Generating Natural-Language Video Descriptions Using Text-Mined Knowledge (2013)
We present a holistic data-driven technique that generates natural-language descriptions for videos. We combine the output of state-of-the-art object and activity detectors with ``real-world'' knowledge to select the most probable subject-verb-object triplet for describing a video. We show that this knowledge, automatically mined from web-scale text corpora, enhances the triplet selection algorithm by providing it contextual information and leads to a four-fold increase in activity identification. Unlike previous methods, our approach can annotate arbitrary videos without requiring the expensive collection and annotation of a similar training video corpus. We evaluate our technique against a baseline that does not use text-mined knowledge and show that humans prefer our descriptions 61% of the time.
Proceedings of the NAACL HLT Workshop on Vision and Language (WVL '13) (2013), pp. 10--19.

Niveda Krishnamoorthy Masters Alumni niveda [at] cs utexas edu
Girish Malkarnenkar Masters Alumni girish [at] cs utexas edu
Raymond J. Mooney Faculty mooney [at] cs utexas edu