MP1.L3: Perception Models in Visual AI Systems - I
Mon, 28 Oct, 14:30 - 16:00 Gulf Standard Time (UTC +4)
Location: Lecture Room 3
Session Type: Lecture
Session Chair: Hanseok Ko, Korea University
Track: Visual Artificial Intelligence
Click the to view the manuscript on IEEE Xplore Open Preview
Mon, 28 Oct, 14:30 - 14:48 Gulf Standard Time (UTC +4)

MP1.L3.1: MVAFormer: RGB-Based Multi-View Spatio-Temporal Action Recognition with Transformer
Taiga Yamane, Satoshi Suzuki, Ryo Masumura, Shotaro Tora, NTT Corporation, Japan
Mon, 28 Oct, 14:48 - 15:06 Gulf Standard Time (UTC +4)

MP1.L3.2: Prune Channel and Distill: Discriminative Knowledge Distillation for Semantic Segmentation
Bokyeung Lee, Kyungdeuk Ko, Jonghwan Hong, Hanseok Ko, Korea University, Korea, Republic of
Mon, 28 Oct, 15:06 - 15:24 Gulf Standard Time (UTC +4)

MP1.L3.3: TDAD: TRIDENT DISTILLATIONS FOR ANOMALY DETECTION
Wenrui Hu, China Mobile Research Institute, China; Yuan Xie, East China Normal University, China; Wei Yu, China Mobile Research Institute, China
Mon, 28 Oct, 15:24 - 15:42 Gulf Standard Time (UTC +4)

MP1.L3.4: NEURAL MESH FUSION: UNSUPERVISED 3D PLANAR SURFACE UNDERSTANDING
Farhad G. Zanjani, Hong Cai, Yinhao Zhu, Leyla Mirvakhabova, Fatih Porikli, Qualcomm Technologies Inc., Netherlands
Mon, 28 Oct, 15:42 - 16:00 Gulf Standard Time (UTC +4)

MP1.L3.5: CONTRAST-GUIDED WIREFRAME PARSING
Xueyuan Chen, Baojiang Zhong, Soochow University, China