% article % author % title % journal % volume % number % pages % year % inproceedings % author % title % booktitle % pages % year % arxiv % author % title % journal % volume % year % years @string{accepted = {accepted}} % schools @string{mit = {MIT}} % journals @string{aireview = {Artificial Intelligence Review}} @string{cognition = {Cognition}} @string{cviu = {Computer Vision and Image Understanding (CVIU)}} @string{jair = {Journal of Artificial Intelligence Research (JAIR)}} @string{tpami = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)}} @string{aij = {Artificial Intelligence (AIJ)}} @string{tip = {IEEE Transactions on Image Processing (TIP)}} @string{toplas = {ACM Transactions on Programming Languages and Systems (TOPLAS)}} @string{hosc = {Higher-Order and Symbolic Computation (HOSC)}} @string{acs = {Advances in Cognitive Systems (ACS)}} @string{tcsvt = {IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)}} @string{mvap = {Machine Vision and Applications (MVAP)}} @string{tnnls = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)}} @string{ijcv = {International Journal of Computer Vision (IJCV)}} @string{jmlr = {Journal of Machine Learning Research (JMLR)}} @string{oms = {Optimization Methods \& Software (OMS)}} % conferences @string{arv = {Conference on Advanced Research in VLSI}} @string{acl = {Annual Meeting of the Association for Computational Linguistics (ACL)}} @string{aaai = {Conference on Artificial Intelligence (AAAI)}} @string{eccv = {European Conference on Computer Vision (ECCV)}} @string{iccv = {International Conference on Computer Vision (ICCV)}} @string{icassp = {International Conference on Acoustics, Speech, and Signal Processing (ICASSP)}} @string{icip = {International Conference on Image Processing (ICIP)}} @string{nips = {Advances in Neural Information Processing Systems (NeurIPS)}} @string{popl = {Annual Symposium on Principles of Programming Languages (POPL)}} @string{ad = {International Conference on Automatic Differentiation (AD)}} @string{icra = {International Conference on Robotics and Automation (ICRA)}} @string{cvpr = {Computer Vision and Pattern Recognition (CVPR)}} @string{uai = {Conference on Uncertainty in Artificial Intelligence (UAI)}} @string{acsconf = {Annual Conference for Advances in Cognitive Systems (ACS)}} @string{icml = {International Conference on Machine Learning (ICML)}}} @string{iclr = {International Conference on Learning Representations (ICLR)}}} @string{accv = {Asian Conference on Computer Vision (ACCV)}}} % publishers @string{oup = {Oxford University Press}} @string{cascadilla = {Cascadilla Press}} % workshops @string{mlnlo = {AAAI Spring Symposium Workshop on Machine Learning of Natural Language and Ontology}} @string{cuny = {CUNY Sentence Processing Conference}} @string{spie = {Annual Conference of the Society of Photo-Optical Instrumentation Engineers (SPIE)}} @string{inlvp = {AAAI Workshop on Integration of Natural Language and Vision Processing}} @string{bucld = {Boston University Conference on Language Development}} @string{lcbais = {AAAI Fall Symposium Workshop on Learning Complex Behaviors in Adaptive Intelligent Systems}} @string{necrs = {NEC Research Symposium}} @string{ei = {IS{\&}T/SPIE Annual Symposium on Electronic Imaging}} @string{ssp = {IEEE Workshop on Statistical Signal Processing}} @string{is = {SIAM Conference on Imaging Science}} @string{ifl = {International Workshop on Implementation and Application of Functional Languages (IFL)}} @string{fpic = {Computer Vision and Pattern Recognition Workshop on Vision Meets Cognition (CVPR Workshop)}} % institutions @string{mitai = {Artificial Intelligence Laboratory, MIT}} @string{ircs = {Institute for Research in Cognitive Science, University of Pennsylvania}} @string{neci = {NEC Research Institute, Inc.