ACTIVE: Activity Concept Transitions in Video Event Classification

By Chen Sun, Ramkant Nevatia. 2013

81 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Actions ~ Transformations (2015, background): “Temporal structure of videos have also been shown effective in action recognition [47, 6, 44, 13, 34].”
Structural-RNN: Deep Learning on Spatio-Temporal Graphs (2015, background): “Examples include human activity recognition and segmentation from videos [50, 47, 62, 60, 8, 25, 37, 36], context-rich human-object interactions [39, 33, 29, 20, 30], modeling human motion [14, 57, 56] etc.”
Asynchronous Temporal Fields for Action Recognition (2016, background): “Capturing the whole information of the video in terms of temporal evolution of the video stream has been the focus of some recent approaches [51, 6, 12, 35, 49, 30].”
Semantic Aware Video Transcription Using Random Forest Classifiers (2014, background): “Usual goal is activity or event classification of pre-defined categories [32,27,18].”
What do 15,000 object categories tell us about classifying and localizing actions? (2015, unknown): “Such attributes allow zero shot recognition [26], or modeling semantic relations over time [25, 43].”
A Review of Human Activity Recognition Methods (2015, background): “Sun and Nevatia (2013) treated video sequences as sets of short clips rather than a whole representation of actions.”
Rank Pooling for Action Recognition (2015, methodology): “The proposed use of parameters of functions as a new representation is by no means restricted to action recognition or ranking functions.”
Social Attention: Modeling Attention in Human Crowds (2017, background): “This spatio-temporal formulation finds applications in robotics and computer vision, [5], [9], [26].”
Video Action Detection with Relational Dynamic-Poselets (2014, background): “Several previous works [9,3,19,28,18] have considered the relations among parts for action recognition and detection.”
Going deeper into action recognition: A survey (2016, background): “In Jain et al. (2013); Xing et al. (2015); Kantorov and Laptev (2014); Sun and Nevatia (2013) VLAD descriptors obtained from spatiotemporal features are employed for action recognition.”
Modeling video evolution for action recognition (2015, methodology): “In [32], a representation for events is presented that encodes statistical information of the atomic action transition probabilities using a HMM model.”
DISCOVER: Discovering Important Segments for Classification of Video Events and Recounting (2014, methodology): “ELM uses a compact action transition representation motivated by [20] to impose temporal consistency for adjacent pieces of evidence.”
Leveraging Weak Semantic Relevance for Complex Video Event Classification (2017, methodology): “To alleviate this issue, methods utilizing semantic information have been proposed [1, 30, 10, 25, 12, 13, 32].”