Abstract
Any kind of action is done by an agent which can be a human, animal, object, etc. So far most of the exploration done in the field of action recognition targets the actions performed by the agents and not the agents themselves. But, one agent cannot perform an action in the same way as another. In this paper, we addressed this action recognition problem between multiple agents using the Actor-Action Dataset. This study focuses on two scenarios: individual-class mapping and grouped-class mapping. We applied two strategies to model these cases: non-transfer approach and transfer-learning approach. It is observed that transfer learning techniques along with image augmentation outperforms the models without transfer learning. The results show that our approaches provide an average accuracy of 92% on individual-class mapping, 87% on grouped-class mapping.
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
References
D'Sa, A.G., et al.: A survey on vision based activity recognition, its applications and challenges. In: Second International Conference on Advanced Computational and Communication Paradigms (ICACCP), pp. 1–8 (2019)
Al-Faris, M., et al.: Appearance and motion information based human activity recognition. In: IET 3rd International Conference on Intelligent Signal Processing (ISP 2017), pp. 1–6 (2017)
Xu, D., et al.: Group activity recognition by using effective multiple modality relation representation with temporal-spatial attention. IEEE Access 8, 65689–65698 (2020)
Li, R., et al.: Discriminative virtual views for cross-view action recognition. In: Computer Vision and Pattern Recognition (IEEE), pp. 2855–2862 (2012)
Kasteren, T., Englebienne, G., Kröse, B.: Hierarchical activity recognition using automatically clustered actions. In: Keyson, D.V., et al. (eds.) AmI 2011. LNCS, vol. 7040, pp. 82–91. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-25167-2_9
Gordon, D., et al.: Group activity recognition using wearable sensing devices. Ambient Intell. 323–335 (2014)
Liu, J., et al.: Cross-view action recognition via view knowledge transfer. In: Computer Vision and Pattern Recognition (IEEE), pp. 3209–3216 (2011)
Wang, H., et al.: Action recognition by dense trajectories. In: Computer Vision and Pattern Recognition (IEEE), pp. 3169–3176 (2011)
Wang, H., Wang, L.: Cross-agent action recognition. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2908–2919 (2018)
Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Computer Vision and Pattern Recognition (IEEE), pp. 2625–2634 (2015)
Jain, M., et al.: Better exploiting motion for better action recognition. In: Computer Vision and Pattern Recognition (IEEE), pp. 2555–2562 (2013)
Peng, X., Changqing Zou, Y., Qiao, Q.: Action recognition with stacked fisher vectors. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 581–595. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_38
Long, M., et al.: Transfer sparse coding for robust image representation. In: Computer Vision and Pattern Recognition (IEEE), pp. 407–414 (2013)
Cao, L., Liu, Z., Huang, T.S.: Cross-dataset action detection. In: Computer Vision and Pattern Recognition, pp. 1998–2005. IEEE (2010)
Fernando, B., et al.: Modeling video evolution for action recognition. In: Computer Vision and Pattern Recognition, pp. 5378–5387. IEEE (2015)
Lan, Z., et al.: Beyond Gaussian pyramid: multi-skip feature stacking for action recognition. In: Computer Vision and Pattern Recognition, pp. 204–212. IEEE (2015)
Ji, S., Wei, X., Yang, M., Kai, Y.: 3d convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221–231 (2013)
Bilen, H., et al.: Dynamic image networks for action recognition. In: Computer Vision and Pattern Recognition, pp. 3034–3042. IEEE (2016)
Karpathy, A., et al.: Large-scale video classification with convolutional neural networks. In: Computer Vision and Pattern Recognition, pp. 1725–1732. IEEE (2014)
Simonyan, K., et al.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568–576 (2014)
Srivastava, N., et al.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning, pp. 843–852. ACM (2015)
Farhadi, A., Tabrizi, M.: Learning to recognize activities from the wrong view point. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 154–166. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88682-2_13
Mokari, M., et al.: Recognizing involuntary actions from 3D skeleton data using body states. In: Scientia Iranica, pp. 1424–1436 (2020)
Viola, P., et al.: Rapid object detection using a boosted cascade of simple features. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. I-I (2001)
Li, Q., et al.: An improved algorithm on Viola-Jones object detector. In: 10th International Workshop on Content-Based Multimedia Indexing (CBMI), pp. 1–6 (2012)
Redmon, J., et al.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788 (2016)
Salas, Y., Bermudez, D., López, A., Peña, D., Gomez, T.: Improving HOG with Image segmentation: application to human detection. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P., Zemčík, P. (eds.) Advanced Concepts for Intelligent Vision Systems: 14th International Conference, ACIVS 2012, Brno, Czech Republic, September 4-7, 2012. Proceedings, pp. 178–189. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33140-4_16
Dalal, N., et al.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), pp. 886–893 (2005)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
He, K., et al.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988 (2017)
Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sarah, J., Danny, A.M., Deen, J.M. (2022). Performance Enhancement of Action Recognition System Using Inception V3 Model. In: Abraham, A., et al. Proceedings of the 13th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2021). SoCPaR 2021. Lecture Notes in Networks and Systems, vol 417. Springer, Cham. https://doi.org/10.1007/978-3-030-96302-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-96302-6_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96301-9
Online ISBN: 978-3-030-96302-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)