Program

8:30 Welcome and general remarks
8:40 Invited talk by Stefanos Zafeiriou: Estimating Affect in-the-wild
9:20 Oral presentation #1: Generating Synthetic Video Sequences by Explicitly Modeling Object Motion by Simone Palazzo, Pierluca D'Oro, Daniela Giordano and Concetto Spampinato.
9:35 Oral presentation #2: Deep Multitask Gaze Estimation with a Constrained Landmark-Gaze Model by Yu Yu.
9:50 Oral presentation #3: Semi-DGPose: A Semi-supervised Deep Generative Model for Human Body Analysis by Rodrigo de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, N. Siddharth and Philip Torr.
10:05 Oral presentation #4: Pose guided human image synthesis by view disentanglement and enhanced weighting loss by Mohamed I Lakhal, Oswald Lanz and Andrea Cavallaro.
10:20 Oral presentation #5: Photorealistic Facial Synthesis in the Dimensional Affect Space by Dimitrios Kollias, Stefanos Zafeiriou, Shiyang Cheng and Maja Pantic.
10:35 Poster session:
  • Generating Synthetic Video Sequences by Explicitly Modeling Object Motion by Simone Palazzo, Pierluca D'Oro, Daniela Giordano and Concetto Spampinato.
  • Deep Multitask Gaze Estimation with a Constrained Landmark-Gaze Model by Yu Yu.
  • Semi-DGPose: A Semi-supervised Deep Generative Model for Human Body Analysis by Rodrigo de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, N. Siddharth and Philip Torr.
  • Pose guided human image synthesis by view disentanglement and enhanced weighting loss by Mohamed I Lakhal, Oswald Lanz and Andrea Cavallaro.
  • Photorealistic Facial Synthesis in the Dimensional Affect Space by Dimitrios Kollias, Stefanos Zafeiriou, Shiyang Cheng and Maja Pantic.
  • Give ear to my face: modelling multimodal attention to social interactions by Vittorio Cuculo, Giuseppe Boccignone, Alessandro D'Amelio, Giuliano Grossi and Raffaella Lanzarotti.
  • Investigating Depth Domain Adaptation for Efficient Human Pose Estimation by Angel N Martinez Gonzalez, Michael Villamizar, Olivier Canevet and Jean-Marc Odobez.
  • Filling the Gaps: Predicting Missing Joints of Human Poses Using Denoising Autoencoders by Nicolo' Carissimi, Paolo Rota, Cigdem Beyan and Vittorio Murino.
  • A Semi-Supervised Data Augmentation Approach using 3D Graphical Engines by Shuangjun Liu and Sarah Ostadabbas.
  • Towards Learning a Realistic Rendering of Human Behavior by Patrick Esser, Timo Milbich, Johannes Haux and Bjorn Ommer.
  • Human Action Recognition Based on Temporal Pose CNN and Multi-Dimensional Fusion by Yi Huang, Shang-Hong Lai and Shao-Heng Tai.
  • Rendering Realistic Subject-Dependent Expression Images by Learning 3DMM Deformation Coefficients by Claudio Ferrari, Stefano Berretti, Pietro Pala and Alberto Del Bimbo.
  • Role of Group Level Affect to Find The Most Influential Person in Images by Shreya Ghosh and Abhinav Dhall.
  • Residual Stacked RNNs for Action Recognition by Mohamed I Lakhal, Albert Clapes, Sergio Escalera, Oswald Lanz and Andrea Cavallaro.
  • Pattern-of-Life Detection in Human Trajectory Visualisation by Yazan Qarout and David Lowe.
11:35 Invited talk by Michael Black: Learning to be a Digital Human
12:15 Conclusion