Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks

We present an approach that exploits hierarchical Recurrent Neural Networks (RNNs) to tackle the video captioning problem, i.e., generating one or multiple sentences to describe a realistic video. Our hierarchical framework contains a sentence generator and a paragraph generator. The sentence generator produces one simple short sentence that describes a specific short video interval. It exploits both temporal-and spatial-attention mechanisms to selectively focus on visual elements during generation. The paragraph generator captures the inter-sentence dependency by taking as input the sentential embedding produced by the sentence generator, combining it with the paragraph history, and outputting the new initial state for the sentence generator. We evaluate our approach on two large-scale benchmark datasets: YouTubeClips and TACoS-MultiLevel. The experiments demonstrate that our approach significantly outperforms the current state-of-the-art methods with BLEU@4 scores 0.499 and 0.305 respectively.

[1]  Jeffrey Mark Siskind,et al.  Learning to Describe Video with Weak Supervision by Exploiting Negative Sentential Information , 2015, AAAI.

[2]  Ruslan Salakhutdinov,et al.  Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models , 2014, ArXiv.

[3]  U. Austin,et al.  Translating Videos to Natural Language Using Deep Recurrent Neural Networks , 2017 .

[4]  C. Lawrence Zitnick,et al.  CIDEr: Consensus-based image description evaluation , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Sven J. Dickinson,et al.  Video In Sentences Out , 2012, UAI.

[6]  Chenliang Xu,et al.  A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[8]  Trevor Darrell,et al.  Sequence to Sequence -- Video to Text , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[9]  Gunhee Kim,et al.  Expressing an Image Stream with a Sequence of Natural Sentences , 2015, NIPS.

[10]  Jason Weston,et al.  Question Answering with Subgraph Embeddings , 2014, EMNLP.

[11]  Kate Saenko,et al.  Generating Natural-Language Video Descriptions Using Text-Mined Knowledge , 2013, AAAI.

[12]  Cordelia Schmid,et al.  Action recognition by dense trajectories , 2011, CVPR 2011.

[13]  Marc'Aurelio Ranzato,et al.  Sequence Level Training with Recurrent Neural Networks , 2015, ICLR.

[14]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Gunnar Farnebäck,et al.  Two-Frame Motion Estimation Based on Polynomial Expansion , 2003, SCIA.

[16]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[17]  Xinlei Chen,et al.  Learning a Recurrent Visual Representation for Image Caption Generation , 2014, ArXiv.

[18]  Bernt Schiele,et al.  Translating Video Content to Natural Language Descriptions , 2013, 2013 IEEE International Conference on Computer Vision.

[19]  Lei Zhang,et al.  Human Focused Video Description , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[20]  Wei Chen,et al.  Jointly Modeling Deep Video and Compositional Text to Bridge Vision and Language in a Unified Framework , 2015, AAAI.

[21]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[22]  Ramakant Nevatia,et al.  Semantic Aware Video Transcription Using Random Forest Classifiers , 2014, ECCV.

[23]  David Vandyke,et al.  Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems , 2015, EMNLP.

[24]  Trevor Darrell,et al.  YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-Shot Recognition , 2013, 2013 IEEE International Conference on Computer Vision.

[25]  Kunio Fukunaga,et al.  Natural Language Description of Human Activities from Video Images Based on Concept Hierarchy of Actions , 2002, International Journal of Computer Vision.

[26]  Christopher Joseph Pal,et al.  Describing Videos by Exploiting Temporal Structure , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Bernt Schiele,et al.  Coherent Multi-sentence Video Description with Variable Level of Detail , 2014, GCPR.

[28]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[29]  Lei Zhang,et al.  Towards coherent natural language description of video streams , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[30]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[31]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[32]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[35]  Wei Xu,et al.  Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN) , 2014, ICLR.

[36]  Marcus Rohrbach,et al.  A Multi-scale Multiple Instance Video Description Network , 2015, ArXiv.

[37]  Samy Bengio,et al.  Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks , 2015, NIPS.

[38]  Klamer Schutte,et al.  Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions , 2012, ECCV Workshops.

[39]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[40]  Phil Blunsom,et al.  Recurrent Continuous Translation Models , 2013, EMNLP.

[41]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[42]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[43]  Alon Lavie,et al.  METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments , 2005, IEEvaluation@ACL.

[44]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[45]  Daniel Jurafsky,et al.  A Hierarchical Neural Autoencoder for Paragraphs and Documents , 2015, ACL.

[46]  Lorenzo Torresani,et al.  C3D: Generic Features for Video Analysis , 2014, ArXiv.

[47]  Ming Zhou,et al.  Hierarchical Recurrent Neural Network for Document Modeling , 2015, EMNLP.

[48]  Tao Mei,et al.  Jointly Modeling Embedding and Translation to Bridge Video and Language , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[49]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[50]  William B. Dolan,et al.  Collecting Highly Parallel Data for Paraphrase Evaluation , 2011, ACL.

[51]  Xu Wei,et al.  Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[52]  Peter Young,et al.  From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions , 2014, TACL.

[53]  Hong Cheng,et al.  Sparse Representation, Modeling and Learning in Visual Recognition , 2015, Advances in Computer Vision and Pattern Recognition.

[54]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[55]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[56]  Cordelia Schmid,et al.  Aggregating Local Image Descriptors into Compact Codes , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[57]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[58]  Mun Wai Lee,et al.  SAVE: A framework for semantic annotation of visual events , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[59]  Xinlei Chen,et al.  Microsoft COCO Captions: Data Collection and Evaluation Server , 2015, ArXiv.