SimonBibtex

SimonBibtex.bib

@article{kadir2001saliency,
  title={Saliency, scale and image description},
  author={Kadir, Timor and Brady, Michael},
  journal={International Journal of Computer Vision},
  volume={45},
  number={2},
  pages={83--105},
  year={2001},
  publisher={Springer}
}
@inproceedings{ren2015exploring,
  title={Exploring models and data for image question answering},
  author={Ren, Mengye and Kiros, Ryan and Zemel, Richard},
  booktitle={Proceedings of Advances in Neural Information Processing Systems},
  month={Dec.},
  pages={2953--2961},
  year={2015}
}
@inproceedings{malinowski2015ask,
  title={Ask your neurons: A neural-based approach to answering questions about images},
  author={Malinowski, Mateusz and Rohrbach, Marcus and Fritz, Mario},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  month={Dec.},
  pages={1--9},
  year={2015}
}
@inproceedings{malinowski2014multi,
  title={A multi-world approach to question answering about real-world scenes based on uncertain input},
  author={Malinowski, Mateusz and Fritz, Mario},
  booktitle={Proceedings of Advances in Neural Information Processing Systems},
  month={Dec.},
  pages={1682--1690},
  year={2014}
}
@inproceedings{luong2015effective,
  title={Effective approaches to attention-based neural machine translation},
  author={Luong, Minh-Thang and Pham, Hieu and Manning, Christopher D},
  booktitle={Proceedings of conference on Empirical Methods on Natural Language Processing},
  month={Sept.},
  year={2015}
}
@inproceedings{antol2015vqa,
  title={Vqa: Visual question answering},
  author={Antol, Stanislaw and Agrawal, Aishwarya and Lu, Jiasen and Mitchell, Margaret and Batra, Dhruv and Lawrence Zitnick, C and Parikh, Devi},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  month={Dec.},
  pages={2425--2433},
  year={2015}
}
@inproceedings{kuznetsova2013generalizing,
  title={Generalizing Image Captions for Image-Text Parallel Corpus},
  author={Kuznetsova, Polina and Ordonez, Vicente and Berg, Alexander C and Berg, Tamara L and Choi, Yejin},
  booktitle={Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics},
  pages={790--796},
  month={Aug.},
  year={2013},
  organization={Citeseer}
}
@inproceedings{kuznetsova2012collective,
  title={Collective generation of natural image descriptions},
  author={Kuznetsova, Polina and Ordonez, Vicente and Berg, Alexander C and Berg, Tamara L and Choi, Yejin},
  booktitle={Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics},
  volume={1},
  month={Jul.},
  pages={359--368},
  year={2012},
  organization={Association for Computational Linguistics}
}

@article{kulkarni2013babytalk,
  title={Babytalk: Understanding and generating simple image descriptions},
  author={Kulkarni, Girish and Premraj, Visruth and Ordonez, Vicente and Dhar, Sagnik and Li, Siming and Choi, Yejin and Berg, Alexander C and Berg, Tamara L},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={35},
  number={12},
  pages={2891--2903},
  year={2013},
  publisher={IEEE}
}
@inproceedings{farhadi2010every,
  title={Every picture tells a story: Generating sentences from images},
  author={Farhadi, Ali and Hejrati, Mohsen and Sadeghi, Mohammad Amin and Young, Peter and Rashtchian, Cyrus and Hockenmaier, Julia and Forsyth, David},
  booktitle={Proceedings of European conference on computer vision},
  month={Sept.},
  pages={15--29},
  year={2010},
  organization={Springer}
}
@inproceedings{lin2004automatic,
  title={Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics},
  author={Lin, Chin-Yew and Och, Franz Josef},
  booktitle={Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics},
  month={Jul.},
  pages={605--612},
  year={2004},
  organization={Association for Computational Linguistics}
}

