Deeply learned attributes for crowded scene understanding
Authors:
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 4657-4666
Abstract
Crowded scene understanding is a fundamental problem in computer vision. In this study, we develop a multi-task deep model to jointly learn and combine appearance and motion features for crowd understanding. We propose crowd motion channels as the input of the deep model and the channel design is inspired by generic properties of crowd systems. To well demonstrate our deep model, we construct a new large-scale WWW Crowd dataset with 10, 000 videos from 8, 257 crowded scenes, and build an attribute set with 94 attributes on WWW. We further measure user study performance on WWW and compare this with the proposed deep models. Extensive experiments show that our deep models display significant performance improvements in cross-scene attribute recognition compared to strong crowd-related feature-based baselines, and the deeply learned features behave a superior performance in multi-task learning.Keywords
This publication has 32 references indexed in Scilit:
- Scene-Independent Group Profiling in Crowd2014
- SUN attribute database: Discovering, annotating, and recognizing scene attributes2012
- Human action recognition by learning bases of action attributes and parts2011
- Data-driven crowd analysis in videos2011
- Action recognition by dense trajectories2011
- Interactively building a discriminative vocabulary of nameable attributes2011
- Locality-constrained Linear Coding for image classification2010
- Abnormal crowd behavior detection using social force model2009
- Unsupervised Activity Perception by Hierarchical Bayesian Models2007
- Matching Local Self-Similarities across Images and Videos2007