Abstract
High level semantic analysis typically involves constructing a Markov network over detections from low level detectors to encode context and model relationships between them. In complex higher order networks (e.g. Markov Logic Networks), each detection can be part of many factors and the network size grows rapidly as a function of the number of detections. Hence to keep the network size small, a threshold is applied on the confidence measures of the detections to discard the less likely detections. A practical challenge is to decide what thresholds to use to discard noisy detections. A high threshold will lead to a high false dismissal rate. A low threshold can result in many detections including mostly noisy ones which leads to a large network size and increased computational requirements. We propose a feedback based incremental technique to keep the network size small. We initialize the network with detections above a high confidence threshold and then based on the high level semantics in the initial network, we incrementally select the relevant detections from the remaining ones that are below the threshold. We show three different ways of selecting detections which are based on three scoring functions that bound the increase in the optimal value of the objective function of network, with varying degrees of accuracy and computational cost. We perform experiments with an event recognition task in one-on-one basketball videos that uses Markov Logic Networks.
Chapter PDF
Similar content being viewed by others
References
Brendel, W., Fern, A., Todorovic, S.: Probabilistic event logic for interval-based event recognition. In: CVPR (2011)
Choi, M., Torralba, A., Willsky, A.: A tree-based context model for object recognition. PAMI 34, 240–252 (2012)
Desai, C., Ramanan, D., Fowlkes, C.: Discriminative models for multi-class object layout. In: ICCV (2009)
Globerson, A., Jaakkola, T.: Fixing max-product: convergent message passing algorithms for MAP LP-relaxations. In: NIPS (2007)
Gurobi-Optimization-Inc.: Gurobi Optimizer Reference Manual (2013). http://www.gurobi.com
Kohli, P., Torr, P.: Measuring uncertainty in graph cut solutions - efficiently computing min-marginal energies using dynamic graph cuts. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 30–43. Springer, Heidelberg (2006)
Kok, S., Sumner, M., Richardson, M., Singla, P.: The Alchemy System for Statistical Relational (2009). http://alchemy.cs.washington.edu/
Kumar, M.P., Koller, D.: Efficiently selecting regions for scene understanding. In: CVPR (2010)
Lin, D., Fidler, S., Urtasun, R.: Holistic scene understanding for 3D object detection with RGBD cameras. In: ICCV (2013)
Morariu, V., Davis, L.: Multi-agent event recognition in structured scenarios. In: CVPR (2011)
Noessner, J., Niepert, M., Stuckenschmidt, H.: RockIt: exploiting parallelism and symmetry for map inference in statistical relational models. In: AAAI (2013)
Richardson, M., Domingos, P.: Markov logic networks. Machine Learning, January 2006
Sontag, D., Meltzer, T., Globerson, A.: Tightening LP relaxations for map using message passing. In: UAI (2008)
Sun, M., Bao, S.Y., Savarese, S.: Object detection using geometrical context feedback. IJCV, August 2012
Tran, S.D., Davis, L.S.: Event modeling and recognition using markov logic networks. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 610–623. Springer, Heidelberg (2008)
Zhu, Y., Nayak, N., Chowdhury, A.R.: Context-aware activity recognition and anomaly detection in video. In: CVPR (2013)
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
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Nagaraja, V.K., Morariu, V.I., Davis, L.S. (2015). Feedback Loop Between High Level Semantics and Low Level Vision. In: Agapito, L., Bronstein, M., Rother, C. (eds) Computer Vision - ECCV 2014 Workshops. ECCV 2014. Lecture Notes in Computer Science(), vol 8926. Springer, Cham. https://doi.org/10.1007/978-3-319-16181-5_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-16181-5_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16180-8
Online ISBN: 978-3-319-16181-5
eBook Packages: Computer ScienceComputer Science (R0)