references.bib

@inproceedings{akbari2019multi,
  title     = {Multi-level multimodal common semantic space for image-phrase grounding},
  author    = {Akbari, Hassan and Karaman, Svebor and Bhargava, Surabhi and Chen, Brian and Vondrick, Carl and Chang, Shih-Fu},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages     = {12476--12486},
  year      = {2019}
}

@inproceedings{akbik2019flair,
  title     = {FLAIR: An easy-to-use framework for state-of-the-art NLP},
  author    = {Akbik, Alan and Bergmann, Tanja and Blythe, Duncan and Rasul, Kashif and Schweter, Stefan and Vollgraf, Roland},
  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)},
  pages     = {54--59},
  year      = {2019}
}

@inproceedings{anderson2018bottom,
  title     = {Bottom-up and top-down attention for image captioning and visual question answering},
  author    = {Anderson, Peter and He, Xiaodong and Buehler, Chris and Teney, Damien and Johnson, Mark and Gould, Stephen and Zhang, Lei},
  booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages     = {6077--6086},
  year      = {2018}
}

@article{arbelle2021detector,
  title   = {Detector-Free Weakly Supervised Grounding by Separation},
  author  = {Arbelle, Assaf and Doveh, Sivan and Alfassy, Amit and Shtok, Joseph and Lev, Guy and Schwartz, Eli and Kuehne, Hilde and Levi, Hila Barak and Sattigeri, Prasanna and Panda, Rameswar and others},
  journal = {arXiv preprint arXiv:2104.09829},
  year    = {2021}
}

@inproceedings{chen2018knowledge,
  title     = {Knowledge aided consistency for weakly supervised phrase grounding},
  author    = {Chen, Kan and Gao, Jiyang and Nevatia, Ram},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages     = {4042--4050},
  year      = {2018}
}

@article{conser2019revisiting,
  title   = {Revisiting Visual Grounding},
  author  = {Conser, Erik and Hahn, Kennedy and Watson, Chandler M and Mitchell, Melanie},
  journal = {arXiv preprint arXiv:1904.02225},
  year    = {2019}
}

@inproceedings{cunningham2002gate,
  title     = {GATE: an architecture for development of robust HLT applications},
  author    = {Cunningham, Hamish and Maynard, Diana and Bontcheva, Kalina and Tablan, Valentin},
  booktitle = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics},
  pages     = {168--175},
  year      = {2002}
}

@inproceedings{datta2019align2ground,
  title     = {Align2ground: Weakly supervised phrase grounding guided by image-caption alignment},
  author    = {Datta, Samyak and Sikka, Karan and Roy, Anirban and Ahuja, Karuna and Parikh, Devi and Divakaran, Ajay},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages     = {2601--2610},
  year      = {2019}
}

@inproceedings{de2006generating,
  title     = {Generating typed dependency parses from phrase structure parses.},
  author    = {De Marneffe, Marie-Catherine and MacCartney, Bill and Manning, Christopher D and others},
  booktitle = {Lrec},
  volume    = {6},
  pages     = {449--454},
  year      = {2006}
}

@inproceedings{de2008stanford,
  title     = {The Stanford typed dependencies representation},
  author    = {De Marneffe, Marie-Catherine and Manning, Christopher D},
  booktitle = {Coling 2008: proceedings of the workshop on cross-framework and cross-domain parser evaluation},
  pages     = {1--8},
  year      = {2008}
}

@article{deerwester1990indexing,
  title     = {Indexing by latent semantic analysis},
  author    = {Deerwester, Scott and Dumais, Susan T and Furnas, George W and Landauer, Thomas K and Harshman, Richard},
  journal   = {Journal of the American society for information science},
  volume    = {41},
  number    = {6},
  pages     = {391--407},
  year      = {1990},
  publisher = {Wiley Online Library}
}

