The open access proceedings of the workshop are available at the CVF open access repository.
The workshop will be held within the ICCV 2019 conference, as a half-day workshop in the morning of Saturday Nov. 2 2019.
Place: Room 307A
Date: Saturday Nov. 2 2019
Time: 8:30-12:45
The poster session will be held in Section 1 (poster numbers 41-63). The program reports the number assigned to each poster.
| 8:30 | 8:45 | Welcome |
| 8:45 | 9:30 | Invited Talk by Marc Pollefeys (ETH Zurich, CH) |
| 9:30 | 10:00 | Oral Session I |
| Simultaneous Segmentation and Recognition: Towards more accurate Ego Gesture Recognition Tejo Chalasani (Trinity College Dublin), Aljosa Smolic (Trinity College Dublin) |
||
| EgoVQA - An Egocentric Video Question Answering Benchmark Dataset Chenyou Fan (Google) |
||
| 10:00 | 11:00 | Coffee Break and Poster Session (Section 1) |
| Full Papers | ||
| 41. Simultaneous Segmentation and Recognition: Towards more accurate Ego Gesture Recognition Tejo Chalasani (Trinity College Dublin), Aljosa Smolic (Trinity College Dublin) |
||
| 42. EgoVQA - An Egocentric Video Question Answering Benchmark Dataset Chenyou Fan (Google) |
||
| 43. Learning Spatiotemporal Attention for Egocentric Action Recognition Minlong Lu (Simon Fraser University), Danping Liao (Zhejiang University), Ze-Nian Li (Simon Fraser University) |
||
| 44. Seeing and Hearing Egocentric Actions: How Much Can We Learn? Alejandro Cartas (University of Barcelona), Jordi Luque, Petia Radeva, Carlos Segura, Mariella Dimiccoli |
||
| 45. Multitask Learning to Improve Egocentric Action Recognition George Kapidis (Utrecht University), Ronald Poppe (Utrecht University), Elsbeth van Dam (Noldus IT), Lucas Noldus (Noldus IT), Remco C. Veltkamp (Utrecht University) |
||
| 46. Weakly-supervised Degree of Eye-closeness Estimation Eyasu Zemene (Qualcomm), Shuai Zhang (Qualcomm AI Research), Bijan Forutanpour (Qualcomm), Yingyong Qi (Qualcomm), Ning Bi (Qualcomm) |
||
| 47. Ego-Semantic Labeling of Scene from Depth Image for Visually Impaired and Blind People Chayma Zatout (University USTHB), Slimane Larabi (USTHB University), Ilyes Mendili (University USTHB), Barnabé SOEDJI (University USTHB) |
||
| 48. An Analysis of how Driver Experience Affects Eye-Gaze Behavior for Robotic Wheelchair Operation Yamato Maekawa (Nagoya University), Naoki Akai (Nagoya University), Takatsugu Hirayama (Nagoya University), Luis Yoichi Morales (Nagoya University), Daisuke Deguchi (Nagoya University), Yasutomo Kawanishi (Nagoya University), Ichiro Ide (Nagoya University), Hiroshi Murase (Nagoya University) |
||
| 49. Manipulation-skill Assessment from Videos with Spatial Attention Network Zhenqiang Li (The University of Tokyo), Yifei Huang (The University of Tokyo), Minjie Cai (Hunan University), Yoichi Sato (University of Tokyo) |
||
| 50. The applicability of Cycle GANs for pupil and eyelid segmentation, data generation and image refinement Wolfgang Fuhl (University of Tuebingen), David Geisler (University of Tübingen), Wolfgang Rosenstiel (University of Tuebingen), Enkelejda Kasneci (University of Tuebingen) |
||
| 51. EPIC-Tent: An Egocentric Video Dataset for Camping Tent Assembly Youngkyoon Jang (University of Bristol), Brian Sullivan (University of Bristol), Casimir Ludwig (University of Bristol), Iain Gilchrist (University of Bristol), Dima Damen (University of Bristol), Walterio Mayol-Cuevas (Bristol University) |
||
| 52. First-person camera system to evaluate Tender Dementia-care skill Atsushi Nakazawa (Kyoto University), Miwako Honda (Tokyo Medical Center) |
||
| 53. Assessment of Optical See-Through Head Mounted Display Calibration for interactive Augmented Reality Giorgio Ballestin (University of Genoa), Manuela Chessa (University of Genova, Italy), Fabio Solari (University of Genova, Italy) |
||
| Extended Abstracts | ||
| 54. Early Estimation of User's Intention of Tele-Operation Using Object Affordance and Hand Motion in a Dual First-Person Vision Motoki Kojima (Toyohashi University of Technology), Jun Miura (Toyohashi University of Technology) |
||
| 55. Dog-Centric Activity Recognition by Integrating Appearance, Motion and Sound Tsuyohito Araki (Univ. Electro-Comm., Tokyo), Ryunosuke Hamada (Tohoku University), Kazunori Ohno (Tohoku University), Keiji Yanai (Univ. Electro-Comm., Tokyo) |
||
| Invited Papers From ICCV/ICCV Workshops | ||
| 56. EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition Evangelos Kazakos (University of Bristol, UK), Arsha Nagrani (University of Oxford, UK), Andrew Zisserman (University of Oxford, UK), Dima Damen (University of Bristol, UK) |
||
| 57. Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings Michael Wray (University of Bristol, UK), Diane Larlus (Naver Labs Europe), Gabriela Csurka (Naver Labs Europe), Dima Damen (University of Bristol, UK) |
||
| 58. Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos Will Price (University of Bristol, UK), Dima Damen (University of Bristol, UK) |
||
| 59. What Would you Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention Antonino Furnari (University of Catania, Italy), Giovanni Maria Farinella (University of Catania, Italy) |
||
| 60. xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera Denis Tome (University College London & Facebook Reality Lab), Patrick Peluse (Facebook Reality Lab), Lourdes Agapito (University College London), Hernan Badino (Facebook Reality Lab) |
||
| 61. Ego-Pose Estimation and Forecasting as Real-Time PD Control Ye Yuan (Carnegie Mellon University), Kris Kitani (Carnegie Mellon University) |
||
| 62. Grounded Human-Object Interaction Hotspots from Video Tushar Nagarajan (UT Austin), Christoph Feichtenhofer (Facebook AI Research), Kristen Grauman (Facebook AI Research) |
||
| 11:00 | 11:45 | Invited Talk by Oswald Lanz (Fondazione Bruno Kessler, Trento, Italy) |
| 11:45 | 12:30 | Oral Session II |
| Learning Spatiotemporal Attention for Egocentric Action Recognition Minlong Lu (Simon Fraser University), Danping Liao (Zhejiang University), Ze-Nian Li (Simon Fraser University) |
||
| Seeing and Hearing Egocentric Actions: How Much Can We Learn? Alejandro Cartas (University of Barcelona), Jordi Luque, Petia Radeva, Carlos Segura, Mariella Dimiccoli |
||
| Multitask Learning to Improve Egocentric Action Recognition George Kapidis (Utrecht University), Ronald Poppe (Utrecht University), Elsbeth van Dam (Noldus IT), Lucas Noldus (Noldus IT), Remco C. Veltkamp (Utrecht University) |
||
| 12:30 | 12:45 | Closing Remarks |