Exemplar-based Action Recognition in Video

By Geert Willems, Jan Hendrik Becker, Tinne Tuytelaars, Luc Van Gool. 2009

74 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Video Representation Learning Using Discriminative Pooling (2018, methodology): “In this respect, our pooling scheme is also different from ExemplarSVMs [29, 56, 61] that learns feature filters per data sample and then use these filters for feature extraction.”
Action Recognition with Exemplar Based 2.5D Graph Matching (2012, background): “While the majority of work in computer vision are model based, exemplar based methods have also been applied in object recognition [25–27] and video classification [28].”
Real-time Action Recognition by Spatiotemporal Semantic and Structural Forests (2010, methodology): “[27] used an extended SURF descriptor for action recognition.”
Animated Pose Templates for Modeling and Detecting Human Actions (2014, unknown): “Table 3 reports the average precision (AP) of our methods and previous work [26], [40], [41].”
Does Human Action Recognition Benefit from Pose Estimation? (2011, background): “Lately, spatio-temporal interest points have become especially popular, e.g. cuboids [6], 3D Harris corners [16] and 3D Hessians [31].”
Temporal Localization of Actions with Actoms (2013, unknown): “[4, 6, 7, 10–12 , 38– 45”
Hough Forests for Object Detection, Tracking, and Action Recognition (2011, background): “Using spatio-temporal interest points for action recognition has become very popular, e.g., cuboids [10], 3D Harris corners [52], 3D Hessians [53], and 3D salient points [54].”
A Hough transform-based voting framework for action recognition (2010, background): “In addition to classification, action recognition systems are also trying to address localization, or estimating the spatio-temporal boundaries of a given action [22, 23, 21, 35, 30].”
Coupled Action Recognition and Pose Estimation from Multiple Views (2012, background): “2010) or completely bypass the difficulties of pose estimation and directly classify actions with abstract and low-level appearance features (Dollar et al. 2005; Efros et al. 2003; Jhuang et al. 2007; Laptev and Lindeberg 2003; Schindler and Van Gool 2008; Willems et al. 2009).”
High Five: Recognising human interactions in TV shows (2010, methodology): “Our experiments show that using structured learning improves the retrieval results compared to using the interaction classifiers independently.”