Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition

By Mikel D. Rodriguez, Javed Ahmed, Mubarak Shah. 2008

1,386 citations recorded by the source corpus.

Subfields: Biomedical Engineering, 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 Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

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].”
Differential Recurrent Neural Networks for Action Recognition (2015, neutral): “Rodriguez et al. [22] 81.50 Jhuang et al.[13] 91.70 Schindler et al. [23] 92.70 3DCNN [2] 91.04”
Finding action tubes (2014, methodology): “Contrary to J-HMDB, UCF Sports has been widely used by scientists for evaluation purposes.”
Video In Sentences Out (2012, methodology): “…2003; Darrell et al., 2011; McKevitt, 1994, 1995–1996) and recognition of action in video (Blank et al., 2005; Laptev et al., 2008; Liu et al., 2009; Rodriguez et al., 2008; Schuldt et al., 2004; Siskind and Morris, 1996; Starner et al., 1998; Wang and Mori, 2009; Xu et al., 2002, 2005) have been…”
The “Something Something” Video Database for Learning and Evaluating Visual Common Sense (2017, background): “Not surprisingly, most of the currently popular labeled video datasets are action recognition datasets [27, 17, 24, 11].”
Unstructured human activity detection from RGBD images (2011, methodology): “We have also made the dataset and code available open-source at: http://pr.cs.cornell.edu/humanactivities”
Gibson Env: Real-World Perception for Embodied Agents (2018, background): “Similarly, video datasets [53, 66, 95] are pre-recorded and still passive.”
Towards Weakly-Supervised Action Localization (2016, background): “• The UCF-Sports dataset [37] consists of 150 sports videos with 10 actions, such as diving or running .”
Visual Semantic Role Labeling (2015, background): “Given annotations can be generated automatically, this will be a large dataset, but is inadequate for us as it does not have the visual grounding which is our interest here.”
Action Classification with Locality-Constrained Linear Coding (2014, methodology): “The average accuracies of our algorithm using SC and LLC are 89.6% and 94.1%, respectively.”
Learning to Track for Spatio-Temporal Action Localization (2015, neutral): “UCF-Sports [35].”
Dense Trajectories and Motion Boundary Descriptors for Action Recognition (2013, background): “In this section, we evaluate the impact of the parameters on dense trajectories.”
Similarity Constrained Latent Support Vector Machine: An Application to Weakly Supervised Action Classification (2012, methodology): “In this section we examine the performance of our model for action recognition and evidence localization on the UCF-Sports dataset [22].”
Script Data for Attribute-Based Recognition of Composite Activities (2012, background): “KTH dataset [4]), and robustly recognize actions in realistic settings such as Hollywood movies [5], videos from YouTube [6], or sport scenes [7].”
Online Action Detection (2016, neutral): “, UCF Sports [21], the videos are temporally trimmed: they contain exactly the action, from start to finish.”
Efﬁcient feature extraction, encoding and classiﬁcation for action recognition (neutral): “Recent methods show signiﬁcant progress towards action recognition in realistic and challenging videos from YouTube, movies and TV [16, 17, 8, 22, 29, 31, 35].”