@article{devlin2018bert,
  title   = {Bert: Pre-training of deep bidirectional transformers for language understanding},
  author  = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  journal = {arXiv preprint arXiv:1810.04805},
  year    = {2018}
}

@inproceedings{dost2020jointly,
  title        = {Jointly Linking Visual and Textual Entity Mentions with Background Knowledge},
  author       = {Dost, Shahi and Serafini, Luciano and Rospocher, Marco and Ballan, Lamberto and Sperduti, Alessandro},
  booktitle    = {International Conference on Applications of Natural Language to Information Systems},
  pages        = {264--276},
  year         = {2020},
  organization = {Springer}
}

@inproceedings{dost2020visual,
  title        = {On Visual-Textual-Knowledge Entity Linking},
  author       = {Dost, Shahi and Serafini, Luciano and Rospocher, Marco and Ballan, Lamberto and Sperduti, Alessandro},
  booktitle    = {2020 IEEE 14th International Conference on Semantic Computing (ICSC)},
  pages        = {190--193},
  year         = {2020},
  organization = {IEEE}
}

@inproceedings{dost2020vtkel,
  title     = {VTKEL: a resource for visual-textual-knowledge entity linking},
  author    = {Dost, Shahi and Serafini, Luciano and Rospocher, Marco and Ballan, Lamberto and Sperduti, Alessandro},
  booktitle = {Proceedings of the 35th Annual ACM Symposium on Applied Computing},
  pages     = {2021--2028},
  year      = {2020}
}

@article{ferrucci2004uima,
  title     = {UIMA: an architectural approach to unstructured information processing in the corporate research environment},
  author    = {Ferrucci, David and Lally, Adam},
  journal   = {Natural Language Engineering},
  volume    = {10},
  number    = {3-4},
  pages     = {327--348},
  year      = {2004},
  publisher = {Cambridge University Press}
}

@inproceedings{fidler2013sentence,
  title     = {A sentence is worth a thousand pixels},
  author    = {Fidler, Sanja and Sharma, Abhishek and Urtasun, Raquel},
  booktitle = {Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
  pages     = {1995--2002},
  year      = {2013}
}

@inproceedings{girshick2014rich,
  title     = {Rich feature hierarchies for accurate object detection and semantic segmentation},
  author    = {Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra},
  booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages     = {580--587},
  year      = {2014}
}

@inproceedings{girshick2015fast,
  title     = {Fast r-cnn},
  author    = {Girshick, Ross},
  booktitle = {Proceedings of the IEEE international conference on computer vision},
  pages     = {1440--1448},
  year      = {2015}
}

@inproceedings{glorot2010understanding,
  title        = {Understanding the difficulty of training deep feedforward neural networks},
  author       = {Glorot, Xavier and Bengio, Yoshua},
  booktitle    = {Proceedings of the thirteenth international conference on artificial intelligence and statistics},
  pages        = {249--256},
  year         = {2010},
  organization = {JMLR Workshop and Conference Proceedings}
}

@book{goodfellow2016deep,
  title     = {Deep learning},
  author    = {Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron},
  year      = {2016},
  publisher = {MIT press}
}

@inproceedings{gordo2016deep,
  title        = {Deep image retrieval: Learning global representations for image search},
  author       = {Gordo, Albert and Almaz{\'a}n, Jon and Revaud, Jerome and Larlus, Diane},
  booktitle    = {European conference on computer vision},
  pages        = {241--257},
  year         = {2016},
  organization = {Springer}
}

@inproceedings{gupta2020contrastive,
  title        = {Contrastive learning for weakly supervised phrase grounding},
  author       = {Gupta, Tanmay and Vahdat, Arash and Chechik, Gal and Yang, Xiaodong and Kautz, Jan and Hoiem, Derek},
  booktitle    = {Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part III 16},
  pages        = {752--768},
  year         = {2020},
  organization = {Springer}
}

