Abstract
Holistic methods based on dense trajectories [29, 30] are currently the de facto standard for recognition of human activities in video. Whether holistic representations will sustain or will be superseded by higher level video encoding in terms of body pose and motion is the subject of an ongoing debate [12]. In this paper we aim to clarify the underlying factors responsible for good performance of holistic and pose-based representations. To that end we build on our recent dataset [2] leveraging the existing taxonomy of human activities. This dataset includes \(24,920\) video snippets covering \(410\) human activities in total. Our analysis reveals that holistic and pose-based methods are highly complementary, and their performance varies significantly depending on the activity. We find that holistic methods are mostly affected by the number and speed of trajectories, whereas pose-based methods are mostly influenced by viewpoint of the person. We observe striking performance differences across activities: for certain activities results with pose-based features are more than twice as accurate compared to holistic features, and vice versa. The best performing approach in our comparison is based on the combination of holistic and pose-based approaches, which again underlines their complementarity.
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
Ainsworth, B., Haskell, W., Herrmann, S., Meckes, N., Bassett, D., Tudor-Locke, C., Greer, J., Vezina, J., Whitt-Glover, M., Leon, A.: 2011 compendium of physical activities: a second update of codes and MET values. MSSE 43(8), 1575–1581 (2011)
Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human poseestimation: new benchmark and state of the art analysis. In: CVPR’14
Brendel, W., Todorovic, S.: Learning spatiotemporal graphs of human activities. In: ICCV’11
Cardinaux, F., Bhowmik, D., Abhayaratne, C., Hawley, M.S.: Video based technology for ambient assisted living: a review of the literature. J. Ambient Intell. Smart Environ. 3(3), 253–269 (2011)
Chakraborty, B., Holte, M.B., Moeslund, T.B., Gonzalez, J., Xavier Roca, F.: A selective spatio-temporal interest point detector for human action recognition in complex scenes. In: ICCV’11
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection.In: CVPR’05
Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: ECCV’06
Dantone, M., Gall, J., Leistner, C., Gool., L.V.: Human pose estimation usingbody parts dependent joint regressors. In: CVPR’13
Duchenne, O., Laptev, I., Sivic, J., Bach, F., Ponce, J.: Automatic annotation of human actions in video. In: ICCV’09
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html
Ferrari, V., Marin, M., Zisserman, A.: Progressive search space reduction for human pose estimation. In: CVPR’08
Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: ICCV’13
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: Proceedings of the International Conference on Computer Vision (ICCV) (2011)
Laptev, I.: On space-time interest points. IJCV 64(2/3), 107–123 (2005)
Laptev, I., Marszałek, M., Schmid, C., Rozenfeld, B.: Learning realistichuman actions from movies. In: CVPR’08
Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos in thewild. In: CVPR’09
Marszałek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR’09
Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Poselet conditionedpictorial structures. In: CVPR’13
Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Strong appearance and expressive spatial models for human pose estimation. In: ICCV’13
Rodriguez, M.D., Ahmed, J., Shah, M.: Action mach: a spatio-temporal maximum average correlation height filter for action recognition. In: CVPR’08
Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: CVPR’12
Rohrbach, M., Stark, M., Schiele, B.: Evaluating knowledge transfer andzero-shot learning in a large-scale setting. In: CVPR’11
Sadanand, S., J., C.J.: Action bank: a high-level representation of activity in video. In: ECCV’12
Sapp, B., Taskar, B.: Multimodal decomposable models for human pose estimation. In: CVPR’13
Singh, V.K., Nevatia, R.: Action recognition in cluttered dynamic scenes usingpose-specific part models. In: ICCV’11
Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human action classes from videos in the wild. Technical report CRCV-TR-12-01, UCF (2012)
Vedaldi, A., Zisserman, A.: Efficient additive kernels via explicit feature maps. In: CVPR’10
Vishwakarma, S., Agrawal, A.: A survey on activity recognition and behavior understanding in video surveillance. VC 29(10), 983–1009 (2013)
Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. IJCV 103(1), 60–79 (2013)
Wang, H., Schmid, C.: Action recognition with improved trajectories. In:ICCV’13
Wang, H., Ullah, M.M., Kläser, A., Laptev, I., Schmid, C.: Evaluation oflocal spatio-temporal features for action recognition. In: BMVC’09
Yang, Y., Ramanan, D.: Articulated human detection with flexible mixtures of parts. PAMI 61(1), 55–79 (2013)
Acknowledgements
The authors would like to thank Marcus Rohrbach and Sikandar Amin for helpful discussions. This work has been supported by the Max Planck Center for Visual Computing & Communication.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Pishchulin, L., Andriluka, M., Schiele, B. (2014). Fine-Grained Activity Recognition with Holistic and Pose Based Features. In: Jiang, X., Hornegger, J., Koch, R. (eds) Pattern Recognition. GCPR 2014. Lecture Notes in Computer Science(), vol 8753. Springer, Cham. https://doi.org/10.1007/978-3-319-11752-2_56
Download citation
DOI: https://doi.org/10.1007/978-3-319-11752-2_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11751-5
Online ISBN: 978-3-319-11752-2
eBook Packages: Computer ScienceComputer Science (R0)