Parameterized modeling and recognition of activities

By Y. Yacoob, Michael J. Black. 1998

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): “While body part based approaches regard the human skeleton as a connected set of segments, and then focus on individual or connected pairs of body parts [50] and joint angles [33].”
Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (2016, background): “…can be mainly divided into two perspectives, namely (i) generative models that assume the skeleton points are produced by a latent dynamic model [2] corrupted by noise and (ii) discriminative approaches that generate compact representations of sequences on which classifiers are trained [3].”
A Biologically Inspired System for Action Recognition (2007, background): “One class of approaches relies on the tracking of object parts [32, 19, 3].”
Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data (2016, background): “On the other hand, part-based approaches consider human skeleton as a set of connected rigid segments, and represent it with features like joint angles [18, 19, 31], bio-inspired 3D features [6], individual part locations [38], relative 3D geometry between parts [33], etc.”
Human Action Recognition in Videos Using Kinematic Features and Multiple Instance Learning (2010, unknown): “Note that work by [3] and [4] can also be categorized under a volume-based representation.”
Actions as Space-Time Shapes (2007, unknown): “Others, [31], [7] employ feature tracking and face difficulties in cases of self-occlusions, change of appearance, and problems of reinitialization.”
Recent developments in human motion analysis (2003, methodology): “In addition to three approaches described above, the Principle Component Analysis (PCA) method [142,143] and some variants from HMM and NN such as Coupled Hidden Markov Models (CHMM) [139], Variable-Length Markov Model (VLMM) [144] and Time-Delay Neural Network (TDNN) [145], have also appeared in th”
Does Human Action Recognition Benefit from Pose Estimation? (2011, methodology): “The sequences themselves were then classified through exemplar matching [12, 23, 32] or with state-space models such as HMMs [5].”
Chaotic Invariants for Human Action Recognition (2007, background): “Some leading representations are: learned geometrical models of human body parts [19, 20], space-time pattern templates [12, 16]), 3D information ([17]), shape or form features [21, 13]), interest point based representation [23], motion/optical flow patterns [24, 18] and volumetric features [22, 15]”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, background): “Motion, frequency and others [15], [16], [23], [24], [26], [28], [29], [34], [35], [38], [79], [81], [82], [85], [87], [103], [106], [116], [117], [119], [122], [129]–[134]”
Event-based analysis of video (2001, background): “, [24, 2, 9]), it can be refined with the gradual increase in knowledge about the underlying data.”
A Survey of Computer Vision-Based Human Motion Capture (2001, background): “1998 Pinhanez [118] 1998 Silaghi [131] 1998 Sul * [132] 1998 Utsumi [137] * 1998 Wren * [145] 1998 Wren [147] * 1998 Yacoob * * [149] 1998 Yamada [150] 1998 Yamamoto * [151] 1998 Yaniz * [154] 1998 Zheng * [155] 1999 Amat [4] * * 1999 Andersen [5] * 1999 Brand * [16] 1999 Cham [24] * 1999 Cutler [31”
Coupled Action Recognition and Pose Estimation from Multiple Views (2012, methodology): “matching (Gavrila and Davis 1995; Yacoob and Black 1999; Rao et al. 2002) or with state-space models such as HMMs (Campbell and Bobick 1995).”
Discovering Motion Primitives for Unsupervised Grouping and One-Shot Learning of Human Actions, Gestures, and Expressions (2013, unknown): “, HOF), computed from sequences of images depicting the action (as in [49], [13]).”
Max-Margin Early Event Detectors (2012, background): “2011; Reddy and Shah 2012), and activity recognition (e.g., Brand et al. 1997; Yacoob and Black 1999; Chomat and Crowley 1999; Dollár et al. 2005; Tran and Davis 2008; Nguyen et al. 2009; Ryoo and Aggarwal 2009; Brendel and Todorovic 2011).”
Motion segmentation and pose recognition with motion history gradients (2000, background): “The most common frameworks to recognition of body motion and gesture include the analysis of temporal trajectories of the motion parameters [6, 29, 35, 40], hidden Markov models (HMMs) and state-space models [37, 39, 41], and static-activity templates [12, 17, 19, 34].”
A system for learning statistical motion patterns (2006, methodology): “For instance, Yacoob and Black [49] learn behavior models using PCA of a number of exemplar actions.”