@online{gupta2020differences,
  author  = {Lavanya Gupta},
  title   = {Differences Between Word2Vec and BERT},
  year    = 2020,
  url     = {https://medium.com/swlh/differences-between-word2vec-and-bert-c08a3326b5d1},
  urldate = {2020-11-12}
}

@online{honnibal2020spacy,
  author  = {Honnibal, Matthew and Montani, Ines and Van Landeghem, Sofie and Boyd, Adriane},
  title   = {spaCy: Industrial-strength Natural Language Processing in Python},
  year    = 2020,
  url     = {https://spacy.io/},
  urldate = {2020-01-01}
}

@inproceedings{hu2016natural,
  title     = {Natural language object retrieval},
  author    = {Hu, Ronghang and Xu, Huazhe and Rohrbach, Marcus and Feng, Jiashi and Saenko, Kate and Darrell, Trevor},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages     = {4555--4564},
  year      = {2016}
}

@article{jaccard1901comparative,
  title   = {Comparative study of the floral distribution in a portion of the Alps and Jura},
  author  = {Jaccard, Paul},
  journal = {The Company Vaudoise Bulletin of Natural Sciences},
  volume  = {37},
  number  = {5},
  pages   = {547--579},
  year    = {1901}
}

@article{jaderberg2015spatial,
  title   = {Spatial transformer networks},
  author  = {Jaderberg, Max and Simonyan, Karen and Zisserman, Andrew and others},
  journal = {Advances in neural information processing systems},
  volume  = {28},
  pages   = {2017--2025},
  year    = {2015}
}

@article{javed2018learning,
  title   = {Learning unsupervised visual grounding through semantic self-supervision},
  author  = {Javed, Syed Ashar and Saxena, Shreyas and Gandhi, Vineet},
  journal = {arXiv preprint arXiv:1803.06506},
  year    = {2018}
}

@article{kafle2017visual,
  title     = {Visual question answering: Datasets, algorithms, and future challenges},
  author    = {Kafle, Kushal and Kanan, Christopher},
  journal   = {Computer Vision and Image Understanding},
  volume    = {163},
  pages     = {3--20},
  year      = {2017},
  publisher = {Elsevier}
}

@inproceedings{kazemzadeh2014referitgame,
  title     = {Referitgame: Referring to objects in photographs of natural scenes},
  author    = {Kazemzadeh, Sahar and Ordonez, Vicente and Matten, Mark and Berg, Tamara},
  booktitle = {Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)},
  pages     = {787--798},
  year      = {2014}
}

@inproceedings{kong2014you,
  title     = {What are you talking about? text-to-image coreference},
  author    = {Kong, Chen and Lin, Dahua and Bansal, Mohit and Urtasun, Raquel and Fidler, Sanja},
  booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages     = {3558--3565},
  year      = {2014}
}

@article{kotsiantis2006data,
  title     = {Data preprocessing for supervised leaning},
  author    = {Kotsiantis, Sotiris B and Kanellopoulos, Dimitris and Pintelas, Panagiotis E},
  journal   = {International journal of computer science},
  volume    = {1},
  number    = {2},
  pages     = {111--117},
  year      = {2006},
  publisher = {Citeseer}
}

@article{krishna2017visual,
  title     = {Visual genome: Connecting language and vision using crowdsourced dense image annotations},
  author    = {Krishna, Ranjay and Zhu, Yuke and Groth, Oliver and Johnson, Justin and Hata, Kenji and Kravitz, Joshua and Chen, Stephanie and Kalantidis, Yannis and Li, Li-Jia and Shamma, David A and others},
  journal   = {International journal of computer vision},
  volume    = {123},
  number    = {1},
  pages     = {32--73},
  year      = {2017},
  publisher = {Springer}
}

