• Keynote: 35 minutes + 5minutes QA
  • Oral: 10 minutes (8 minutes + 2 minutes QA)
  • 21 Aug. 2022, 9:00-12:00 AM (Montreal Quebec Time zone)

    Time

    Title

    Speaker

    Chair

    09:00-09:10

    Welcome and Opening

    Zhanyu Ma

    09:10-09:50

    Deep Prototype Learning for Classification and Generalization in Open World

    Cheng-Lin Liu (Institute of Automation of Chinese Academy of Sciences)

    Zhaoxiang Zhang

    09:50-10:30

    Improving Distillation Schemes for Incremental Learning in Semantic Segmentation

    Elisa Ricci (University of Trento)

    Liqiang Nie

    10:30-10:40

    Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition

    Yi-Chang Chen, Yu-Chuan Chang, Yen-Cheng Chang, Yi-Ren Yeh

    Lei Zhu

    10:40-10:50

    FRENet: Faster Road Extraction of High-Resolution Remote Sensing Images via Real-Time Semantic Segmentation

    Hucheng Liu, Wanfeng Zheng, Zhanbei Cui, Chuang Zhang, Ming Wu

    10:50-11:00

    HiMFR: A Hybrid Masked Face Recognition Through Face Inpainting

    Md Imran Hosen, MD BAHARUL ISLAM

    11:00-11:10

    AdaptiveFashion: Improving Consumer-to-Shop Clothes Retrieval with Adaptive Margin

    Pendar Alirezazadeh, Fadi Dornaika, Abdelmalik Moujahid

    11:10-11:20

    MSF3DDETR: Multi-Sensor Fusion 3D Detection Transformer for Autonomous Driving

    Gopi Krishna Erabati, Helder Araujo

    Peng Hu

    11:20-11:30

    Facial Beauty Prediction Using Hybrid CNN Architectures and Dynamic Robust Loss Function

    Fares Bougourzi, Fadi Dornaika, Cosimo Distante, Abdelmalik Taleb-Ahmed

    11:30-11:40

    Improving Identification Accuracy on Unconstrained Low-Resolution Tiny Faces via Absolute Cosine Similarity

    RAVINDRA KUMAR SONI, Neeta Nain

    11:40-11:50

    P3DAttnNet: Automated Assembly Plan Generation from Video Demonstration

    Abhinav Upadhyay, Priyanshu Abhijit Barua, Alpana Dubey, Shubhashis Sengupta, Suma Mani Kuriakose, Piyush Goenka

    Closing