Skip to main content

2014 | OriginalPaper | Buchkapitel

4. Social Role Recognition for Human Event Understanding

verfasst von : Vignesh Ramanathan, Bangpeng Yao, Li Fei-Fei

Erschienen in: Human-Centered Social Media Analytics

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

We deal with the problem of recognizing social roles played by people in an event. Social roles are governed by human interactions, and form a fundamental component of human event description. We focus on a weakly supervised setting, where we are provided with different videos belonging to an event class, without training role labels. Since social roles are described by the interaction between people in an event, we propose a Conditional Random Field to model the inter-role interactions, along with person-specific social descriptors. We develop tractable variational inference to simultaneously infer model weights, as well as role assignment to all people in the videos. We also present a novel YouTube social roles dataset with ground truth role annotations, and introduce annotations on a subset of videos from the TRECVID-MED11 event kits for evaluation purposes. The performance of the model is compared against different baseline methods on these datasets.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
2.
Zurück zum Zitat Biddle, B.J.: Recent development in role theory. Ann. Rev. Sociol. 12, 67–92 (1986)CrossRef Biddle, B.J.: Recent development in role theory. Ann. Rev. Sociol. 12, 67–92 (1986)CrossRef
3.
Zurück zum Zitat Burgos-Artizzu, X., Dollar, P., Lin, D., Anderson, D., Perona, P.: Social behavior recognition in continuous videos. In: CVPR (2012) Burgos-Artizzu, X., Dollar, P., Lin, D., Anderson, D., Perona, P.: Social behavior recognition in continuous videos. In: CVPR (2012)
4.
Zurück zum Zitat Choi, W., Savarese, S.: A unified framework for multi-target tracking and collective activity recognition. In: ECCV (2012) Choi, W., Savarese, S.: A unified framework for multi-target tracking and collective activity recognition. In: ECCV (2012)
5.
Zurück zum Zitat Cristani, M., Paggetti, G., Fossati, A., Bazzani, L., Tosato, D., Bue, A.D., Menegaz, G., Murino, V.: Social interaction discovery by statistical analysis of f-formations. In: BMVC (2011) Cristani, M., Paggetti, G., Fossati, A., Bazzani, L., Tosato, D., Bue, A.D., Menegaz, G., Murino, V.: Social interaction discovery by statistical analysis of f-formations. In: BMVC (2011)
6.
Zurück zum Zitat Ding, L., Yilmaz, A.: Learning relations among movie characters: a social network perspective. In: ECCV (2010) Ding, L., Yilmaz, A.: Learning relations among movie characters: a social network perspective. In: ECCV (2010)
7.
Zurück zum Zitat Ding, L., Yilmaz, A.: Inferring social relations from visual concepts. In: ICCV (2011) Ding, L., Yilmaz, A.: Inferring social relations from visual concepts. In: ICCV (2011)
8.
Zurück zum Zitat Direkolu, C., OConnor, N.: Team activity recognition in sports. In: ECCV (2012) Direkolu, C., OConnor, N.: Team activity recognition in sports. In: ECCV (2012)
9.
Zurück zum Zitat Fathi, A., Hoggins, J.K., Rehg, J.M.: Social interactions: a first person perspective. In: CVPR (2012) Fathi, A., Hoggins, J.K., Rehg, J.M.: Social interactions: a first person perspective. In: CVPR (2012)
10.
Zurück zum Zitat Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010) Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)
11.
Zurück zum Zitat Fu, Y., Hospedales, T., Xiang, T., Gong, S.: Attribute learning for understanding unstructured social activity, In: ECCV (2012) Fu, Y., Hospedales, T., Xiang, T., Gong, S.: Attribute learning for understanding unstructured social activity, In: ECCV (2012)
12.
Zurück zum Zitat Gallagher, A.C., Chen, T.: Understanding images of groups of people. In: CVPR (2009) Gallagher, A.C., Chen, T.: Understanding images of groups of people. In: CVPR (2009)
13.
Zurück zum Zitat Kläser, A., Marszałek, M., Schmid, C.: A spatio-temporal descriptor based on 3d-gradients. In: BMVC (2008) Kläser, A., Marszałek, M., Schmid, C.: A spatio-temporal descriptor based on 3d-gradients. In: BMVC (2008)
14.
Zurück zum Zitat Klaser, A., Schmid, C., Liu, C.-L.: Action recognition by dense trajectories. In: CVPR (2011) Klaser, A., Schmid, C., Liu, C.-L.: Action recognition by dense trajectories. In: CVPR (2011)
15.
Zurück zum Zitat Lan, T., Sigal, L., Mori, G.: Social roles in hierarchical models for human activity recognition. In: CVPR (2012) Lan, T., Sigal, L., Mori, G.: Social roles in hierarchical models for human activity recognition. In: CVPR (2012)
16.