@inproceedings{lin2012syntactic,
  title     = {Syntactic annotations for the google books ngram corpus},
  author    = {Lin, Yuri and Michel, Jean-Baptiste and Lieberman, Erez Aiden and Orwant, Jon and Brockman, Will and Petrov, Slav},
  booktitle = {Proceedings of the ACL 2012 system demonstrations},
  pages     = {169--174},
  year      = {2012}
}

@inproceedings{liu2016ssd,
  title        = {Ssd: Single shot multibox detector},
  author       = {Liu, Wei and Anguelov, Dragomir and Erhan, Dumitru and Szegedy, Christian and Reed, Scott and Fu, Cheng-Yang and Berg, Alexander C},
  booktitle    = {European conference on computer vision},
  pages        = {21--37},
  year         = {2016},
  organization = {Springer}
}

@inproceedings{liu2019adaptive,
  title     = {Adaptive reconstruction network for weakly supervised referring expression grounding},
  author    = {Liu, Xuejing and Li, Liang and Wang, Shuhui and Zha, Zheng-Jun and Meng, Dechao and Huang, Qingming},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages     = {2611--2620},
  year      = {2019}
}

@inproceedings{manning2014stanford,
  title     = {The Stanford CoreNLP natural language processing toolkit},
  author    = {Manning, Christopher D and Surdeanu, Mihai and Bauer, John and Finkel, Jenny Rose and Bethard, Steven and McClosky, David},
  booktitle = {Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations},
  pages     = {55--60},
  year      = {2014}
}

@article{marcus1993building,
  title  = {Building a large annotated corpus of English: The Penn Treebank},
  author = {Marcus, Mitchell and Santorini, Beatrice and Marcinkiewicz, Mary Ann},
  year   = {1993}
}

@article{marquez2000machine,
  title     = {A machine learning approach to POS tagging},
  author    = {Marquez, Lluis and Padro, Lluis and Rodriguez, Horacio},
  journal   = {Machine Learning},
  volume    = {39},
  number    = {1},
  pages     = {59--91},
  year      = {2000},
  publisher = {Springer}
}

@inproceedings{mikolov2013distributed,
  title     = {Distributed representations of words and phrases and their compositionality},
  author    = {Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and Corrado, Greg S and Dean, Jeff},
  booktitle = {Advances in neural information processing systems},
  pages     = {3111--3119},
  year      = {2013}
}

@article{mikolov2013efficient,
  title   = {Efficient estimation of word representations in vector space},
  author  = {Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey},
  journal = {arXiv preprint arXiv:1301.3781},
  year    = {2013}
}

@article{mikolov2013exploiting,
  title   = {Exploiting similarities among languages for machine translation},
  author  = {Mikolov, Tomas and Le, Quoc V and Sutskever, Ilya},
  journal = {arXiv preprint arXiv:1309.4168},
  year    = {2013}
}

@inproceedings{mikolov2013linguistic,
  title     = {Linguistic regularities in continuous space word representations},
  author    = {Mikolov, Tom{\'a}{\v{s}} and Yih, Wen-tau and Zweig, Geoffrey},
  booktitle = {Proceedings of the 2013 conference of the north american chapter of the association for computational linguistics: Human language technologies},
  pages     = {746--751},
  year      = {2013}
}

@inproceedings{nivre2016universal,
  title     = {Universal dependencies v1: A multilingual treebank collection},
  author    = {Nivre, Joakim and De Marneffe, Marie-Catherine and Ginter, Filip and Goldberg, Yoav and Hajic, Jan and Manning, Christopher D and McDonald, Ryan and Petrov, Slav and Pyysalo, Sampo and Silveira, Natalia and others},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)},
  pages     = {1659--1666},
  year      = {2016}
}

@article{nivre2017universal,
  title  = {Universal Dependencies 2.1},
  author = {Nivre, Joakim and Agi{\'c}, {\v{Z}}eljko and Ahrenberg, Lars and Antonsen, Lene and Aranzabe, Maria Jesus and Asahara, Masayuki and Ateyah, Luma and Attia, Mohammed and Atutxa, Aitziber and Augustinus, Liesbeth and others},
  year   = {2017}
}

