Histograms of oriented optical flow and Binet-Cauchy kernels on nonlinear dynamical systems for the recognition of human actions

By Rizwan Ahmed Chaudhry, Avinash Ravichandran, Gregory Hager, René Vidal. 2009

720 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

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 Signal Processing

Citations in the corpus

Deep Learning on Lie Groups for Skeleton-Based Action Recognition (2016, background): “Typical examples include shape silhouettes in Kendall’s shape space [39, 3], linear dynamical systems on the Grassmann manifold [38], histograms of oriented optical ﬂow on a hyper-sphere [11], and pairwise transformations of skeletal joints on a Lie group [40, 3, 41].”
Improving Multi-Step Prediction of Learned Time Series Models (2015, methodology): “Motivated by prior work in kernelized modeling of dynamical systems (Ralaivola and D’Alche-Buc 2004; Chaudhry et al. 2009; Wingate and Singh 2006; Kawahara, Yairi, and Machida 2006), we use kernel regression, a nonparametric learning procedure that allows us to embed our data points into a high, pos”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “This includes both discriminative [1], [13], [14], [15] and generative models [16], [17].”
Less is More: Micro-expression Recognition from Video using Apex Frame (2016, result): “Different from the conventional Histogram of Oriented Optical Flow (HOOF) [3], the orientation histogram bins have equal votes.”
A Main Directional Mean Optical Flow Feature for Spontaneous Micro-Expression Recognition (2016, methodology): “We evaluate our proposed method on three spontaneous micro-expression databases (SMIC, CASME, and CASME II) and compare MDMO with two state-of-the-art baseline features (HOOF [22] and LBP-TOP [13], [23]).”
Movement Pattern Histogram for Action Recognition and Retrieval (2014, methodology): “Note that MPH is quite different from other flow-based models such as the histograms of oriented optical flow (HOOF) [4].”
Online Action Recognition via Nonparametric Incremental Learning (2014, methodology): “Our approach for KTH and Weizmann datasets is based on the histogram of oriented optical flows (HOOF) [8] using 32 bins.”
Elastic functional coding of human actions: From vector-fields to latent variables (2015, methodology): “Examples include activity recognition [25, 4, 29], medical image analysis [6], and shape analysis [21].”
HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object Classification (2018, background): “It is inspired by its frame-based counterpart [10], but in [12] the algorithm for computing the optical ﬂow relies on the temporal information carried by the events.”
Video-Based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms (2021, methodology): “MDMO and sparse MDMO are similar to the histogram of oriented optical ﬂow (HOOF) feature [87]; however, the key difference is that MDMO and sparse MDMO use HOOF features in a local way (i.e., in each ROI region) and are thus more discriminative.”
Summarizing surveillance videos with local-patch-learning-based abnormality detection, blob sequence optimization, and type-based synopsis (2015, methodology): “In our experiments, histogram of oriented optical flow (HOOF) [15] is utilized as the motion descriptor.”
A Review of Human Activity Recognition Methods (2015, methodology): “Other optical flow-based methods which gained popularity were presented by Dalal et al. (2006), Chaudhry et al. (2009), and Lin et al. (2009).”