Learning a hierarchy of discriminative space-time neighborhood features for human action recognition

By Adriana Kovashka, Kristen Grauman. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

565 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/698305079aad248aa23bbc87d12a9452f6fda579

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 Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A Review of Human Activity Recognition Methods (2015, methodology): “A vocabulary based approach has been proposed by Kovashka and Grauman (2010).”
Trajectory-Based Modeling of Human Actions with Motion Reference Points (2012, background): “The first category extracts/learns spatial-temporal local features where many efforts have been devoted to the design of good detectors/descriptors [1,7,8,9,10,11] or feature learning algorithms [12,13,14].”
Script Data for Attribute-Based Recognition of Composite Activities (2012, result): “This is in contrast to approaches that represent activities as bags of spatio-temporal features [14, 1, 2, 15] disregarding potential structure within the activity.”
Body Surface Context: A New Robust Feature for Action Recognition From Depth Videos (2014, unknown): “encoded structure information in action representation [25].”
Motion Interchange Patterns for Action Recognition in Unconstrained Videos (2012, methodology): “On this older, artificial, and perhaps more limited benchmark our system achieves 93% accuracy which is on par with results reported by leading contributions that apply similar setting (for example, [9, 14, 22]).”
Evaluating New Variants of Motion Interchange Patterns (2013, methodology): “Recent methods use local descriptors for recognition [13, 28, 17].”
Dense Trajectories and Motion Boundary Descriptors for Action Recognition (2013, unknown): “1% which is around 2% better than the state of the art (Kovashka and Grauman, 2010).”
Discriminative figure-centric models for joint action localization and recognition (2011, methodology): “Kovashka and Grauman [13] consider higher-order relations between visual words, each with discriminatively selected spatial arrangements.”
Multi-task Sparse Learning with Beta Process Prior for Action Recognition (2013, methodology): “The UCF sports database was tested in a leave-one-out manner, cycling each example in as a test video one at a time, following [18] [24] [22].”
The Action Similarity Labeling Challenge (2012, background): “Early sets, such as KTH [1] and Weizmann [2], have been extensively used to report action recognition performance (e.g., [18], [19], [20], [21], [22], [23], [24], to name a few).”
RGBD-HuDaAct: A color-depth video database for human daily activity recognition (2011, background): “However, the simplicity of the action categories as well as the clean backgrounds make the recognition tasks easy.”
Recognizing human actions by attributes (2011, background): “Some approaches have attempted to integrate contextual information, such as spacetime neighborhood features[13], object-scene-action mixture models[12], and spatial and temporal relations[22].”
Visual event recognition in videos by learning from web data (2010, background): “Promising results [12], [20], [27], [32], [41] have been reported on video data sets under controlled conditions, such as Weizman [12] and KTH [41] data sets.”
Real-time Action Recognition by Spatiotemporal Semantic and Structural Forests (2010, background): “33 sequence Neighbourhood** (2010) [6] - - - - - - 94.”