@inproceedings{padilla2020survey,
  title        = {A survey on performance metrics for object-detection algorithms},
  author       = {Padilla, Rafael and Netto, Sergio L and da Silva, Eduardo AB},
  booktitle    = {2020 International Conference on Systems, Signals and Image Processing (IWSSIP)},
  pages        = {237--242},
  year         = {2020},
  organization = {IEEE}
}

@inproceedings{pennington2014glove,
  title     = {Glove: Global vectors for word representation},
  author    = {Pennington, Jeffrey and Socher, Richard and Manning, Christopher D},
  booktitle = {Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)},
  pages     = {1532--1543},
  year      = {2014}
}

@article{petsiuk2018rise,
  title   = {Rise: Randomized input sampling for explanation of black-box models},
  author  = {Petsiuk, Vitali and Das, Abir and Saenko, Kate},
  journal = {arXiv preprint arXiv:1806.07421},
  year    = {2018}
}

@inproceedings{plummer2015flickr30k,
  title     = {Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models},
  author    = {Plummer, Bryan A and Wang, Liwei and Cervantes, Chris M and Caicedo, Juan C and Hockenmaier, Julia and Lazebnik, Svetlana},
  booktitle = {Proceedings of the IEEE international conference on computer vision},
  pages     = {2641--2649},
  year      = {2015}
}

@article{qi2020stanza,
  title   = {Stanza: A Python natural language processing toolkit for many human languages},
  author  = {Qi, Peng and Zhang, Yuhao and Zhang, Yuhui and Bolton, Jason and Manning, Christopher D},
  journal = {arXiv preprint arXiv:2003.07082},
  year    = {2020}
}

@inproceedings{radenovic2016cnn,
  title        = {CNN image retrieval learns from BoW: Unsupervised fine-tuning with hard examples},
  author       = {Radenovi{\'c}, Filip and Tolias, Giorgos and Chum, Ond{\v{r}}ej},
  booktitle    = {European conference on computer vision},
  pages        = {3--20},
  year         = {2016},
  organization = {Springer}
}

@inproceedings{ramanishka2017top,
  title     = {Top-down visual saliency guided by captions},
  author    = {Ramanishka, Vasili and Das, Abir and Zhang, Jianming and Saenko, Kate},
  booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages     = {7206--7215},
  year      = {2017}
}

@inproceedings{redmon2016you,
  title     = {You only look once: Unified, real-time object detection},
  author    = {Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali},
  booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages     = {779--788},
  year      = {2016}
}

@article{ren2015faster,
  title   = {Faster r-cnn: Towards real-time object detection with region proposal networks},
  author  = {Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian},
  journal = {Advances in neural information processing systems},
  volume  = {28},
  pages   = {91--99},
  year    = {2015}
}

@article{rigoni2021better,
  title   = {A Better Loss for Visual-Textual Grounding},
  author  = {Rigoni, Davide and Serafini, Luciano and Sperduti, Alessandro},
  journal = {arXiv preprint arXiv:2108.05308},
  year    = {2021}
}

@inproceedings{rohrbach2016grounding,
  title        = {Grounding of textual phrases in images by reconstruction},
  author       = {Rohrbach, Anna and Rohrbach, Marcus and Hu, Ronghang and Darrell, Trevor and Schiele, Bernt},
  booktitle    = {European Conference on Computer Vision},
  pages        = {817--834},
  year         = {2016},
  organization = {Springer}
}

@inproceedings{sadhu2019zero,
  title     = {Zero-shot grounding of objects from natural language queries},
  author    = {Sadhu, Arka and Chen, Kan and Nevatia, Ram},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages     = {4694--4703},
  year      = {2019}
}

