric videos using adversarial networks. In: CVPR (2017)
Zhang, Y., Black, M.J., Tang, S.: We are more than our joints: predicting how 3D bodies move. In: CVPR (2021)
Zhang, Y., Hassan, M., Neumann, H., Black, M.J., Tang, S.: Generating 3D people in scenes without people. In: CVPR (2020)
Acknowledgments
Portions of this project were supported in part by a gift from Facebook. We thank Fiona Ryan for the valuable feedback.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jia, W., Liu, M., Rehg, J.M. (2022). Generative Adversarial Network for Future Hand Segmentation from Egocentric Video. 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 13673. Springer, Cham. https://doi.org/10.1007/978-3-031-19778-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-19778-9_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19777-2
Online ISBN: 978-3-031-19778-9
eBook Packages: Computer ScienceComputer Science (R0)