Trajectory clustering with mixtures of regression models
KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Multiple view geometry in computer vision
Multiple view geometry in computer vision
Convex Optimization
Smooth minimization of non-smooth functions
Mathematical Programming: Series A and B
Generalized Principal Component Analysis (GPCA)
IEEE Transactions on Pattern Analysis and Machine Intelligence
Graph Embedding and Extensions: A General Framework for Dimensionality Reduction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient projections onto the l1-ball for learning in high dimensions
Proceedings of the 25th international conference on Machine learning
Robust Face Recognition via Sparse Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
NUS-WIDE: a real-world web image database from National University of Singapore
Proceedings of the ACM International Conference on Image and Video Retrieval
Unified tag analysis with multi-edge graph
Proceedings of the international conference on Multimedia
Improving the fisher kernel for large-scale image classification
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Efficient highly over-complete sparse coding using a mixture model
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Multi-label visual classification with label exclusive context
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
| Hi-index | 0.00 |
In this work, we investigate how to automatically uncover the underlying group structure of a feature vector such that each group characterizes certain object-specific patterns, e.g., visual pattern or motion trajectories from one object. By mining the group structure, we can effectively alleviate the mutual inference of multiple objects and improve the performance in various visual analysis tasks. To this end, we propose a novel auto-grouped sparse representation (ASR) method. ASR groups semantically correlated feature elements together through optimally fusing their multiple sparse representations. Due to the intractability of primal objective function, we also propose well-behaved convex relaxation and smooth approximation to guarantee obtaining a global optimal solution effectively. Finally, we apply ASR in two important visual analysis tasks: multi-label image classification and motion segmentation. Comprehensive experimental evaluations show that ASR is able to achieve superior performance compared with the state-of-the-arts on these two tasks.