PyTorch @misc{pytorch, title={Pytorch: Tensors and Dynamic neural networks in Python with strong GPU acceleration.} howpublished={\url{http://pytorch.org/}} note={Accessed: 2017-06-11} } ImageNet @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} } Adam @article{kingma2014adam, title={Adam: A method for stochastic optimization}, author={Kingma, Diederik and Ba, Jimmy}, journal={arXiv preprint arXiv:1412.6980}, year={2014} } AlexNet @inproceedings{krizhevsky2012imagenet, title={Imagenet classification with deep convolutional neural networks}, author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E}, booktitle={Advances in neural information processing systems}, pages={1097--1105}, year={2012} } VGGNet @article{simonyan2014very, title={Very deep convolutional networks for large-scale image recognition}, author={Simonyan, Karen and Zisserman, Andrew}, year={2014} } ZFNet @inproceedings{zeiler2014visualizing, title={Visualizing and understanding convolutional networks}, author={Zeiler, Matthew D and Fergus, Rob}, booktitle={European conference on computer vision}, pages={818--833}, year={2014}, organization={Springer} } ResNet @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} } Region proposals: Selective search @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} } Region proposals: EdgeBoxes @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} } SPP Spatial Pyramid Pooling @inproceedings{he2014spatial, title={Spatial pyramid pooling in deep convolutional networks for visual recognition}, author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian}, booktitle={European Conference on Computer Vision}, pages={346--361}, year={2014}, organization={Springer} } Show Attend and Tell @inproceedings{xu2015show, title={Show, attend and tell: Neural image caption generation with visual attention}, author={Xu, Kelvin and Ba, Jimmy and Kiros, Ryan and Cho, Kyunghyun and Courville, Aaron and Salakhudinov, Ruslan and Zemel, Rich and Bengio, Yoshua}, booktitle={International Conference on Machine Learning}, pages={2048--2057}, year={2015} } Fast R-CNN @inproceedings{girshick2015fast, title={Fast r-cnn}, author={Girshick, Ross}, booktitle={Proceedings of the IEEE International Conference on Computer Vision}, pages={1440--1448}, year={2015} } Faster R-CNN @inproceedings{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}, booktitle={Advances in neural information processing systems}, pages={91--99}, year={2015} } Weakly supervised: Is object localization for free? @inproceedings{oquab2015object, title={Is object localization for free?-weakly-supervised learning with convolutional neural networks}, author={Oquab, Maxime and Bottou, L{\'e}on and Laptev, Ivan and Sivic, Josef}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={685--694}, year={2015} } Weakly supervised: Transfer learning @article{shitransfer, title={Transfer Learning by Ranking for Weakly Supervised Object Annotation}, author={Shi, Zhiyuan and Siva, Parthipan and Xiang, Tao} } Results on weakly-supervised bounding @inproceedings{papadopoulos2016we, title={We don't need no bounding-boxes: Training object class detectors using only human verification}, author={Papadopoulos, Dim P and Uijlings, Jasper RR and Keller, Frank and Ferrari, Vittorio}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={854--863}, year={2016} } @article{luong2015effective, title={Effective approaches to attention-based neural machine translation}, author={Luong, Minh-Thang and Pham, Hieu and Manning, Christopher D}, journal={Empirical Methods in Natural Language Processing}, year={2015} } @inproceedings{chorowski2015attention, title={Attention-based models for speech recognition}, author={Chorowski, Jan K and Bahdanau, Dzmitry and Serdyuk, Dmitriy and Cho, Kyunghyun and Bengio, Yoshua}, booktitle={Advances in Neural Information Processing Systems}, pages={577--585}, year={2015} } PhdThesis{Gal2016Uncertainty, title={Uncertainty in Deep Learning}, author={Gal, Yarin}, year={2016}, school={University of Cambridge} } @article{ba2multiple, title={MULTIPLE OBJECT RECOGNITION WITH VISUAL ATTENTION}, author={Ba, Jimmy Lei and Mnih, Volodymyr and Kavukcuoglu, Koray}, journal={context}, volume={2}, number={l3}, pages={l4} } @inproceedings{mnih2014recurrent, title={Recurrent models of visual attention}, author={Mnih, Volodymyr and Heess, Nicolas and Graves, Alex and others}, booktitle={Advances in neural information processing systems}, pages={2204--2212}, year={2014} } @inproceedings{teh2016attention, title={Attention networks for weakly supervised object localization}, author={Teh, Eu Wern and Rochan, Mrigank and Wang, Yang} }