@article{sanderson2010christopher,
  title     = {Christopher D. Manning, Prabhakar Raghavan, Hinrich Sch{\"u}tze, Introduction to Information Retrieval, Cambridge University Press. 2008. ISBN-13 978-0-521-86571-5, xxi+ 482 pages.},
  author    = {Sanderson, Mark},
  journal   = {Natural Language Engineering},
  volume    = {16},
  number    = {1},
  pages     = {100--103},
  year      = {2010},
  publisher = {cambridge university press}
}

@inproceedings{schmitt2019replicable,
  title        = {A replicable comparison study of NER software: StanfordNLP, NLTK, OpenNLP, SpaCy, Gate},
  author       = {Schmitt, Xavier and Kubler, Sylvain and Robert, J{\'e}r{\'e}my and Papadakis, Mike and LeTraon, Yves},
  booktitle    = {2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS)},
  pages        = {338--343},
  year         = {2019},
  organization = {IEEE}
}

@article{sebastiani2002machine,
  title     = {Machine learning in automated text categorization},
  author    = {Sebastiani, Fabrizio},
  journal   = {ACM computing surveys (CSUR)},
  volume    = {34},
  number    = {1},
  pages     = {1--47},
  year      = {2002},
  publisher = {ACM New York, NY, USA}
}

@online{sharma2020understanding,
  author  = {Himanshu Sharma},
  title   = {Understanding Data Analysis Step-By-Step},
  year    = 2020,
  url     = {https://towardsdatascience.com/understanding-data-analysis-step-by-step-48e604cb882},
  urldate = {2020-06-25}
}

@inproceedings{silveira2014gold,
  title        = {A Gold Standard Dependency Corpus for English.},
  author       = {Silveira, Natalia and Dozat, Timothy and De Marneffe, Marie-Catherine and Bowman, Samuel R and Connor, Miriam and Bauer, John and Manning, Christopher D},
  booktitle    = {LREC},
  pages        = {2897--2904},
  year         = {2014},
  organization = {Citeseer}
}

@inproceedings{socher2013parsing,
  title     = {Parsing with compositional vector grammars},
  author    = {Socher, Richard and Bauer, John and Manning, Christopher D and Ng, Andrew Y},
  booktitle = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages     = {455--465},
  year      = {2013}
}

@inproceedings{straka2018udpipe,
  title     = {UDPipe 2.0 prototype at CoNLL 2018 UD shared task},
  author    = {Straka, Milan},
  booktitle = {Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies},
  pages     = {197--207},
  year      = {2018}
}

@inproceedings{tellex2003quantitative,
  title     = {Quantitative evaluation of passage retrieval algorithms for question answering},
  author    = {Tellex, Stefanie and Katz, Boris and Lin, Jimmy and Fernandes, Aaron and Marton, Gregory},
  booktitle = {Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval},
  pages     = {41--47},
  year      = {2003}
}

@inproceedings{thomason2017guiding,
  title     = {Guiding interaction behaviors for multi-modal grounded language learning},
  author    = {Thomason, Jesse and Sinapov, Jivko and Mooney, Raymond},
  booktitle = {Proceedings of the First Workshop on Language Grounding for Robotics},
  pages     = {20--24},
  year      = {2017}
}

@inproceedings{turian2010word,
  title     = {Word representations: a simple and general method for semi-supervised learning},
  author    = {Turian, Joseph and Ratinov, Lev and Bengio, Yoshua},
  booktitle = {Proceedings of the 48th annual meeting of the association for computational linguistics},
  pages     = {384--394},
  year      = {2010}
}

@article{uijlings2013selective,
  title     = {Selective search for object recognition},
  author    = {Uijlings, Jasper RR and Van De Sande, Koen EA and Gevers, Theo and Smeulders, Arnold WM},
  journal   = {International journal of computer vision},
  volume    = {104},
  number    = {2},
  pages     = {154--171},
  year      = {2013},
  publisher = {Springer}
}

