Actions as Space-Time Shapes

By Lena Gorelick, Moshe Blank, Eli Shechtman, Michal Irani, Ronen Basri. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007

961 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/183a697bdea9cdc9cec21267ddbf6ab2eb118258

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A 3-dimensional sift descriptor and its application to action recognition (2007, methodology): “For this purpose we employ the action data set provided by [1].”
Human activity recognition using multi-features and multiple kernel learning (2014, background): “[17] analyzed 3D shapes of silhouettes in a space-time volume to create 3D spatio-temporal features for human activity recognition.”
Discovering discriminative action parts from mid-level video representations (2012, methodology): “The second uses global spatiotemporal templates, such as motion history [3], spatiotemporal shapes [1], and other templates [13], that retain the spatial structure.”
Online robust action recognition based on a hierarchical model (2014, methodology): “These methods can be divided into two categories: recognition based on global video descriptors [4] and recognition based on local video descriptors [1,3].”
Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding (2016, background): “Standard approaches in the past have used videos downloaded from the Internet [3,4,5,6,7,8] gathered from movies [9,10,11] or recorded in controlled environments [12,13,14,15,16,17].”
Lifelong Learning of Action Representations with Deep Neural Self-Organization (2017, methodology): “Our experiments yielded an overall accuracy of 98.6%, which is a very competitive result with respect to the state of the art of 99.64% reported by (Gorelick et al. 2005).”
Tensor Canonical Correlation Analysis for Action Classification (2007, background): “Importantly, it has been noted that spatial information contains cues as important as dynamic information for human action classification [2].”
An efficient part-based approach to action recognition from RGB-D video with BoW-pyramid representation (2013, methodology): “Then, we classify the extracted features into different parts and organize them into BoW-Pyramid to represent an action for each part.”
Effective Active Skeleton Representation for Low Latency Human Action Recognition (2016, background): “temporal interest point [22]–[25], trajectories [26]–[29] or using deep learning models [30].”
Learning deformable action templates from cluttered videos (2009, background): “This poses a challenge for many approaches on action recognition [1, 5, 23, 11] that assume the foreground segmentation (silhouette) is available.”
Actions as space-time shapes (2005, neutral): “A preliminary version of this paper appeared in ICCV’05 [4].”
Robust Action Recognition Based on a Hierarchical Model (2013, methodology): “These methods can be divided into two categories: recognition based on global video descriptors [4] and recognition based on local video descriptors [1] [3].”