8:20-8:25 Welcome and opening
8:25-9:00 Invited Talk: "Bridging the Gap between Egocentric Vision and Surveillance" Ali Borji, University of Central Florida
9:00-10:00 Multi-camera and Saliency
"Temporal Localization and Spatial Segmentation of Joint Attention in Multiple First-Person Videos"
Yifei Huang, Minjie Cai, Hiroshi Kera, Ryo Yonetani, Keita Higuchi, Yoichi Sato
"Finding Time Together: Detection and Classification of Focused Interaction in Egocentric Video "
Sophia Bano, Jianguo Zhang, Stephen McKenna
"SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes"
Marc Reina, Xavier Giro-i-Nieto, Kevin McGuinness and Noel O'Connor
"Convolutional Long Short-Term Memory Networks for Recognizing First Person Interactions"
Swathikiran Sudhakaran, Oswald Lanz
10:00-10:30 Morning break
10:30-11:05 Invited talk: "Learning Egocentric Policies for Where to Look", Kristen Grauman, University of Texas at Austin
11:05-11:35 Egocentric Activities
"Batch-Based Activity Recognition from Egocentric Photo-Streams"
Alejandro Cartas, Mariella Dimiccoli, Petia Radeva
"Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention"
Gedas Bertasius, Jianbo Shi
11:35-12:30 Spotlights and Poster Session
"Egomotion Recognition by Convolutional-Recurrent Neural Network"
Takayoshi Yamashita, Yuji Yamauchi, Hironobu Fujiyoshi
"Skill Determination from Egocentric Video"
Hazel Doughty, Dima Damen, Walterio Mayol-Cuevas
"Am I a Baller? Basketball Performance Assessment from First-Person Videos"
Gedas Bertasius, Hyun Soo Park, Stella X. Yu, Jianbo Shi
"Unsupervised Learning of Important Objects from First-Person Videos"
Gedas Bertasius, Hyun Soo Park, Stella X. Yu, Jianbo Shi
"Social Style Characterization from Egocentric Photo-streams"
Maedeh Aghaei, Mariella Dimiccoli, Cristian Canton, Petia Radeva
"Egocentric Perception using a Biologically Inspired Software Retina Integrated with a Deep CNN"
Piotr Ozime, Lorinc Balog, Ryan Wong, Tom Esparon, Jan Paul Siebert
"Contextually Driven First-person Action Recognition From Videos"
Alejandro Cartas, Petia Radeva, Mariella Dimiccoli
12:30-14:00 Lunch
14:00-14:35 Invited talk: "The Lifetime of an Object in Egocentric Vision", Dima Damen, University of Bristol
14:35-15:20 Object Interactions in Egocentric Vision
"An Object is Worth Six Thousand Pictures: The Egocentric, Manual, Multi-Image (EMMI) Dataset"
Xiaohan Wang, Fernanda Eliot, James Ainooson, Joshua Palmer, Maithilee Kunda
"How Shall we Evaluate Egocentric Action Recognition?"
Antonino Furnari, Sebastiano Battiato, Giovanni Maria Farinella
"Fully Convolutional Network and Region Proposal for Instance Identification with Egocentric Vision"
Maxime Portaz, Matthias Kohl
15:20-15:50 Afternoon Break
15:50-16:20 Activity Recognition and Application
"Outdoor Operation of Structured Light in Mobile Phone"
Byeonghoon Park
"Reading Text in the Wild from Compressed Images"
Leonardo Galteri, Dena Bazazian, Lorenzo Seidenari, Marco Bertini, Andrew Bagdanov, Anguelos Nicolaou, Dimosthenis Karatzas, Alberto Del Bimbo
16:20-17:00 Panel Discussion
Presenting Challenges
Panel Discussion
Moderator: Dima Damen, University of Bristol
- Ali Borji, University of Central Florida
- Mariella Dimiccoli, University of Barcelona and Computer Vision Center
- Sanja Fidler, University of Toronto
- Giovanni Maria Farinella, University of Catania
- Hamed Pirsiavash, University of Maryland Baltimore County
Group Discussions
Feedback to Panel
Closing Remarks