Interpretable human action recognition in compressed domain

35 citations recorded by the source corpus.

How researchers see this paper

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

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “on. AudioMNIST [46] 7 X + LRP on DeepLight. fMRI data from Human Connectome Project [47] 7 X + LRP on CNN and on BoW(bag of words)/SVM [48] 7 X + LRP on compressed domain action recognition algorithm [49] 7 7 + LRP on video deep learning, selective relevance method [51] 7 X + BiLRP [50] 7 X DeepLIFT”
Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models (2017, background): “More discussion on this experiment can be found in [36].”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “[350, 351] applied it respectively to test models built with Fisher vector classifiers for object recognition in images and to SVMs, trained on videos, to understand and interpret action recognition and to check whether LRP allows identifying in which point of the video the important action happens.”
Understanding Patch-Based Learning by Explaining Predictions (2018, methodology): “While a different approach for human action recognition has been analyzed before [25] using the LRP framework [1], to our knowledge this work is the ﬁrst to analyze any neural network for video classiﬁcation using deep Taylor decomposition [13].”