Atomic action features: a new feature for action recognition
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Attribute learning for understanding unstructured social activity
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
A survey of video datasets for human action and activity recognition
Computer Vision and Image Understanding
NuActiv: recognizing unseen new activities using semantic attribute-based learning
Proceeding of the 11th annual international conference on Mobile systems, applications, and services
A comparative study of encoding, pooling and normalization methods for action recognition
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Towards zero-shot learning for human activity recognition using semantic attribute sequence model
Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing
Human action recognition by fast dense trajectories
Proceedings of the 21st ACM international conference on Multimedia
Violent scene detection using mid-level feature
Proceedings of the Fourth Symposium on Information and Communication Technology
Robust action recognition using local motion and group sparsity
Pattern Recognition
Silhouette-based human action recognition using SAX-Shapes
The Visual Computer: International Journal of Computer Graphics
Max-Margin Early Event Detectors
International Journal of Computer Vision
Hi-index | 0.00 |
In this paper we explore the idea of using high-level semantic concepts, also called attributes, to represent human actions from videos and argue that attributes enable the construction of more descriptive models for human action recognition. We propose a unified framework wherein manually specified attributes are: i) selected in a discriminative fashion so as to account for intra-class variability; ii) coherently integrated with data-driven attributes to make the attribute set more descriptive. Data-driven attributes are automatically inferred from the training data using an information theoretic approach. Our framework is built upon a latent SVM formulation where latent variables capture the degree of importance of each attribute for each action class. We also demonstrate that our attribute-based action representation can be effectively used to design a recognition procedure for classifying novel action classes for which no training samples are available. We test our approach on several publicly available datasets and obtain promising results that quantitatively demonstrate our theoretical claims.