}} @string{ece = {School of Electrical and Computer Engineering, Purdue University}} @string{arxiv = {arXiv}} @article{baydin2018, author = {A. G. Baydin and B. A. Pearlmutter and A. A. Radul and J. M. Siskind}, title = {Automatic Differentiation in Machine Learning: a Survey}, journal = jmlr, volume = 18, number = 153, pages = {1-43}, year = 2018} @article{siskind2008, author = {J. M. Siskind and B. A. Pearlmutter}, title = {Nesting forward-mode {AD} in a functional framework}, journal = hosc, volume = 21, number = 4, pages = {361-376}, year = 2008} @article{pearlmutter2008, author = {B. A. Pearlmutter and J. M. Siskind}, title = {Reverse-Mode {AD} in a Functional Framework: Lambda the Ultimate Backpropagator}, journal = toplas, volume = 30, number = 2, pages = {1-36}, year = 2008} @article{lowe1987, author = {David G. Lowe}, title = {Three-Dimensional Object Recognition from Single Two-Dimensional Images}, journal = aij, volume = 31, number = 3, pages = {355-395}, year = 1987} @article{dementhon1995, author = {Daniel F. Dementhon and Larry S. Davis}, title = {Model-Based Object Pose in 25 Lines of Code}, journal = ijcv, volume = 15, number = {1--2}, pages = {123-141}, year = 1995} @inproceedings{dalal2005, author = {Naveet Dalal and Bill Triggs}, title = {Histograms of Oriented Gradients for Human Detection}, booktitle = cvpr, pages = {886-893}, year = 2005} @article{felzenszwalb2010, author = {Pedro F. Felzenszwalb and Ross B. Girshick and David McAllester and Deva Ramanan}, title = {Object Detection with Discriminatively Trained Part-Based Models}, journal = tpami, volume = 32, number = 9, pages = {1627-1645}, year = 2010} @inproceedings{krizhevsky2012, author = {Alex Krizhevsky and Ilya Sutskever and Geoffrey E. Hinton}, title = {Image{N}et Classification with Deep Convolutional Neural Networks}, booktitle = nips, pages = {1097-1105}, year = 2012} @inproceedings{simonyan2015, author = {Karen Simonyan and Andrew Zisserman}, title = {Very Deep Convolutional Networks for Large-Scale Image Recognition}, booktitle = iclr, numpages = 14, year = 2015} @inproceedings{szegedy2015, 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, Andrew}, title = {Going deeper with convolutions}, booktitle = cvpr, numpages = 9, year = 2015} @inproceedings{ioffe2015, author = {Sergey Ioffe and Cristian Szegedy}, title = {Batch normalization: accelerating deep network training by reducing internal covariate shift}, booktitle = icml, pages = {448-456}, year = 2015} @inproceedings{he2016, author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun}, title = {Deep Residual Learning for Image Recognition}, booktitle = cvpr, pages = {770-778}, year = 2016} @inproceedings{szegedy2016, author = {Szegedy, Christian and Vanhoucke, Vincent and Ioffe, Sergey and Shlens, Jon and Wojna, Zbigniew}, title = {Rethinking the {Inception} architecture for computer vision}, booktitle = cvpr, pages = {2818-2826}, year = 2016} @inproceedings{szegedy2017, author = {Szegedy, Christian and Ioffe, Sergey and Vanhoucke, Vincent and Alemi, Alexander A.}, title = {Inception-v4, {Inception}-{ResNet} and the Impact of Residual Connections on Learning}, booktitle = aaai, pages = {4278-4284}, year = 2017} @inproceedings{huang2017, author = {Huang, Gao and Liu, Zhuang and Van Der Maaten, Laurens and Weinberger, Kilian Q}, title = {Densely connected convolutional networks}, booktitle = cvpr, pages = {4700-4708}, year = 2017} @inproceedings{girshick2014, author = {Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra}, title = {Rich feature hierarchies for accurate object detection and semantic segmentation}, booktitle = cvpr, pages = {580-587}, year = 2014} @inproceedings{girshick2015, author = {Girshick, Ross}, title = {Fast {R-CNN}}, booktitle = cvpr, pages = {1440-1448}, year = 2015} @inproceedings{ren2015, author = {Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian}, title = {Faster {R-CNN}: Towards real-time object detection with region proposal networks}, booktitle = nips, pages = {91-99}, year = 2015} @inproceedings{redmon2016, author = {Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali}, title = {You only look once: Unified, real-time object detection}, booktitle = cvpr, pages = {779-788}, year = 2016} @inproceedings{liu2016, author = {Liu, Wei and Anguelov, Dragomir and Erhan, Dumitru and Szegedy, Christian and Reed, Scott and Fu, Cheng-Yang and Berg, Alexander C}, title = {{SSD}: Single shot multibox detector}, booktitle = eccv, pages = {21-37}, year = 2016} @inproceedings{he2017, author = {He, Kaiming and Gkioxari, Georgia and Doll{\'a}r, Piotr and Girshick, Ross}, title = {Mask {R-CNN}}, booktitle = iccv, pages = {2961-2969}, year = 2017} @inproceedings{lin2017, author = {Lin, Tsung-Yi and Doll{\'a}r, Piotr and Girshick, Ross and He, Kaiming and Hariharan, Bharath and Belongie, Serge}, title = {Feature pyramid networks for object detection}, booktitle = cvpr, pages = {2117-2125}, year = 2017} @inproceedings{redmon2017, author = {Redmon, Joseph and Farhadi, Ali}, title = {{YOLO}9000: better, faster, stronger}, booktitle = cvpr, pages = {7263-7271}, year = 2017} @inproceedings{karpathy2014, author = {Karpathy, Andrej and Toderici, George and Shetty, Sanketh and Leung, Thomas and Sukthankar, Rahul and Fei-Fei, Li}, title = {Large-scale video classification with convolutional neural networks}, booktitle = cvpr, pages = {1725-1732}, year = 2014} @inproceedings{simonyan2014, author = {Simonyan, Karen and Zisserman, Andrew}, title = {Two-stream convolutional networks for action recognition in videos}, booktitle = nips, pages = {568-576}, year = 2014} @inproceedings{wang2015, author = {Wang, Limin and Qiao, Yu and Tang, Xiaoou}, title = {Action recognition with trajectory-pooled deep-convolutional descriptors}, booktitle = cvpr, pages = {4305-4314}, year = 2015} @inproceedings{tran2015, author = {Tran, Du and Bourdev, Lubomir and Fergus, Rob and Torresani, Lorenzo and Paluri, Manohar}, title = {Learning spatiotemporal features with {3D} convolutional networks}, booktitle = iccv, pages = {4489-4497}, year = 2015} @inproceedings{yue2015, author = {Yue-Hei Ng, Joe and Hausknecht, Matthew and Vijayanarasimhan, Sudheendra and Vinyals, Oriol and Monga, Rajat and Toderici, George}, title = {Beyond short snippets: Deep networks for video classification}, booktitle = cvpr, pages = {4694-4702}, year = 2015} @inproceedings{feichtenhofer2016, author = {Feichtenhofer, Christoph and Pinz, Axel and Zisserman, Andrew}, title = {Convolutional two-stream network fusion for video action recognition}, booktitle = cvpr, pages = {1933-1941}, year = 2016} @inproceedings{wang2016, author = {Wang, Limin and Xiong, Yuanjun and Wang, Zhe and Qiao, Yu and Lin, Dahua and Tang, Xiaoou and Van Gool, Luc}, title = {Temporal segment networks: Towards good practices for deep action recognition}, booktitle = eccv, pages = {20-36}, year = 2016} @inproceedings{diba2017, author = {Diba, Ali and Sharma, Vivek and Van Gool, Luc}, title = {Deep temporal linear encoding networks}, booktitle = cvpr, pages = {2329-2338}, year = 2017} @inproceedings{carreira2017, author = {Carreira, Joao and Zisserman, Andrew}, title = {Quo vadis, action recognition? a new model and the {K}inetics dataset}, booktitle = cvpr, pages = {6299-6308}, year = 2017} @inproceedings{wang2018, author = {Wang, Xiaolong and Girshick, Ross and Gupta, Abhinav and He, Kaiming}, title = {Non-local neural networks}, booktitle = cvpr, pages = {7794-7803}, year = 2018} @inproceedings{wu2018, author = {Wu, Chao-Yuan and Zaheer, Manzil and Hu, Hexiang and Manmatha, R and Smola, Alexander J and Kr{\"a}henb{\"u}hl, Philipp}, title = {Compressed video action recognition}, booktitle = cvpr, pages = {6026-6035}, year = 2018} @inproceedings{zhou2018, author = {Zhou, Bolei and Andonian, Alex and Oliva, Aude and Torralba, Antonio}, title = {Temporal relational reasoning in videos}, booktitle = eccv, pages = {803-818}, year = 2018} % missing @inproceedings{zhu2018, author = {Zhu, Yi and Lan, Zhenzhong and Newsam, Shawn and Hauptmann, Alexander}, title = {Hidden two-stream convolutional networks for action recognition}, booktitle = accv, pages = {363-378}, year = 2018} @inproceedings{zolfaghari2018, author = {Zolfaghari, Mohammadreza and Singh, Kamaljeet and Brox, Thomas}, title = {{ECO}: Efficient convolutional network for online video understanding}, booktitle = eccv, pages = {695-712}, year = 2018} @inproceedings{feichtenhofer2019, author = {Feichtenhofer, Christoph and Fan, Haoqi and Malik, Jitendra and He, Kaiming}, title = {Slowfast networks for video recognition}, booktitle = iccv, pages = {6202-6211}, year = 2019} @inproceedings{lin2019, author = {Lin, Ji and Gan, Chuang and Han, Song}, title = {{TSM}: Temporal shift module for efficient video understanding}, booktitle = iccv, pages = {7083-7093}, year = 2019} @inproceedings{li2020, author = {Li, Yan and Ji, Bin and Shi, Xintian and Zhang, Jianguo and Kang, Bin and Wang, Limin}, title = {{TEA}: Temporal Excitation and Aggregation for Action Recognition}, booktitle = cvpr, pages = {909-918}, year = 2020} @inproceedings{feichtenhofer2020, author = {Feichtenhofer, Christoph}, title = {{X3D}: Expanding Architectures for Efficient Video Recognition}, booktitle = cvpr, pages = {203-213}, year = 2020}