Histogram of oriented rectangles: A new pose descriptor for human action recognition
Image and Vision Computing
Human Activity Recognition Using the 4D Spatiotemporal Shape Context Descriptor
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Robust copy detection by mining temporal self-similarities
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
A survey on vision-based human action recognition
Image and Vision Computing
Representing pairwise spatial and temporal relations for action recognition
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
View and style-independent action manifolds for human activity recognition
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Making action recognition robust to occlusions and viewpoint changes
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
A survey of vision-based methods for action representation, segmentation and recognition
Computer Vision and Image Understanding
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part III
On supervised human activity analysis for structured environments
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part III
Toward active sensor placement for activity recognition
NEHIPISIC'11 Proceeding of 10th WSEAS international conference on electronics, hardware, wireless and optical communications, and 10th WSEAS international conference on signal processing, robotics and automation, and 3rd WSEAS international conference on nanotechnology, and 2nd WSEAS international conference on Plasma-fusion-nuclear physics
Probabilistic feature extraction from multivariate time series using spatio-temporal constraints
PAKDD'11 Proceedings of the 15th Pacific-Asia conference on Advances in knowledge discovery and data mining - Volume Part II
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part II
Human action recognition using multiple views: a comparative perspective on recent developments
J-HGBU '11 Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding
Spatial feature interdependence matrix (SFIM): a robust descriptor for face recognition
PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part I
Fast Local Self-Similarity for describing interest regions
Pattern Recognition Letters
Intelligent multi-camera video surveillance: A review
Pattern Recognition Letters
Multi-view action recognition using local similarity random forests and sensor fusion
Pattern Recognition Letters
Trajectory-Based modeling of human actions with motion reference points
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
Cross-View action recognition based on statistical machine translation
CCBR'12 Proceedings of the 7th Chinese conference on Biometric Recognition
Common-sense reasoning for human action recognition
Pattern Recognition Letters
Temporal segmentation and assignment of successive actions in a long-term video
Pattern Recognition Letters
Machine Vision and Applications
Robust human action recognition scheme based on high-level feature fusion
Multimedia Tools and Applications
Hi-index | 0.00 |
This paper concerns recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures across views. Building upon this key observation we develop an action descriptor that captures the structure of temporal similarities and dissimilarities within an action sequence. Despite this descriptor not being strictly view-invariant, we provide intuition and experimental validation demonstrating the high stability of self-similarities under view changes. Self-similarity descriptors are also shown stable under action variations within a class as well as discriminative for action recognition. Interestingly, self-similarities computed from different image features possess similar properties and can be used in a complementary fashion. Our method is simple and requires neither structure recovery nor multi-view correspondence estimation. Instead, it relies on weak geometric properties and combines them with machine learning for efficient cross-view action recognition. The method is validated on three public datasets, it has similar or superior performance compared to related methods and it performs well even in extreme conditions such as when recognizing actions from top views while using side views for training only.