Adaptive Feature Abstraction for Translating Video to LanguageDownload PDF

02 Nov 2024 (modified: 21 Jul 2022)ICLR 2017 Invite to WorkshopReaders: Everyone
Abstract: A new model for video captioning is developed, using a deep three-dimensional Convolutional Neural Network (C3D) as an encoder for videos and a Recurrent Neural Network (RNN) as a decoder for captions. A novel attention mechanism with spatiotemporal alignment is employed to adaptively and sequentially focus on different layers of CNN features (levels of feature "abstraction"), as well as local spatiotemporal regions of the feature maps at each layer. The proposed approach is evaluated on the YouTube2Text benchmark. Experimental results demonstrate quantitatively the effectiveness of our proposed adaptive spatiotemporal feature abstraction for translating videos to sentences with rich semantic structures.
Conflicts: duke.edu, nec-labs.com, virginia.edu
0 Replies

Loading