Temporal Tessellation: A Unified Approach for Video Analysis

Dotan Kaufman, Gil Levi, Tal Hassner, Lior Wolf; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 94-104

Abstract


We present a general approach to video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a video to be a 1D sequence of clips, each one associated with its own semantics. The nature of these semantics -- natural language captions or other labels -- depends on the task at hand. A test video is processed by forming correspondences between its clips and the clips of reference videos with known semantics, following which, reference semantics can be transferred to the test video. We describe two matching methods, both designed to ensure that (a) reference clips appear similar to test clips and (b), taken together, the semantics of the selected reference clips is consistent and maintains temporal coherence. We use our method for video captioning on the LSMDC'16 benchmark, video summarization on the SumMe and TVSum benchmarks, Temporal Action Detection on the Thumos2015 benchmark, and sound prediction on the Greatest Hits benchmark. Our method not only surpasses the state of the art, in four out of five benchmarks, but importantly, it is the only single method we know of that was successfully applied to such a diverse range of tasks.

Related Material


[pdf] [arXiv] [video]
[bibtex]
@InProceedings{Kaufman_2017_ICCV,
author = {Kaufman, Dotan and Levi, Gil and Hassner, Tal and Wolf, Lior},
title = {Temporal Tessellation: A Unified Approach for Video Analysis},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}