@inproceedings{ma2015learning,
  title={Learning to answer questions from image using convolutional neural network},
  author={Ma, Lin and Lu, Zhengdong and Li, Hang},
  booktitle={Proceedings of Association for the Advancement of Artificial Intelligence Conference},
  month={Feb.},
  page={3567--3573},
  year={2016}
}
@inproceedings{wu2015value,
  title={What value do explicit high level concepts have in vision to language problems?},
  author={Wu, Qi and Shen, Chunhua and Liu, Lingqiaoand Dick, AAnthony and Hengel, Anton van den},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  month = {Jun.},
  pages={203--212},
  year={2016}
}

@inproceedings{karpathy2015deep,
  title={Deep visual-semantic alignments for generating image descriptions},
  author={Karpathy, Andrej and Fei-Fei, Li},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  month = {Jun.},
  pages={3128--3137},
  year={2015}
}
@inproceedings{vinyals2015show,
  title={Show and tell: A neural image caption generator},
  author={Vinyals, Oriol and Toshev, Alexander and Bengio, Samy and Erhan, Dumitru},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  month = {Jun.},
  pages={3156--3164},
  year={2015}
}
@inproceedings{fang2015captions,
  title={From captions to visual concepts and back},
  author={Fang, Hao and Gupta, Saurabh and Iandola, Forrest and Srivastava, Rupesh K and Deng, Li and Doll{\'a}r, Piotr and Gao, Jianfeng and He, Xiaodong and Mitchell, Margaret and Platt, John C and others},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={1473--1482},
  year={2015}
}

@inproceedings{xu2015show,
   title="Show, Attend and Tell: Neural Image Caption Generation with Visual Attention",
   Author={Xu, Kelvin and Ba, Jimmy Lei and Kiros, Ryan and Cho, Kyunghyun and Courville, Aaronand and Salakhudinov, Ruslan and Zemel, Richard S and Bengio, Yoshua},
   year={2015},
   Booktitle={Proceedings of the International Conference on Machine Learning},
  month = {Jul.},
   pages={2048--2057}
}
@article{ferreira2007introduction,
  title={Introduction to the special issue on language--vision interactions},
  author={Ferreira, Fernanda and Tanenhaus, Michael K},
  journal={Journal of Memory and Language},
  volume={57},
  number={4},
  pages={455--459},
  year={2007},
  publisher={Elsevier}
}
@incollection{nuallain1994investigation,
  title={An investigation into the common semantics of language and vision},
  author={Nuallain, Sean O and Smith, Arnold G},
  booktitle={Integration of Natural Language and Vision Processing},
  pages={21--30},
  year={1994},
  publisher={Springer}
}
@article{rosch1976basic,
  title={Basic objects in natural categories},
  author={Rosch, Eleanor and Mervis, Carolyn B and Gray, Wayne D and Johnson, David M and Boyes-Braem, Penny},
  journal={Cognitive psychology},
  volume={8},
  number={3},
  pages={382--439},
  year={1976},
  publisher={Elsevier}
}
@inproceedings{vreeswijk2012all,
  title={All vehicles are cars: Subclass preferences in container concepts},
  author={Vreeswijk, Daan TJ and Snoek, Cees GM and van de Sande, Koen EA and Smeulders, Arnold WM},
  booktitle={Proceedings of the 2nd ACM International Conference on Multimedia Retrieval},
  pages={8},
  year={2012},
  organization={ACM}
}

@inproceedings{mettes2016imagenet,
  title={The imagenet shuffle: Reorganized pre-training for video event detection},
  author={Mettes, Pascal and Koelma, Dennis C and Snoek, Cees GM},
  booktitle={Proceedings of the ACM International Conference on Multimedia Retrieval},
  pages={175--182},
  year={2016},
  organization={ACM}
}

@inproceedings{deselaers2011visual,
  title={Visual and semantic similarity in imagenet},
  author={Deselaers, Thomas and Ferrari, Vittorio},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={1777--1784},
  year={2011},
  organization={IEEE}
}

