[ECCV 2024] SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition
5:17
Prediction of multi-layer metasurface design using cDCGAN
11:47
[ICCV 2021, Oral 3%] XVFI: eXtreme Video Frame Interpolation (Oral 12min Presentation)
6:53
[arXiv 2023] DyBluRF: (...) for Blurry Monocular Video (6min Presentation)
6:14
[CVPR 2024 Oral] FMA-Net: (...) for Joint Video Super-Resolution and Deblurring
40:01
[SPARO Seminar] Dynamic Spatial Propagation Network for Depth Completion (AAAI 2022)
41:43
VMamba: Visual State Space Model
20:35
US Fighter Jets Equipped with Antigravity Technology Finally Revealed!
42:14