Hierarchical Boundary-Aware Neural Encoder for Video Captioning

Hierarchical Boundary-Aware Neural Encoder for Video Captioning

Lorenzo Baraldi,  Costantino Grana,  Rita Cucchiara

(Submitted on 28 Nov 2016 ( v1), last revised 10 Apr 2017 (this version, v3))

The use of Recurrent Neural Networks for video captioning has recently gained a lot of attention, since they can be used both to encode the input video and to generate the corresponding description. In this paper, we present a recurrent video encoding scheme which can discover and leverage the hierarchical structure of the video. Unlike the classical encoder-decoder approach, in which a video is encoded continuously by a recurrent layer, we propose a novel LSTM cell, which can identify discontinuity points between frames or segments and modify the temporal connections of the encoding layer accordingly. We evaluate our approach on three large-scale datasets: the Montreal Video Annotation dataset, the MPII Movie Description dataset and the Microsoft Video Description Corpus. Experiments show that our approach can discover appropriate hierarchical representations of input videos and improve the state of the art results on movie description datasets.

Comments:	CVPR 2017
Subjects:	Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:1611.09312 [cs.CV]
	(or arXiv:1611.09312v3 [cs.CV] for this version)

Submission history

From: Lorenzo Baraldi [ view email] 
[v1] Mon, 28 Nov 2016 20:02:28 GMT (1743kb,D)
[v2] Fri, 3 Mar 2017 12:50:20 GMT (1945kb,D)
[v3] Mon, 10 Apr 2017 13:36:08 GMT (2331kb,D)