@inproceedings{wang2016learning,
  title     = {Learning deep structure-preserving image-text embeddings},
  author    = {Wang, Liwei and Li, Yin and Lazebnik, Svetlana},
  booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages     = {5005--5013},
  year      = {2016}
}

@inproceedings{wang2019phrase,
  title     = {Phrase localization without paired training examples},
  author    = {Wang, Josiah and Specia, Lucia},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages     = {4663--4672},
  year      = {2019}
}

@article{wang2020maf,
  title   = {Maf: Multimodal alignment framework for weakly-supervised phrase grounding},
  author  = {Wang, Qinxin and Tan, Hao and Shen, Sheng and Mahoney, Michael W and Yao, Zhewei},
  journal = {arXiv preprint arXiv:2010.05379},
  year    = {2020}
}

@inproceedings{xiao2017weakly,
  title     = {Weakly-supervised visual grounding of phrases with linguistic structures},
  author    = {Xiao, Fanyi and Sigal, Leonid and Jae Lee, Yong},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages     = {5945--5954},
  year      = {2017}
}

@inproceedings{yang2019fast,
  title     = {A fast and accurate one-stage approach to visual grounding},
  author    = {Yang, Zhengyuan and Gong, Boqing and Wang, Liwei and Huang, Wenbing and Yu, Dong and Luo, Jiebo},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages     = {4683--4693},
  year      = {2019}
}

@article{young2014image,
  title     = {From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions},
  author    = {Young, Peter and Lai, Alice and Hodosh, Micah and Hockenmaier, Julia},
  journal   = {Transactions of the Association for Computational Linguistics},
  volume    = {2},
  pages     = {67--78},
  year      = {2014},
  publisher = {MIT Press}
}

@article{yu2018rethinking,
  title   = {Rethinking diversified and discriminative proposal generation for visual grounding},
  author  = {Yu, Zhou and Yu, Jun and Xiang, Chenchao and Zhao, Zhou and Tian, Qi and Tao, Dacheng},
  journal = {arXiv preprint arXiv:1805.03508},
  year    = {2018}
}

@inproceedings{zeman2008reusable,
  title     = {Reusable Tagset Conversion Using Tagset Drivers.},
  author    = {Zeman, Daniel},
  booktitle = {LREC},
  volume    = {2008},
  pages     = {28--30},
  year      = {2008}
}

@inproceedings{zhang2018grounding,
  title     = {Grounding referring expressions in images by variational context},
  author    = {Zhang, Hanwang and Niu, Yulei and Chang, Shih-Fu},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages     = {4158--4166},
  year      = {2018}
}

@article{zhang2018top,
  title     = {Top-down neural attention by excitation backprop},
  author    = {Zhang, Jianming and Bargal, Sarah Adel and Lin, Zhe and Brandt, Jonathan and Shen, Xiaohui and Sclaroff, Stan},
  journal   = {International Journal of Computer Vision},
  volume    = {126},
  number    = {10},
  pages     = {1084--1102},
  year      = {2018},
  publisher = {Springer}
}

@inproceedings{zhao2018weakly,
  title     = {Weakly supervised phrase localization with multi-scale anchored transformer network},
  author    = {Zhao, Fang and Li, Jianshu and Zhao, Jian and Feng, Jiashi},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages     = {5696--5705},
  year      = {2018}
}

@article{zhou2018brief,
  title     = {A brief introduction to weakly supervised learning},
  author    = {Zhou, Zhi-Hua},
  journal   = {National science review},
  volume    = {5},
  number    = {1},
  pages     = {44--53},
  year      = {2018},
  publisher = {Oxford University Press}
}

@inproceedings{zitnick2014edge,
  title        = {Edge boxes: Locating object proposals from edges},
  author       = {Zitnick, C Lawrence and Doll{\'a}r, Piotr},
  booktitle    = {European conference on computer vision},
  pages        = {391--405},
  year         = {2014},
  organization = {Springer}
}