Continuing Part 1, the article will share all the summaries and details of the remaining Facebook Research studies presented at CVPR 2020.

21. Lightweight multiview 3D pose estimation through camera-disentangled representation
Edoardo Remelli, Shangchen Han, Sina Honari, Pascal Fua, Robert Wang

22. Listen to look: Action recognition by previewing audio
Ruohan Gao, Tae-Hyun Oh, Kristen Grauman, Lorenzo Torresani

23. Momentum contrast for unsupervised visual representation learning
Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick

24. Object fusion
Martin Rünz, Kejie Li, Meng Tang, Lingni Ma, Chen Kong, Tanner Schmidt, Ian Reid, Lourdes Agapito, Julian Straub, Steven Lovegrove, Richard Newcombe

25. One-Shot Domain Adaptation For Face Generation
Chao Yang, Ser-Nam Lim

26. PIFuHD: Multilevel pixel-aligned implicit function for high-resolution 3D human digitization
Shunsuke Saito, Tomas Simon, Jason Saragih, Hanbyul Joo

27. PointRend: Image segmentation as rendering
Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick

28. Pretext invariant self-supervised representation learning
Ishan Misra, Laurens van der Maaten

29. Transferring Dense Pose to Proximal Animal Classes
Artsiom Sanakoyeu, Vasil Khalidov, Maureen S. McCarthy, Andrea Vedaldi, Natalia Neverova

30. Use the Force, Luke! Learning to predict physical forces by simulating effects
Kiana Ehsani, Shubham Tulsiani, Saurabh Gupta, Ali Farhadi, Abhinav Gupta

31. VPLNet: Deep single view normal estimation with vanishing points and lines
Rui Wang, David Geraghty, Kevin Matzen, Jan-Michael Frahm, and Richard Szeliski

32. ViBE: Dressing for diverse body shapes
Wei-Lin Hsiao, Kristen Grauman

33. Video classification with correlation networks
Heng Wang, Du Tran, Lorenzo Torresani, Matt Feiszli

34. Visual navigation via neural topological mapping
Devendra Singh Chaplot, Ruslan Salakhutdinov, Abhinav Gupta, Saurabh Gupta

35. What makes training multi-modal networks hard?
Weiyao Wang, Du Tran, Matt Feiszli

36. Wish You Were Here: Context Aware Human Generation
Oran Gafni, Lior Wolf

37. X3D: Expanding Architectures for Fast Video Recognition
Christoph Feichtenhofer

38. You2Me: Inferring body pose in egocentric video via first and second person interactions
Evonne Ng, Donglai Xiang, Hanbyul Joo, Kristen Grauman

Source: Facebook AI

 

Related posts: