Journal Club

This page lists the talks of the joint CML journal club in Hamburg and Beijing.

Summer Semester 2020

Note: due to the Corona virus measures, all meetings will take place as online Zoom meetings this semester.

• Wednesday, 16 September 2020, 13:00 (Hamburg), 19:00 (Beijing), Zoom meeting
  

  We will discuss a paper proposed by Ziwei Chen (CAS):

  Henderson, J.M., Hayes, T.R. (2017).
  Meaning-based guidance of attention in scenes as revealed by meaning maps.
  Nat Hum Behav 1, 743–747 (2017). doi.org/10.1038/s41562-017-0208-0

• Wednesday, 26 August 2020, 13:00 (Hamburg), 20:00 (Beijing), Zoom meeting
  

  We will discuss a preprint proposed by Shuang Li:

  Lin Shao, Toki Migimatsu, Qiang Zhang, Kaiyuan Yang, Jeannette Bohg (2020).
  Concept2Robot: Learning Manipulation Concepts from Instructions and Human Demonstrations
  Paper, Video.

• Wednesday, 5 August 2020, 13:00 (Hamburg), 20:00 (Beijing), Zoom meeting
  Wednesday, 12 August 2020, 13:00 (Hamburg), 20:00 (Beijing), Zoom meeting
  

  We will discuss a preprint proposed by Julius Richter:

  Vincent Sitzmann*, Julien N. P. Martel*, Alexander Bergman, David B. Lindell, Gordon Wetzstein (2020).
  Implicit Neural Representations with Periodic Activation Functions
  Preprint: Arxiv 2006.09661, Code/Demo: Siren github.
  

• Wednesday, 15 July 2020, 13:00 (Hamburg), 21:00 (Beijing), Zoom meeting
  

  We will discuss a comprehensive review proposed by Özge Alacam:

  T. Baltrušaitis, C. Ahuja and L. Morency. (2019).
  Multimodal Machine Learning: A Survey and Taxonomy.
  IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 2, pp. 423-443, 1 Feb. 2019.
  doi: 10.1109/TPAMI.2018.2798607

• Wednesday, 1 July 2020, 13:00 (Hamburg), 21:00 (Beijing), Zoom meeting
  

  This week's paper was proposed by Carina Bauer from Institute of Systems Neuroscience, UKE:

  Karla K Evans, Anne Treisman. (2010).
  Natural Cross-Modal Mappings Between Visual and Auditory Features.
  Journal of Vision, 2010, 10(1):6.1-12.

• Wednesday, 17 June 2020, 13:00 (Hamburg), 21:00 (Beijing), Zoom meeting
  

  This week's paper was selected by Xintong Wang from Language Technology Group:

  Yusuf Aytar, Carl Vondrick, Antonio Torralba. (2017).
  See, Hear, and Read: Deep Aligned Representations.
  Arxiv 1706.00932

• Wednesday, 27 May 2020, 13:00 (Hamburg), 21:00 (Beijing), Zoom meeting
  

  This week's paper was selected by Fares Abawi. The authors investigate the applicability of audio cues in conjunction with visual ones in predicting saliency maps using deep neural networks.

  Hamed R. Tavakoli, Ali Borji, Esa Rahtu, Juho Kannala. (2019).
  DAVE: Deep Audio-Visual Embedding for Dynamic Saliency Prediction.
  Arxiv 1905.10693

• Wednesday, 13 May 2020, 13:00 (Hamburg), 21:00 (Beijing), Zoom meeting
  

  This week's paper about attention and EEG was selected by Cora Kubetschek:

  Toshihiro Kumagai and Hiroaki Mizuhara (2016).
  Top-down and bottom-up attention cause the ventriloquism effect with distinct electroencephalography modulations.
  NeuroReport 27:647-651 (2016).

• Wednesday, 29 April 2020, 13:00, Zoom meeting
  

  This week's paper about vision and touch, using deep networks and reinforcement learning, was proposed by Michael Görner:

  Michelle A. Lee, Yuke Zhu, Peter Zachares, Matthew Tan, Krishnan Srinivasan, Silvio Savarese, Li Fei-Fei, Animesh Garg, Jeannette Bohg (2019).
  Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks.
  Arxiv 1907.04975, 2019.

• Wednesday, 8 April 2020, 14:00 (Hamburg) 20:00 (Beijing), Zoom meeting.

  This week's paper about audio-visual speech was proposed by Hongzhuo Liang:

  Triantafyllos Afouras, Joon Son Chung, Andrew Zisserman (2019).
  My lips are concealed: Audio-visual speech enhancement through obstructions.
  Arxiv 907.04975, 2019.

Previous Semesters (CML Phase 1)

Please see here for an archive of the Journal Club in Phase 1 of the project.