Discriminative Hierarchical Rank Pooling for Activity Recognition

By Basura Fernando, Peter Anderson, Marcus Hutter, Stephen Gould. 2016

113 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization (2016, methodology): “…vision where they have been applied to parameter and hyper-parameter learning [Do et al., 2007, Domke, 2012, Klatzer and Pock, 2015], image denoising [Samuel and Tappen, 2009, Ochs et al., 2015], and most recently, video activity recognition [Fernando and Gould, 2016, Fernando et al., 2016].”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, neutral): “Hierarchical rank pooling [33] is proposed to learn higher order and non-linear representations compared to the original work.”
Spatially and Temporally Structured Global to Local Aggregation of Dynamic Depth Information for Action Recognition (2018, methodology): “Hierarchical rank pooling [33] encodes the dynamics of a video sequence recursively over several layers.”
Encouraging LSTMs to Anticipate Actions Very Early (2017, methodology): “To overcome this, some methods localize the feature extraction process by exploiting dense trajectories [39, 38, 9] or optical flow [18].”
Structured Images for RGB-D Action Recognition (2017, methodology): “In work [9], the authors indicated that the rank pooling method employed by Fernado et al.”
Learning End-to-end Video Classification with Rank-Pooling (2016, methodology): “It captures the time varying information using rank pooling (Fernando et al., 2015; 2016b) and has the ability to handle variable length sequences.”
UvA-DARE (Digital Academic Repository) Self-Supervised Video Representation Learning With Odd-One-Out Networks (unknown): “There has also been unsupervised temporal feature encoding methods to capture the structure of videos for action classification [13, 14, 15, 29, 36].”
Generalized Rank Pooling for Activity Recognition (2017, methodology): “[15, 13], the problem of pooling using the temporal structure is cast in a learning-to-rank setup, termed Rank Pooling, that computes a line in input space; the projection of input data onto this line preserving the temporal order.”
Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks (2018, methodology): “Firstly, it treats a video sequence in a single temporal scale which is usually too shallow [18].”
UvA-DARE (Digital Academic Repository) Dynamic Image Networks for Action Recognition (2016, background): “Recent works such as [5, 6, 7, 9, 22] pointed out that long term dynamics and temporal patterns are a very important cues for the recognition of actions.”