-
Non-Linear Temporal Subspace Representations for Activity Recognition
Representations that can compactly and effectively capture the temporal ...
read it
-
Human Action Attribute Learning From Video Data Using Low-Rank Representations
Representation of human actions as a sequence of human body movements or...
read it
-
Generalized Rank Pooling for Activity Recognition
Most popular deep models for action recognition split video sequences in...
read it
-
Action Recognition with Dynamic Image Networks
We introduce the concept of "dynamic image", a novel compact representat...
read it
-
Action Representation Using Classifier Decision Boundaries
Most popular deep learning based models for action recognition are desig...
read it
-
Semantic Image Networks for Human Action Recognition
In this paper, we propose the use of a semantic image, an improved repre...
read it
-
Action Recognition with Deep Multiple Aggregation Networks
Most of the current action recognition algorithms are based on deep netw...
read it
Sequence Summarization Using Order-constrained Kernelized Feature Subspaces
Representations that can compactly and effectively capture temporal evolution of semantic content are important to machine learning algorithms that operate on multi-variate time-series data. We investigate such representations motivated by the task of human action recognition. Here each data instance is encoded by a multivariate feature (such as via a deep CNN) where action dynamics are characterized by their variations in time. As these features are often non-linear, we propose a novel pooling method, kernelized rank pooling, that represents a given sequence compactly as the pre-image of the parameters of a hyperplane in an RKHS, projections of data onto which captures their temporal order. We develop this idea further and show that such a pooling scheme can be cast as an order-constrained kernelized PCA objective; we then propose to use the parameters of a kernelized low-rank feature subspace as the representation of the sequences. We cast our formulation as an optimization problem on generalized Grassmann manifolds and then solve it efficiently using Riemannian optimization techniques. We present experiments on several action recognition datasets using diverse feature modalities and demonstrate state-of-the-art results.
READ FULL TEXT
Comments
There are no comments yet.