| 14:00 | Welcome
Lamberto Ballan (University of Padova, Italy), Ting Yao (JD AI Research, China) |
|---|---|
| 14:10 – 14:50 | Keynote 1: Human Centric Special Understanding
Dr. Wenjun Zeng, IEEE Fellow, Sr. Principal Research Manager, MSRA, China |
| 14:50 – 15:30 | Keynote 2: Human-Centric Object Interactions - A Fine-Grained Perspective from Egocentric Videos
Prof. Dima Damen, Program Co-Chair ICCV 2021, University of Bristol, UK |
| 15:30 – 16:10 | Keynote 3: Speaker localisation and enhancement in populated environments
Dr. Xavier Alameda-Pineda, Research Scientist, INRIA, France |
| 16:10 – 16:50 | Keynote 4: Recent Advances in Understanding Human Centered Activities and Learning Video-Language Interactions
Prof. Jiebo Luo, IEEE/ACM/AAAI Fellow, University of Rochester, USA |
| 16:50 – 17:00 | TrajNet++ Challenge, by Mr. Kothari Parth, EPFL |
| 17:00 – 18:00 | Paper Presentation (10 papers, each 6 mins) |
| Spot What Matters: Learning Context Using Graph Convolutional Networks for Weakly-Supervised Action Detection
Michail Tsiaousis; Gertjan Burghouts; Fieke Hillerstrom; Peter van der Putten |
|
| Social Modeling Meets Virtual Reality: An Immersive Implication
Habib Ullah; Sultan Daud Khan; Mohib Ullah; Faouzi Alaya-Chekh |
|
| Pickpocketing Recognition in Still Images
Prisa Damrongsiri; Hossein Malekmohamadi |
|
| t-EVA: Time-Efficient t-SNE Video Annotation
Soroosh Poorgholi; Osman Semih Kayhan; Jan van Gemert |
|
| Vision-based Fall Detection using Body Geometry
Djamila Romaissa Beddiar; Mourad Oussalah; Brahim Nini; Yazid Bounab |
|
| Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos
Okan Köpüklü; Fabian Herzog; Gerhard Rigoll |
|
| Generalization of Fitness Exercise Recognition from Doppler Measurements by Domain-Adaption and Few-Shot Learning
Biying Fu; Naser Damer; Florian Kirchbuchner; Arjan Kuijper |
|
| Local Anomaly Detection in Videos using Object-Centric Adversarial Learning
Pankaj PRR Roy; Guillaume-Alexandre Bilodeau; Lama Seoud |
|
| A Hierarchical Framework for Motion Trajectory Forecasting Based on Modality Sampling
Yifan Ma; Bo Zhang; Nicola Conci; Hongbo Liu |
|
| Skeleton-based Methods for Speaker ActionClassification on Lecture Videos
Fei Xu; Kenny Davila; Srirangaraj Setlur; Venu Govindaraju |
18:00 | Closing |