8:20-8:30 Welcome and Opening
8:30-9:05 Keynote: "Capturing First-Person alongside Third-Person Videos in the Wild"
Abinav Gupta (CMU, USA)
9:05-09:35 Full Paper Presentations
"MACNet: Multi-scale Atrous Convolution Networks for Food Places Classification in Egocentric Photo-streams"
Md. Mostafa Kamal Sarker (Rovira i Virgili University), Hatem Rashwan (Rovira i Virgili University), Estefania Talavera (University of Barcelona), Syeda Furruka Banu (Rovira i Virgili University), Petia Radeva (University of Barcelona) and Domenec Puig (Rovira i Virgili University)
"PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks"
Marc Assens Reina (Universitat Politecnica de Catalunya), Kevin McGuinness (Dublin City University), Xavier Giro-i-Nieto (Universitat Politecnica de Catalunya), Noel O'Connor (Dublin City University) - Webpage
9:35-9:50 EPIC-KITCHENS 2018 Dataset: Challenges Opening,
Will Price (University of Bristol, UK) and Antonino Furnari (University of Catania, Italy)
9:50-10:25 Keynote: "Video Understanding: Learning More with Less Annotation"
Ivan Laptev (INRIA Paris, France)
10:25-11:30 Coffee Break and Poster Session
Accepted Abstracts
"Eye Movement Velocity and Gaze Data Generator for Evaluation, Robustness Testing and Assess of Eye Tracking Software and Visualization Tools"
Wolfgang Fuhl (University of Tuebingen) and Enkelejda Kasneci (University of Tuebingen)
"Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images"
Dena Bazazian (Computer Vision Center), Dimosthenis Karatzas (Computer Vision Centre) and Andy Bagdanov (University of Florence)
"On the Role of Event Boundaries in Egocentric Activity Recognition from Photo Streams"
Alejandro Cartas (University of Barcelona), Estefanía Talavera (University of Barcelona), Petia Radeva (University of Barcelona), and Mariella Dimiccoli (Computer Vision Center)
"Joint Attention Estimation from Object-wise 3D Gaze Concurrences in Multiple First-Person Videos and Gazes"
Hiroyuki Ishihara (NTT)
"Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition"
Yifei Huang (University of Tokyo), Minjie Cai (University of Tokyo), Zhenqiang Li (University of Tokyo) and Yoichi Sato (University of Tokyo)
"A Geometric Model of Spatial Misperception in Virtual Environments"
Manuela Chessa (University of Genova) and Fabio Solari (University of Genova)
"Visitors Localization from Egocentric Videos"
Francesco Ragusa (University of Catania), Antonino Furnari (University of Catania), Sebastiano Battiato (University of Catania), Giovanni Signorello (University of Catania) and Giovanni Maria Farinella (University of Catania) - webpage
"Towards an Embodied Semantic Fovea: Semantic 3D scene reconstruction from ego-centric eye-tracker videos"
Mickey Li (Imperial College London), Pavel Orlov (Imperial College London), Aldo Faisal (Imperial College London), Noyan Songur (Imperial College London) and Stefan Leutenegger (Imperial College London)
"The Impact of Temporal Regularisation in Video Saliency Prediction"
Panagiotis Linardos (Universitat Politècnica de Catalunya), Xavier Giro-i-Nieto (Universitat Politecnica de Catalunya), Eva Mohedano (Insight Center for Data Analytics), Monica Cherto (Insight Center for Data Analytics) and Cathal Gurrin (Dublin City University) - Project Webpage
"Depth in the Visual Attention Modelling from the Egocentric Perspective of View"
Miroslav Laco (Slovak University of Technology in Bratislava) and Wanda Benesova (Slovak University of Technology in Bratislava)
"Efficient Egocentric Visual Perception Combining Eye-tracking, a Software Retina and Deep Learning"
Nina Hristozova (University of Glasgow), Piotr Ozimek (University of Glasgow) and Jan Paul Siebert (University of Glasgow)
"Object-centric Attention for Egocentric Activity Recognition"
Swathikiran Sudhakaran (Fondazione Bruno Kessler) and Oswald Lanz (Fondazione Bruno Kessler) - Webpage
Invited ECCV Papers
"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset"
Dima Damen (University of Bristol), Hazel Doughty (University of Bristol), Giovanni Maria Farinella (University of Catania), Sanja Fidler (University of Toronto, NVIDIA), Antonino Furnari (University of Catania), Evangelos Kazakos (University of Bristol), Davide Moltisanti (University of Bristol), Jonathan Munro (University of Bristol), Toby Perrett (University of Bristol), Will Price (University of Bristol) and Michael Wray (University of Bristol)
"Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos"
Mingze Xu (Indiana University), Chenyou Fan (, Yuchen Wang (Indiana University), Michael Ryoo (Indiana University) and David Crandall (Indiana University)
"Efficient 6-DoF Tracking of Handheld Objects from an Egocentric Viewpoint"
Rohit Pandey (Google), Pavel Pidlypenskyi (Google), Shuoran Yang (Google), Christine Kaeser-Chen (Google)
11:30-12:05 Keynote: "Multimodal and Open-ended Learning",
Barbara Caputo (Italian Institute of Technology, Italy)
12:05-12:35 Full Paper Presentations
"Leveraging Uncertainty to Rethink Loss Functions and Evaluation Measures for Egocentric Action Anticipation"
Antonino Furnari (University of Catania), Sebastiano Battiato (University of Catania) and Giovanni Maria Farinella (University of Catania)
"MAM: Transfer Learning for Fully Automatic Video Annotation and Specialized Detector Creation "
Wolfgang Fuhl (University of Tuebingen), Nora J Castner (University Tuebingen), Markus Holzer (Bosch), Lin Zhuang (Bosch) and Enkelejda Kasneci (University of Tuebingen)
12:35-12:40 Closing Remarks