DynTex: A comprehensive database of dynamic textures
By Renaud Péteri, S. Fazekas, Mark J. Huiskes. Pattern Recognition Letters, 2010
347 citations recorded by the source corpus.
We present the DynTex database of high-quality dynamic texture videos. It consists of over 650 sequences of dynamic textures, mostly in everyday surroundings. Additionally, we propose a scheme for the manual annotation of the sequences based on a detailed analysis of the physical processes underlying the dynamic textures. Using this scheme we describe the texture sequences in terms of both visual structure and semantic content. The videos and annotations are made publicly available for scientific research.
Subfields: Computer Vision and Pattern Recognition, Signal Processing
View Paper: https://www.semanticscholar.org/paper/7e003c62c03aa96e03b2b0f0faff3656f1b15997
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
- Dacheng Tao
- Luc Van Gool
- Song-Chun Zhu
- Andrea Vedaldi
- Ming-Hsuan Yang
- Xiaogang Wang
- Trevor Darrell
- Andrew Zisserman
In Signal Processing
- Song-Chun Zhu
- Ying Nian Wu
- Dacheng Tao
- Tian Han
- Xilin Chen
- Shiguang Shan
- Hong Chang
- José Carlos Príncipe
Citations in the corpus
- Video Inpainting of Complex Scenes (2014, methodology): “[This image was taken from the DynTex database [36].”
- Synthesising Dynamic Textures using Convolutional Neural Networks (2017, methodology): “We used example video textures from the DynTex database [11] and from the Internet.”
- Kernel Learning for Dynamic Texture Synthesis (2016, methodology): “(23) The detailed algorithm (training process) is summarized in Algorithm 1.”
- Modeling Video Dynamics with Deep Dynencoder (2014, methodology): “We use DT sequences from the DynTex database [16] as training data respectively.”
- Video fire detection - Review (2013, methodology): “5, dynamic texture detection and segmentation examples are shown, which use video clips from the DynTex dynamic texture and Bilkent databases [51,52,50,47].”
- Divergence Triangle for Joint Training of Generator Model, Energy-Based Model, and Inferential Model (2018, methodology): “The training video clips are selected from Dyntex database [51] and resized to 64 pixels× 64 pixels× 32 frames.”