Latent Dirichlet Allocation with topic-in-set knowledge
SemiSupLearn '09 Proceedings of the NAACL HLT 2009 Workshop on Semi-Supervised Learning for Natural Language Processing
A survey on vision-based human action recognition
Image and Vision Computing
Modeling temporal structure of decomposable motion segments for activity classification
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Human action recognition in video by 'meaningful' poses
Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing
Unsupervised discovery of activity correlations using latent topic models
Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing
Oriented gradients for human action recognition
ICIMCS '10 Proceedings of the Second International Conference on Internet Multimedia Computing and Service
Regularized semi-supervised latent dirichlet allocation for visual concept learning
MMM'11 Proceedings of the 17th international conference on Advances in multimedia modeling - Volume Part I
Generative group activity analysis with quaternion descriptor
MMM'11 Proceedings of the 17th international conference on Advances in multimedia modeling - Volume Part II
Modeling sense disambiguation of human pose: recognizing action at a distance by key poses
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
Adaptive learning codebook for action recognition
Pattern Recognition Letters
Boosted multi-class semi-supervised learning for human action recognition
Pattern Recognition
Integrating local action elements for action analysis
Computer Vision and Image Understanding
Bayesian filter based behavior recognition in workflows allowing for user feedback
Computer Vision and Image Understanding
Survey on classifying human actions through visual sensors
Artificial Intelligence Review
Motion recognition using local auto-correlation of space-time gradients
Pattern Recognition Letters
Discovering activity interactions in a single pass over a video stream
Proceedings of the 27th Annual ACM Symposium on Applied Computing
Video Behaviour Mining Using a Dynamic Topic Model
International Journal of Computer Vision
One-scan rule extraction to explain significant vehicle interactions with guaranteed error value
ACM SIGAPP Applied Computing Review
Trajectory signature for action recognition in video
Proceedings of the 20th ACM international conference on Multimedia
Attribute learning for understanding unstructured social activity
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Collective activity localization with contextual spatial pyramid
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Translating related words to videos and back through latent topics
Proceedings of the sixth ACM international conference on Web search and data mining
Retrieving actions in group contexts
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
Auto learning temporal atomic actions for activity classification
Pattern Recognition
Behavior recognition from video based on human constrained descriptor and adaptable neural networks
Proceedings of the 4th ACM/IEEE international workshop on Analysis and retrieval of tracked events and motion in imagery stream
Activity clustering for anomaly detection
International Journal of Intelligent Information and Database Systems
Knowledge representation, learning, and problem solving for general intelligence
AGI'13 Proceedings of the 6th international conference on Artificial General Intelligence
Dynamic action recognition based on dynemes and Extreme Learning Machine
Pattern Recognition Letters
Kernel analysis on Grassmann manifolds for action recognition
Pattern Recognition Letters
Advanced Engineering Informatics
Continuous human action recognition in real time
Multimedia Tools and Applications
Human action categorization using discriminative local spatio-temporal feature weighting
Intelligent Data Analysis
A top-down event-driven approach for concurrent activity recognition
Multimedia Tools and Applications
A jointly distributed semi-supervised topic model
Neurocomputing
Hi-index | 0.14 |
We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel “bag-of-words” representation, where each frame corresponds to a “word.” Our models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in our models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in our case. Our models have several advantages over other latent topic models used in visual recognition. First of all, the training is much easier due to the decoupling of the model parameters. Second, it alleviates the issue of how to choose the appropriate number of latent topics. Third, it achieves much better performance by utilizing the information provided by the class labels in the training set. We present action classification results on five different data sets. Our results are either comparable to, or significantly better than previously published results on these data sets.