An appearance-based representation of action

By Aaron F. Bobick, James W. Davis. 1996

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

Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, background): “Two kinds of motion representations can be identified: Lagrangian motion [63, 64, 30, 44, 66, 43, 72] and Eulerian motion [4, 5, 80, 38, 78, 67, 68, 3].”
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.”
The Recognition of Human Movement Using Temporal Templates (2001, methodology): “Bobick [6] considers the range of motion interpretation problems and proposes a taxonomy of approaches.”
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]”
Stochastic Tracking of 3D Human Figures Using 2D Image Motion (2000, methodology): “Temporal models of body limb or joint motion also vary in complexity; they include smooth motion [7], linear dynamical models [18], nonlinear models learned from training data using dimensionality reduction [3,16,23], and probabilistic Hidden Markov Models (HMM’s) (e.”
A Review on Human Activity Recognition Using Vision-Based Method (2017, background): “Bobick and Davis [16, 17] stacked the silhouettes as two components for recognizing activities, respectively, the motion-energy image (MEI) and the motion-history image (MHI), which are both 2D representations.”
Motion history image: its variants and applications (2012, background): “They [30,31] present the construction of a binary motion energy image (MEI) or binary motion region (BMR) [47], which represents where motion has occurred in an image sequence.”
Dynamic texture recognition (2001, methodology): “Other methods, such as [7] [3] [5] [36], use a statistical hierarchical approach based on local appearance.”
Parameterized modeling and recognition of activities (1998, background): “The most closely related work to the work reported here is that of Bobick and Davis [6] and Ju et al. 191, both proposed using principal component analysis to model parameters computed from activities but did not demonstrate modeling and recognition of activities .”
Inverse Dynamics for Action Recognition (2013, background): “A number of researchers [3], [4], [33], [39]–[41] have used”
A Survey of Computer Vision-Based Human Motion Capture (2001, unknown): “1980 O’Rourke [114] 1983 Hogg * [58] 1984 Akita * [3] 1984 Hogg * [59] 1985 Lee [83] 1985 Tsukiyama [135] 1987 Bernat [11] 1987 Leung * [88] 1987 Leung [89] 1989 Attwood [6] 1991 Long * [92] 1991 Shio [129] * 1991 Wang * [140] 1991 Yamamoto [152] 1992 Kepple [81] 1992 Lee [84] 1992 Luo * [94] 1992 W”