Video Captioning with Multi-Faceted Attention

Xiang Long, Chuang Gan, Gerard de Melo

(Submitted on 1 Dec 2016)

Recently, video captioning has been attracting an increasing amount of interest, due to its potential for improving accessibility and information retrieval. While existing methods rely on different kinds of visual features and model structures, they do not fully exploit relevant semantic information. We present an extensible approach to jointly leverage several sorts of visual features and semantic attributes. Our novel architecture builds on LSTMs for sentence generation, with several attention layers and two multimodal layers. The attention mechanism learns to automatically select the most salient visual features or semantic attributes, and the multimodal layer yields overall representations for the input and outputs of the sentence generation component. Experimental results on the challenging MSVD and MSR-VTT datasets show that our framework outperforms the state-of-the-art approaches, while ground truth based semantic attributes are able to further elevate the output quality to a near-human level.

Subjects:Computer Vision and Pattern Recognition (cs.CV)Cite as:arXiv:1612.00234 [cs.CV] (or arXiv:1612.00234v1 [cs.CV] for this version)

Submission history

From: Xiang Long [view email] 
[v1] Thu, 1 Dec 2016 13:11:29 GMT (733kb,D)