Similarity Constrained Latent Support Vector Machine: An Application to Weakly Supervised Action Classification

By Nataliya Shapovalova, Arash Vahdat, Kevin J. Cannons, Tian Lan, Greg Mori. 2012

56 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, methodology): “Multiple instance learning methods have been employed in many weakly-supervised video understanding problems including: person recognition in movies using scripts [12, 50, 61], anomaly detection [70], weakly supervised action classification [47, 68] and localization [17, 22, 82], co-reference resolu”
Towards Weakly-Supervised Action Localization (2016, background): “[34] extend latent SVM to model pairwise similarities between latent variables, aiming at discovering common parts for a particular action.”
A Discriminative Model with Multiple Temporal Scales for Action Prediction (2014, unknown): “Human action recognition [17,10,8,18] has been of great interest for the computer vision community for many decades due to its practical importance, such as video analysis and visual surveillance.”
Learning from Video and Text via Large-Scale Discriminative Clustering (2017, methodology): “A weakly supervised extension of this method [34] localizes actions without location supervision at the training time.”
Representing Videos Using Mid-level Discriminative Patches (2013, methodology): “We build upon the recent work of Singh et al. [31] and extract “video poselets” from just action labels.”
We Don’t Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification (2016, background): “Second, like in [9, 12, 21, 38, 43, 47, 44, 51, 61], we combine the object detector score with a general measure of “objectness” [1], which measures how likely it is that a proposal tightly encloses an object of any class (e.”
Revisiting Knowledge Transfer for Training Object Class Detectors (2017, methodology): “Our scheme improves over previous usage of manually engineered object proposals and their associated objectness score [1, 10] in WSOL in two ways: (1) by using trained proposals and objectness scoring function trained on source classes; (2) generalizing the common use of a single classagnostic objec”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, methodology): “Objectness was used in WSOL before, to steer the localization process towards objects and away from background [11, 13, 21, 48, 58, 61, 59, 67, 75].”