Recognition of Composite Human Activities through Context-Free Grammar Based Representation

By Michael S. Ryoo, Jake K. Aggarwal. Computer Vision and Pattern Recognition, 2006

295 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/a6e1a68340951785c7aa3d3ba7a99d64a997a2ef

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Modeling Complex Temporal Composition of Actionlets for Activity Prediction (2012, background): “Grammar based methods [5, 6] show eﬀectiveness for composite human activity recognition.”
A survey on activity recognition and behavior understanding in video surveillance (2013, methodology): “Police guards may not keep surveillance S. Vishwakarma ( ) · A. Agrawal Indian Institute of Information Technology, Allahabad, India e-mail: rs51@iiita.ac.in A. Agrawal e-mail: anupam@iiita.ac.in Present address: S. Vishwakarma N-297 Third Phase, Shivalik Nagar, BHEL, Haridwar, India e-mail: sarvesh”
Interactive body part contrast mining for human interaction recognition (2014, methodology): “Series of researches proposed efficient methods based on RGB videos[2, 3, 4, 5, 6, 7, 8, 9], but they have limitations of location and separation.”
Hierarchical Recognition of Human Activities Interacting with Objects (2007, methodology): “Ryoo and Aggarwal [8]’s system was general enough to recognize continued human activities with any levels of hierarchy, but did not attempt to recognize human activities with objects.”
Action2Activity: Recognizing Complex Activities from Sensor Data (2015, background): “A set of approaches have been proposed to explore the simple relations among actions [Yang, 2009; Liu et al. , 2016; Ryoo and Aggarwal, 2006].”
Ieee Transactions on Pattern Analysis an Machine Intelligence Structured Learning of Human Interactions in Tv Shows (methodology): “Moving towards more realistic datasets, Ryoo and Aggarwal [15] represented an interaction by modeling relations between pairs of spatio-temporal features using spatial and temporal predicates, such as " before " , " after " , " near " or " far " .”
Prediction of Human Activity by Discovering Temporal Sequence Patterns (2014, background): “In public areas, we want to equip a surveillance system that can raise an alarm in advance of any potential dangerous activity happens.”
Weakly-Supervised Alignment of Video with Text (2015, background): “, in the form of Markov models or action grammars, has been used to constrain action prediction in videos [25, 27, 39].”
Rank Pooling for Action Recognition (2015, background): “Although the aforementioned methods successfully capture the local changes within small time windows, they are not designed to model the higher level motion patterns and video-wide appearance and motion evolution associated with certain actions.”
ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification (2017, background): “Modelling long-term temporal structure: Some methods explicitly model the temporal structure of the video using, for example, grammars [36, 40] but are often limited to constrained set-ups such as sports [21], cooking [38], or surveillance [5].”
High-level event recognition in unconstrained videos (2012, background): “Most of them focused on human action/activity analysis, e.g., [1] by Aggarwal and Ryoo, [111] Poppe and [139] Turaga et al., where low-level features, representations, classification models, and datasets were comprehensively surveyed.”
Human Action Recognition and Prediction: A Survey (2018, methodology): “To robustly find body parts, Ryoo and Aggarwal [133] utilized body part tracker to extract each individual in videos and then applied contextfree grammar to model spatial and temporal relationships between people.”
Weakly Supervised Action Labeling in Videos under Ordering Constraints (2014, unknown): “in the form of Markov models or action grammars, have been used to constrain action prediction in videos [13,15,21,23,29,34].”
Towards coherent natural language description of video streams (2011, background): “Ryoo and Aggarwal [20] presented an approach for automatic composite actions recognition based on context free grammar.”
Machine Recognition of Human Activities: A Survey (2008, methodology): “Modeling two-person interactions such as pointing, punching, pushing, hugging, etc., was proposed by Park and Aggarwal [95] in a two-stage process.”
Joint Video and Text Parsing for Understanding Events and Answering Queries (2013, background): “…structures of objects and scenes [21], [6], [22], [23], [24], [25], [7], [8]; temporal parsing recognizes the temporal compositional structures of events [26], [27], [28], [29], [30], [31], [9], [32]; and causal parsing detects the causal relations between events and ﬂuent changes [33], [34], [10].”
Understanding Video Events: A Survey of Methods for Automatic Interpretation of Semantic Occurrences in Video (2009, background): “several event domains including object manipulations [109] and two-person interactions [110].”