Maximum Margin Distance Learning for Dynamic Texture Recognition

162 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.

Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns (2019, methodology): “To quantitatively evaluate the qualities of the recovered videos, we test our method on 7 video sequences, which are collected from DynTex++ dataset of [67], with 3 types of occlusions mentioned above.”
Cooperative Training of Descriptor and Generator Networks (2016, methodology): “We collect the training video clips from DynTex++ dataset of [70] and the Internet.”
Synthesizing Dynamic Patterns by Spatial-Temporal Generative ConvNet (2016, methodology): “We learn the spatial-temporal generative ConvNet from video clips collected from DynTex++ dataset of [4] and the Internet.”
A Comprehensive Look at Coding Techniques on Riemannian Manifolds (2018, methodology): “RECOGNITION ACCURACIES IN % FOR THE MARYLAND [30], DYNTEX++ [12], AND YTC [23] DATA SETS”
Learning LBP structure by maximizing the conditional mutual information (2015, methodology): “LBP and its variants have been widely used in many applications, e.g. image texture classification [1] [2] [3], dynamic texture (DT) recognition [4] [5] [6] [7], scene recognition [8] [9], facial analysis [10] [11] [12] [13] [14] [15] [16] [17] [18] [19], and others [20] [21] [22] [23] [24] [25]…”