/awesomeCVpapers

Let's push all kinds of CV paper weekly

awesomeCVpapers

Video Descriptor

Video Descriptor

(from Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri, Learning Spatiotemporal Features with 3D Convolutional Networks, ICCV15'. )

  • C3D, Facebook AI Research [Paper] [Project Page] Hao
  • Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri, Learning Spatiotemporal Features with 3D Convolutional Networks, ICCV15'.
  • CNN with VLAD, The University of Queensland [Paper] Hao
  • Zhongwen Xu, Yi Yang, Alexander G. Hauptmann, A Discriminative CNN Video Representation for Event Detection, CVPR15'.

Video Description Generation

Video Description

(from Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle, Aaron Courville, Describing Videos by Exploiting Temporal Structure, ICCV15'. )

  • HRNE, Zhejiang University [Paper] Hao
  • Pingbo Pan, Zhongwen Xu, Yi Yang, Fei Wu, Yueting Zhuang, Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning, arXiv:1511.03476.
  • LSTM with CNN+3DCNN & Attention Mechanism, Universite ́ de Montre ́al [Paper] Hao
  • Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle, Aaron Courville, Describing Videos by Exploiting Temporal Structure, ICCV15'.
  • Video caption via LSTM, UT Austin [Paper] [Project Page] Hao
  • Subhashini Venugopalan, Huijuan Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, Kate Saenko, Translating Videos to Natural Language Using Deep Recurrent Neural Networks, ICCV15'.
  • LSTM-E, Microsoft Research, Beijing [Paper] Hao
  • Yingwei Pan, Tao Mei, Ting Yao, Houqiang Li, Yong Rui, Jointly Modeling Embedding and Translation to Bridge Video and Language, arXiv:1505.01861.
  • p-RNN, Purdue University, Baidu Research - Institute of Deep Learning [Paper] Hao
  • Haonan Yu, Jiang Wang, Zhiheng Huang, Yi Yang, Wei Xu, Video Paragraph Captioning using Hierarchical Recurrent Neural Networks, arXiv:1510.07712.

Wrist Camera

  • WristCam System, The University of Tokyo [Paper] JamesChan
  • Katsunori Ohnishi, Atsushi Kanehira, Asako Kanezaki, Tatsuya Harada, ecognizing Activities of Daily Living with a Wrist-mounted Camera, arXiv:1511.06783v1.

Optical Flow

  • Farneback's algorithm : Two-Frame Motion Estimation Based on Polynomial Expansion[PAPER] jimcheng *Joao F. Henriques Pedro Martins Rui Caseiro Jorge Batista˜,Institute of Systems and Robotics University of Coimbra

  • LEAR PROJECT of deep and epic flow [PROJECT PAGE] *DeepMatching: Deep Convolutional Matching. DeepMatching was recently used to improve the estimation of optical flow in several methods like DeepFlow and EpicFlow (joint work with Philippe Weinzaepfel, Zaid Harchaoui, Cordelia Schmid).

  • DeepFlow: Large displacement optical flow with deep matching[PAPER] jimcheng *Philippe Weinzaepfel, J´erˆome Revaud, Zaid Harchaoui, Cordelia Schmid. ICCV, Dec 2013, Sydney, Australia. IEEE, pp.1385-1392, 2013, <10.1109/ICCV.2013.175>.

  • EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow[PAPER] jimcheng *Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui, Cordelia Schmid. CVPR, Jun 2015, Boston, United States.

Hardware Accelaration

  • Parallel Architecture for Hierarchical Optical Flow Estimation Based on FPGA[PAPER] jimcheng *Francisco Barranco, Matteo Tomasi, Javier Diaz, Mauricio Vanegas, and Eduardo Ros, IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, VOL. 20, NO. 6, pp.1058-1067, JUNE 2012.

  • Efficient Hardware Implementation of the Horn-Schunck Algorithm for High-Resolution Real-Time Dense Optical Flow Sensor[PAPER] jimcheng *Mateusz Komorkiewicz *, Tomasz Kryjak and Marek Gorgon, AGH University of Science and Technology, al. Sensors 2014, 14, 2860-2891; doi:10.3390/s140202860.

  • Caffe con Troll: Shallow Ideas to Speed Up Deep Learning[PAPER] jimcheng *Stefan Hadjis† Firas Abuzaid† Ce Zhang†‡ Christopher Ré, Stanford University, University of Wisconsin-Madison, arXiv:1504.04343v2 [cs.LG] 26 May 2015.

  • cuDNN: Efficient Primitives for Deep Learning[PAPER] jimcheng *Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, NVIDIA, Santa Clara, CA 95050, arXiv:1410.0759v3 [cs.NE] 18 Dec 2014.