Zurück zum Zitat Lan, T., Wang, Y., Yang, W., Robinovitch, S., Mori, G.: Discriminative latent models for recognizing contextual group activities. IEEE Trans. Pattern Anal. Mach. Intell. 34(8), 1549–1562 (2012)CrossRef Lan, T., Wang, Y., Yang, W., Robinovitch, S., Mori, G.: Discriminative latent models for recognizing contextual group activities. IEEE Trans. Pattern Anal. Mach. Intell. 34(8), 1549–1562 (2012)CrossRef
17.
Zurück zum Zitat Li, L.-J., Su, H., Xing, E.P., Fei-Fei, L.: Object bank: a high-level image representation for scene classification and semantic feature sparsification. In: NIPS (2010) Li, L.-J., Su, H., Xing, E.P., Fei-Fei, L.: Object bank: a high-level image representation for scene classification and semantic feature sparsification. In: NIPS (2010)
18.
Zurück zum Zitat Li, R., Porfilio, P., Zickler, T.: Finding group interactions in social clutter. In: CVPR (2013) Li, R., Porfilio, P., Zickler, T.: Finding group interactions in social clutter. In: CVPR (2013)
19.
Zurück zum Zitat Liu, D., Dong, C., Nocedal, J.: On the limited memory bfgs method for large scale optimization. Math. Program. 45, 503–528 (1989) Liu, D., Dong, C., Nocedal, J.: On the limited memory bfgs method for large scale optimization. Math. Program. 45, 503–528 (1989)
20.
Zurück zum Zitat Marin-Jimenez, M., Zisserman, A., Ferrari. V.: Heres looking at you, kid-detecting people looking at each other in videos. In: BMVC (2011) Marin-Jimenez, M., Zisserman, A., Ferrari. V.: Heres looking at you, kid-detecting people looking at each other in videos. In: BMVC (2011)
21.
Zurück zum Zitat Perez, A.P., Marszalek, M., Zisserman, A., Reid, I.: High five: recognising human interactions in tv shows. In: BMVC (2010) Perez, A.P., Marszalek, M., Zisserman, A., Reid, I.: High five: recognising human interactions in tv shows. In: BMVC (2010)
22.
Zurück zum Zitat Qin, Z., Shelton, C.R.: Improving multi-target tracking via social grouping. In: CVPR (2012) Qin, Z., Shelton, C.R.: Improving multi-target tracking via social grouping. In: CVPR (2012)
23.
Zurück zum Zitat Ramanathan, V., Yao, B., Fei-Fei, L.: Social role discover in human events. In: CVPR (2013) Ramanathan, V., Yao, B., Fei-Fei, L.: Social role discover in human events. In: CVPR (2013)
24.
Zurück zum Zitat Song, Z., Wang, M., Hua, X., Yan, S.: Predicting occupation via human clothing and contexts. In: ICCV (2011) Song, Z., Wang, M., Hua, X., Yan, S.: Predicting occupation via human clothing and contexts. In: ICCV (2011)
25.
Zurück zum Zitat Stone, Z., Zickler, T., Darrell, T.: Toward large-scale face recognition using social network context. Proc. IEEE 98(8), 1408 (2010) Stone, Z., Zickler, T., Darrell, T.: Toward large-scale face recognition using social network context. Proc. IEEE 98(8), 1408 (2010)
26.
Zurück zum Zitat Vondrick, C., Ramanan, D.: Video annotation and tracking with active learning. In: NIPS (2011) Vondrick, C., Ramanan, D.: Video annotation and tracking with active learning. In: NIPS (2011)
27.
Zurück zum Zitat Wang, G., Gallagher, A., Luo, J., Forsyth, D.: Seeing people in social context: recognizing people and social relationships. In: ECCV (2010) Wang, G., Gallagher, A., Luo, J., Forsyth, D.: Seeing people in social context: recognizing people and social relationships. In: ECCV (2010)
28.
Zurück zum Zitat Weng, C.-Y., Chu, W.-T., Rolenet, J-LWu: Movie analysis from the perspective of social networks. IEEE Trans. Multimedia 2, 256–271 (2009)CrossRef Weng, C.-Y., Chu, W.-T., Rolenet, J-LWu: Movie analysis from the perspective of social networks. IEEE Trans. Multimedia 2, 256–271 (2009)CrossRef
29.
Zurück zum Zitat Yang, Y., Baker, S., Kannan, A., Ramanan, D.: Recognizing proxemics in personal photos. In: CVPR (2012) Yang, Y., Baker, S., Kannan, A., Ramanan, D.: Recognizing proxemics in personal photos. In: CVPR (2012)
30.
Zurück zum Zitat Yu, T., Lim, S.-N., Patwardhan, K., Krahnstoever, N.: Monitoring, recognizing and discovering social networks. In: CVPR (2009) Yu, T., Lim, S.-N., Patwardhan, K., Krahnstoever, N.: Monitoring, recognizing and discovering social networks. In: CVPR (2009)
31.
Zurück zum Zitat Zhu, J., Xing, E.P.: Conditional topic random fields. In: ICML (2010) Zhu, J., Xing, E.P.: Conditional topic random fields. In: ICML (2010)
32.
Zurück zum Zitat Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: CVPR (2012) Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: CVPR (2012)
Metadaten
Titel
Social Role Recognition for Human Event Understanding
verfasst von
Vignesh Ramanathan
Bangpeng Yao
Li Fei-Fei
Copyright-Jahr
2014
DOI
https://doi.org/10.1007/978-3-319-05491-9_4