Video Captioning with Visual and Semantic Features
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Video captioning refers to the process of extracting features from a video and generating video captions usingthe extracted features. This paper introduces a deep neural network model and its learning method foreffective video captioning. In this study, visual features as well as semantic features, which effectively expressthe video, are also used. The visual features of the video are extracted using convolutional neural networks,such as C3D and ResNet, while the semantic features are extracted using a semantic feature extractionnetwork proposed in this paper. Further, an attention-based caption generation network is proposed foreffective generation of video captions using the extracted features. The performance and effectiveness of theproposed model is verified through various experiments using two large-scale video benchmarks such as theMicrosoft Video Description (MSVD) and the Microsoft Research Video-To-Text (MSR-VTT).
Abstract
Video captioning refers to the process of extracting features from a video and generating video captions usingthe extracted features. This paper introduces a deep neural network model and its learning method foreffective video captioning. In this study, visual features as well as semantic features, which effectively expressthe video, are also used. The visual features of the video are extracted using convolutional neural networks,such as C3D and ResNet, while the semantic features are extracted using a semantic feature extractionnetwork proposed in this paper. Further, an attention-based caption generation network is proposed foreffective generation of video captions using the extracted features. The performance and effectiveness of theproposed model is verified through various experiments using two large-scale video benchmarks such as theMicrosoft Video Description (MSVD) and the Microsoft Research Video-To-Text (MSR-VTT).
참고문헌 (16)
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770~778 (2016)
- D. Tran, "Learning spatiotemporal features with 3D convolutional networks", Proceedings of IEEE International Conference on Computer Vision (ICCV), pp.4489~4497 (2015)
- S. Guadarrama, "YouTube2Text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition", Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp.2712~2719 (2013)
- J. Xu, "MSR-VTT: a large video description dataset for bridging video and language", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.5288~5296 (2016)
- S. Venugopalan, "Sequence to sequence:video to text", Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp.4534~4542 (2015)
- Y. Pan, "Jointly modeling embedding and translation to bridge video and language", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.4594~4602 (2016)
- L. Yao, "Describing videos by exploiting temporal structure", Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp.4507~4515 (2015)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", Proceedings of the International Conference on Learning Representations (ICLR) (2015)
- Z. Gan, "Semantic compositional networks for visual captioning", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1141~1150 (2017)
- Y. Pan, "Video Captioning with Transferred Semantic Attributes", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.984~992 (2017)
- Y. Yu, "End-to-end concept word detection for video captioning, retrieval, and question answering", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.3261~3269 (2017)
- F. Nian, "Learning explicit video attributes from mid-level representation for video captioning", Journal of Computer Vision and Image Understanding, 163, pp.126~138 (2017)
- J. Song, "Hierarchical LSTM with adjusted temporal attention for video captioning", Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), pp.2737~2743 (2017)
- A. A. Liu, "Hierarchical & multimodal video captioning: discovering and transferring multimodal knowledge for vision to language", Journal of Computer Vision and Image Understanding, 163, pp.113~125 (2017)
- K. Papineni, "BLEU: a method for automatic evaluation of machine translation", Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pp.311~318 (2002)
- R. Vedantam, "CIDEr: Consensus-based Image Description Evaluation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.4566~4575 (2015)