Title :
Should we discard sparse or incomplete videos?
Author :
Chuan Sun ; Foroosh, H.
Author_Institution :
Dept. of EECS, Univ. of Central Florida, Orlando, FL, USA
Abstract :
In this paper, we determine whether incomplete videos that are often discarded carry useful information for action recognition, and if so, how one can represent such mixed collection of video data (complete versus incomplete, and labeled versus unlabeled) in a unified manner. We propose a novel framework to handle incomplete videos in action classification, and make three main contributions: (1) We cast the action classification problem for a mixture of complete and incomplete data as a semi-supervised learning problem of labeled and unlabeled data. (2) We introduce a two-step approach to convert the input mixed data into a uniform compact representation. (3) Exhaustively scrutinizing 280 configurations, we experimentally show on our two created benchmarks that, even the videos are extremely sparse and incomplete, it is still possible to recover useful information from them, and classify unknown actions by a graph based semi-supervised learning framework.
Keywords :
graph theory; image classification; image representation; learning (artificial intelligence); object recognition; tensors; video signal processing; action classiIcation problem; action recognition; complete data mixture; graph based semi supervised learning framework; incomplete data mixture; incomplete video handling; labeled data; mixed video data collection; tensor decomposition; uniform compact representation; unlabeled data; Benchmark testing; Compressed sensing; Error analysis; Semisupervised learning; Tensile stress; Vectors; Videos; Action classification; semi-supervised learning; sparse video; tensor decomposition;
Conference_Titel :
Image Processing (ICIP), 2014 IEEE International Conference on
Conference_Location :
Paris
DOI :
10.1109/ICIP.2014.7025506