@inproceedings{szegedy2015going,
  title={Going deeper with convolutions},
  author={Szegedy, Christian and Liu, Wei and Jia, Yangqing and Sermanet, Pierre and Reed, Scott and Anguelov, Dragomir and Erhan, Dumitru and Vanhoucke, Vincent and Rabinovich, Andre},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={1--9},
  month={Jun.},
  year={2015}
}

@inproceedings{bahdanau2014neural,
  title={Neural machine translation by jointly learning to align and translate},
  author={Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
  booktitle={Proceedings of the International Conference on Learning Representations},
  month={May.},
  year={2015}
}
@article{russakovsky2015imagenet,
  title={Imagenet large scale visual recognition challenge},
  author={Russakovsky, Olga and Deng, Jia and Su, Hao and Krause, Jonathan and Satheesh, Sanjeev and Ma, Sean and Huang, Zhiheng and Karpathy, Andrej and Khosla, Aditya and Bernstein, Michael and others},
  journal={International Journal of Computer Vision},
  volume={115},
  number={3},
  pages={211--252},
  year={2015},
  publisher={Springer}
}
@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={770--778},
  year={2016}
}
@inproceedings{krizhevsky2012imagenet,
  title={Imagenet classification with deep convolutional neural networks},
  author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
  booktitle={Proceedings of Advances in Neural Information Processing Systems},
  pages={1097--1105},
  year={2012}
}
@article{chen2015microsoft,
  title={Microsoft COCO captions: Data collection and evaluation server},
  author={Chen, Xinlei and Fang, Hao and Lin, Tsung-Yi and Vedantam, Ramakrishna and Gupta, Saurabh and Doll{\'a}r, Piotr and Zitnick, C Lawrence},
  journal={arXiv preprint arXiv:1504.00325},
  year={2015}
}
@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence},
  booktitle={Proceedings of the European Conference on Computer Vision},
  month = {Sept.},
  pages={740--755},
  year={2014}
}
@inproceedings{eiselt2013two,
  title={A Two-Step Named Entity Recognizer for Open-Domain Search Queries.},
  author={Eiselt, Andreas and Figueroa, Alejandro},
  booktitle={International Joint Conference on Natural Language Processing},
  pages={829--833},
  year={2013}
}
@inproceedings{vedantam2015cider,
  title={{CIDEr}: Consensus-based image description evaluation},
  author={Vedantam, Ramakrishna and Zitnick, C. Lawrence and Parikh, Devi},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  month = {Jun.},
  pages={4566--4575},
  year={2015}
}

@inproceedings{papineni2002bleu,
  title={{BLEU}: a method for automatic evaluation of machine translation},
  author={Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing},
  booktitle={Proceedings of the 40th Annual Meeting on Association for Computational Linguistics},
  month = {Jul.},
  pages={311--318},
  year={2002},
}

