Monday 17 June 2019 - Full Day - Seaside 7

07:30-08:50 Breakfast
08:50-09:00 Welcome
09:00-09:35 Keynote: Egocentric Perception of Social and Health-Related Behaviors
Jim Rehg (Georgia Tech, USA)
09:35-09:45 EPIC-Kitchens Challenges: Winner Announcements
09:45-10:15 Action Recognition Challenge: Top-3 Winners Talks
10:15-10:45 Coffee Break
10:45-11:20 Keynote: Anticipation and Prediction for Scene Understanding
Bernt Schiele (Max-Planck-Institute Informatik, Germany)
11:20-11:40 Action Anticipation Challenge - Winners Talks
11:40-12:10 Spotlight Presentations I (Accepted Abstracts)
"Autonomous Human Activity Classification from Ego-vision Camera and Accelerometer Data"
Yantao Lu (Syracuse University), Senem Velipasalar (Syracuse University)
"The role of ego vision in view-invariant action recognition"
Gaurvi Goyal (University of Genova), Nicoletta Noceti (University of Genova), Alessandra Sciutti (Italian Institute of Technology), Francesca Odone (University of Genova)
"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention"
Antonino Furnari (University of Catania), Giovanni Maria Farinella (University of Catania)
"Hand Orientation Estimation in Probability Density Form"
Kazuaki Kondo (Kyoto University), Daisuke Deguchi (Nagoya University), Atsushi Shimada (Kyushu University)
"How Much Does Audio Matter to Recognize Egocentric Object Interactions?"
Alejandro Cartas (University of Barcelona), Jordi Luque (Telefonica Research), Petia Radeva (University of Barcelona), Carlos Segura Perales (Telefonica Research), Dimiccoli Mariella ()
12:10-13:30 Lunch Break
13:30-14:05 Keynote: Saliency, Vision and Language Interaction for Egocentric autonomous views
Rita Cucchiara (University of Modena, Italy)
14:05-15:00 Spotlight Presentations II (Accepted Abstracts)
"Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study"
Satoshi Tsutsui (Indiana University), Dian Zhi (Indiana University), Md Alimoor Reza (Indiana University), David Crandall (Indiana University), Chen Yu (Indiana University)
"Toward Hand-Aware Object Tracking in First-Person Video"
David Russell (Clarkson University), Martial Hebert (Carnegie Mellon University)
"Grounded Human-Object Interaction Hotspots from Video"
Tushar Nagarajan (UT Austin), Christoph Feichtenhofer (Facebook AI Research), Kristen Grauman (Facebook AI Research and UT Austin)
"From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval"
Krishna Regmi (University of Central Florida), Mohamed Elfeki (CRCV), Shervin Ardeshir (Netflix), Ali Borji (University of Central Florida)
"Egocentric affordance detection with the one-shot geometry-driven Interaction Tensor"
Eduardo Ruiz (University of Bristol), Walterio Mayol-Cuevas (University of Bristol)
"Recognizing Manipulation Actions from State-Transformations"
Nachwa Aboubakr (University Grenoble Alps), James L. Crowley (Univ. Grenoble Alpes), Remi Ronfard (INRIA)
"Exploring Visual Saliency of Real Objects at Different Depths"
Miroslav Laco (Slovak University of Technology in Bratislava), Patrik Polatsek (Slovak University of Technology in Bratislava), Wanda Benesova (Slovak University of Technology in Bratislava)
"Detecting Clues for Skill Levels and Machine Operation Difficulty from Egocentric Vision"
Longfei Chen (Kyoto University), Yuichi Nakamura (Kyoto University), Kazuaki Kondo (Kyoto University)
"Egocentric Vision-based Traffic Accident Detection using Future Object Localization"
Yu Yao (University of Michigan), Mingze Xu (Indiana University), Yuchen Wang (Indiana University), David Crandall (Indiana University), Ella Atkins (University of Michigan)
15:00-15:10 Poster Setup
15:10-16:30 Poster Session (and Coffee Break)
16:30-17:05 Keynote: Computer Vision for Industrial Augmented Reality
Daniel Wagner (CTO at DAQRI, Austria)
17:05-17:40 Invited Talks from CVPR 2019 Papers
"Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training"
Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel
"Learning joint reconstruction of hands and manipulated objects"
Yana Hasson, Gul Varol, Dimitrios Tzionas, Igor Kalevatykh, Michael J. Black, Ivan Laptev, Cordelia Schmid
"H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions"
Bugra Tekin, Federica Bogo, Marc Pollefeys
"Less is More: Learning Highlight Detection from Video Duration"
Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, Kristen Grauman
Posters only in poster session
"Deep Dual Relation Modeling for Egocentric Interaction Recognition"
Haoxin Li, Yijun Cai, Wei-Shi Zheng
"DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition"
Toby Perrett, Dima Damen
"The Pros and Cons: Rank-Aware Temporal Attention for Skill Determination in Long Videos"
Hazel Doughty, Walterio Mayol-Cuevas, Dima Damen
"Action Recognition From Single Timestamp Supervision in Untrimmed Videos"
Davide Moltisanti; Sanja Fidler; Dima Damen
17:45-18:00 Challenge Conclusions and Future Directions