Beyond Caption To Narrative: Video Captioning With Multiple Sentences

Beyond Caption To Narrative: Video Captioning With Multiple Sentences

Andrew Shin, Katsunori Ohnishi, Tatsuya
Harada

(Submitted on 18 May 2016)

Recent advances in image captioning task have led to increasing interests in video captioning task. However, most works on video captioning are focused on generating single input of aggregated features, which hardly deviates from image captioning process and
does not fully take advantage of dynamic contents present in videos. We attempt to generate video captions that convey richer contents by temporally segmenting the video with action localization, generating multiple captions from multiple frames, and connecting
them with natural language processing techniques, in order to generate a story-like caption. We show that our proposed method can generate captions that are richer in contents and can compete with state-of-the-art method without explicitly using video-level
features as input.

Comments:	accepted to ICIP 2016
Subjects:	Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:1605.05440 [cs.CV]
	(or arXiv:1605.05440v1 [cs.CV] for this version)

Submission history

From: Andrew Shin [view email] 
[v1] Wed, 18 May 2016 05:00:12 GMT (1186kb,D)