Recognition of Visual Activities and Interactions by Stochastic Parsing

By Yuri A. Ivanov, Aaron F. Bobick. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000

769 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/3ff52ba9498b2ac084c9d8bbf637c343679df402

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

In Human-Computer Interaction

Citations in the corpus

Unsupervised learning of event AND-OR grammar and semantics from video (2011, methodology): “Our work is also inspired by recent progress in unsupervised learning and data mining [14, 5] as well as grammatical learning and induction [2, 4, 15] on video data.”
Dynamic texture recognition (2001, methodology): “A common approach consists in extracting low-level features by local spatio-temporal filters and then using hidden markov models to model the seque nce of poses of the feature responses over time (see for instance [19, 26, 2, 6, 33, 34, 18, 30]).”
Human activity prediction: Early recognition of ongoing activities from streaming videos (2011, background): “stochastic context-free grammars [5]) were able to process high-level human activities by recognizing their sub-events.”
The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities (2014, background): “One good measure of the productivity of the field is the sheer number and variety of datasets that have been produced by researchers in the last few years: A recent survey [3] lists no less than twenty- ∗Part of this work was done at the lab for Computer Vision for Human-Computer Interaction at the…”
Semantic event representation and recognition using syntactic attribute graph grammar (2009, background): “In the computer vision literature, there has been a significant amount of event understanding research in various application domains (Buxton and Gong, 1995; Haritaoglu et al., 2000; Medioni et al., 2001; Ivanov and Bobick, 2000; Bobick and Wilson, 1997; Collins et al., 2000; Xu and Chang, 2007).”
Beyond Actions: Discriminative Models for Contextual Group Activities (2010, positive): “Moore and Essa [29] extend the work in [21] for recognizing multitasked activities.”
Trajectory-Based Anomalous Event Detection (2008, methodology): “of known patterns of atomic events, as in the works by Ivanov and Bobick [3], Minnen et al.”
Hierarchical Recognition of Human Activities Interacting with Objects (2007, background): “Previous syntactic approaches [2,5] were able to recognize human activities with objects, but they were limited on recognizing semantically complicated activities with concurrent sub-events.”
Learning activity patterns using fuzzy self-organizing neural network (2004, methodology): “TDNN has been successfully applied to hand gesture recognition [14] and lip-reading [15] 5) Syntactic techniques [16]: The syntactic approach in machine vision has been studied mostly in the context of pattern recognition in static images.”
A survey on activity recognition and behavior understanding in video surveillance (2013, background): “Space-time volume Bobick and Davis [7] focused to recognize activity in real-time by using two components of vector images: MEI and MHI.”
A survey of vision-based methods for action representation, segmentation and recognition (2011, methodology): “Other dynamic models that have been used for action recognition are: auto regressive models [13,98,4], time delayed neural networks [146], context-free grammars [48] and feature-structure grammars [58,124].”
A syntactic approach to robot imitation learning using probabilistic activity grammars (2013, positive): “Similar to Ivanov’s work [22] where they augmented the conventional SCFG ‘‘parser’’ by considering the uncertainty values oftheinputsymbols,weextendtheconventionalSCFG‘‘induction’’ techniquebyconsideringtheuncertaintyvaluesoftheinputsym-bols.”
View-invariant motion trajectory-based activity classification and recognition (2006, background): “[22] address a similar problem using a stochastic context-free grammar parsing mechanism.”
Learning Perceptual Causality from Video (2013, background): “In recent computer vision literature, human actions are organized into hierarchical representations, such as stochastic event grammar [Ivanov and Bobick 2000] or the Temporal And-Or Graph [Pei et al. 2011].”
Free viewpoint action recognition using motion history volumes (2006, neutral): “Popular methods for doing this are hidden markov models and other stochastic grammars, e.g. stochastic parsing as proposed by Ivanov and Bobick [3].”
A Scalable Approach to Activity Recognition based on Object Use (2007, methodology): “Temporal constraints on actions are addressed either through the use of probabilistic models such as HMM’s [4, 16] or SCFG’s [9], or through explicit temporal correlation methods [21, 26].”