@article{banerjee2005meteor,
  title={The Meteor metric for automatic evaluation of machine translation},
  author={Lavie, Alon and Denkowski, Michael J.},
  journal={Machine Translation},
  volume={23},
  pages={105-115},
  month = {Sept.},
  year={2009}
}
@article{hodosh2013framing,
  title={Framing image description as a ranking task: Data, models and evaluation metrics},
  author={Hodosh, Micah and Young, Peter and Hockenmaier, Julia},
  journal={Journal Artificial Intelligence Research},
  volume={47},
  pages={853--899},
  month={Aug.},
  year={2013}
}
@inproceedings{kiros2014multimodal,
  title={Multimodal Neural Language Models},
  author={Kiros, Ryan and Salakhutdinov, Ruslan and Zemel, Richard S},
   Booktitle={Proceedings of the International Conference on Machine Learning},
  month = {Jun.},
  volume={14},
  pages={595--603},
  year={2014}
}
@inproceedings{donahue2015long,
  title={Long-term recurrent convolutional networks for visual recognition and description},
  author={Donahue, Jeffrey and Anne Hendricks, Lisa and Guadarrama, Sergio and Rohrbach, Marcus and Venugopalan, Subhashini and Saenko, Kate and Darrell, Trevor},
  booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
  pages={2625--2634},
  year={2015}
}
@inproceedings{mao2014deep,
  title={Deep captioning with multimodal recurrent neural networks (m-{RNN})},
  author={Mao, Junhua and Xu, Wei and Yang, Yi and Wang, Jiang and Huang, Zhiheng and Yuille, Alan},
  booktitle={Proceedings of the International Conference on Learning Representations},
  month = {Dec.},
  year={2015}
}
@inproceedings{jia2015guiding,
  title={Guiding the long-short term memory model for image caption generation},
  author={Jia, Xu and Gavves, Efstratios and Fernando, Basura and Tuytelaars, Tinne},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={2407--2415},
  year={2015}
}
@article{jin2015aligning,
  author={Jin, Junqi and Fu, Kun and Cui, Runpeng and Sha, Fei and Zhang, Changshui},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={Aligning Where to See and What to Tell: Image Captioning with Region-based Attention and Scene-specific Contexts}, 
  year={2016}, 
  volume={PP}, 
  number={99}, 
  pages={1-1}
}
@inproceedings{wu2016image,
  title={Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources},
  author={Wu, Qi and Shen, Chunhua and Hengel, Anton van den and Wang, Peng and Dick, Anthony},
  journal={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2016},
  month={June},
  pages={ 4622-4630}
}
@inproceedings{RefCap,
  author = {Ren, Zhou and Wang, Xiaoyu and Zhang, Ning and Lv, Xutao and Li, Li-Jia},
  booktitle = {Proceeding of IEEE conference on Computer Vision and Pattern Recognition},
  title = {Deep Reinforcement Learning-based Image Captioning with Embedding Reward},
  year = {2017},
  month={Jul.},
  pages={290-298}
}
@inproceedings{GLA,
  author = {Li, Linghui and Tang, Sheng and Deng, Lixi and Zhang, Yongdong and Tian, Qi},
  booktitle={Proceedings of Association for the Advancement of Artificial Intelligence Conference},
  title = {Image Caption with Global-Local Attention},
  year = {2017},
  month={Feb.},
  pages={4133-4139}
}
@inproceedings{vonAhn,
 author = {von Ahn, Luis and Dabbish, Laura},
 title = {Labeling Images with a Computer Game},
 booktitle = {Proceedings of the SIGCHI Conference on Human Factors in Computing Systems},
 year = {2004},
 pages = {319--326}
} 
@inproceedings{Cole2002PrinciplesOC,
  title={Principles of Categorization},
  author={Cole, Michael and Quinn, N. and  Rosch,Eleanor and  GIick,Joseph and  Sinclair,Hermina},
  booktitle = {Cognition and categorization},
  year={2002},
 pages = {189--206}
}
@article{Mareschal2000ACA,
  title={A connectionist account of asymmetric category learning in early infancy.},
  author={Denis Mareschal and Robert M. French and Paul C. Quinn},
  journal={Developmental psychology},
  year={2000},
  volume={365},
  pages={635-645}
}
@inproceedings{densecap,
  title={DenseCap: Fully Convolutional Localization Networks for Dense Captioning},
  author={Johnson, Justin and Karpathy, Andrej and Fei-Fei, Li},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and 
             Pattern Recognition},
  year={2016},
  month={Jul.},
  pages={4565-4574}
}
@inproceedings{finegained,
 author = {Jonathan Krause and Hailin Jin and Jianchao Yang and Li Fei-Fei},
 title = {Fine-Grained Recognition without Part Annotations},
 booktitle = "IEEE Conference on Computer Vision and Pattern Recognition",
 year = {2015},
 month = {June},
 pages={5546-5555}
}