Beyond Actions: Discriminative Models for Contextual Group Activities

By Tian Lan, Yang Wang, Weilong Yang, Greg Mori. 2010

163 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, background): “Human action recognition [2] has become an active area in computer vision and there are many important research problems, such as event recognition [23], group based activities recognition [27], human object interactions [15] and activities in egocentric videos [29, 11].”
Unstructured human activity detection from RGBD images (2011, methodology): “We have also made the dataset and code available open-source at: http://pr.cs.cornell.edu/humanactivities”
View-Invariant Action Recognition Using Latent Kernelized Structural SVM (2012, background): “object recognition with attributes [17], image annotation and segmentation [18], action recognition from pose estimation [19], and group activity recognition [20].”
Human group activity analysis with fusion of motion and appearance information (2011, background): “Interactions of person-person and person-group are considered in [7], but the complete layered structure is not explicitly defined.”
Discriminative Latent Models for Recognizing Contextual Group Activities (2012, unknown): “Ç”
Social interactions: A first-person perspective (2012, methodology): “[12] use a discriminative latent SVM model to recognize group activities in images based on individual actions and pairwise context.”
Recognizing proxemics in personal photos (2012, background): “Recent work has applied contextual models to the problem of recognizing group activities [2, 15, 11].”
Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes (2016, background): “Researchers have demonstrated that it is indeed possible to model the interaction between humans and their surroundings to improve or solve numerous computer vision tasks: for instance, to make pedestrian tracking more robust and accurate [1,2,3,4,5], to enable the understanding of activities perfor”
Learning spatiotemporal graphs of human activities (2011, background): “These issues have recently been addressed by learning relevant contextual relations between individual actions of people in a group activity [11].”
Joint Prediction of Activity Labels and Starting Times in Untrimmed Videos (2017, unknown): “In [4] and [21], group context was used for collective activity recognition.”
Gesture Modeling by Hanklet-Based Hidden Markov Model (2014, unknown): “HMM have been widely used for action modeling, for example in [20], [30], [31], [11], [32], [33].”
Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition (2015, background): “in the graphical model depicted in Fig.3. This is a typical structure used in group activity recognition, with all people connected to each other and to the scene node corresponding to group activity [28,27]. For a probabilistic graphical model of this type, a standard inference algorithm is belief ”
Multitype Activity Recognition in Robot-Centric Scenarios (2015, background): “Most of the approaches in the literature tackle the problems of third-person activity recognition [9], [10], [11], [12], two persons interactions [2], [13], [14], [15] and group activities [3], [16], [17].”
Action recognition from a distributed representation of pose and appearance (2011, background): “In addition context based on actions of other agents in the scene can provide valuable cues as well [13].”
Integrating multi-stage depth-induced contextual information for human action recognition and localization (2013, unknown): “It is widely recognized that modeling spatial-temporal contextual information is important for recognizing various interactions including human-human, human-object or human-surroundings [9].”
A Unified Framework for Multi-target Tracking and Collective Activity Recognition (2012, methodology): “[11] train their model on three fourths of the dataset, test on the remaining fourth and evaluate per-scene collective activity classification.”
Zero-Shot Learning via Visual Abstraction (2014, background): “Several papers have studied the relations of people in groups using videos [4, 17], such as “queuing in line” or whether people are looking at each other [19].”
Ieee Transactions on Pattern Analysis an Machine Intelligence Structured Learning of Human Interactions in Tv Shows (methodology): “Structured learning has also started to be used for human activity recognition as shown in recent work by Lan et al. [24] and Niebles et al. [25].”