Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking

1 code implementation • ICCV 2023 • Yiheng Liu, Junta Wu, Yi Fu

Multi-object tracking (MOT) at low frame rates can reduce computational, storage and power overhead to better meet the constraints of edge devices.

Blocking Multi-Object Tracking

Deep learning numerical methods for high-dimensional fully nonlinear PIDEs and coupled FBSDEs with jumps

no code implementations • 30 Jan 2023 • Wansheng Wang, Jie Wang, Jinping Li, Feifei Gao, Yi Fu

We propose a deep learning algorithm for solving high-dimensional parabolic integro-differential equations (PIDEs) and high-dimensional forward-backward stochastic differential equations with jumps (FBSDEJs), where the jump-diffusion process are derived by a Brownian motion and an independent compensated Poisson random measure.

Coherent Loss: A Generic Framework for Stable Video Segmentation

no code implementations • 25 Oct 2020 • Mingyang Qian, Yi Fu, Xiao Tan, YingYing Li, Jinqing Qi, Huchuan Lu, Shilei Wen, Errui Ding

Video segmentation approaches are of great importance for numerous vision tasks especially in video manipulation for entertainment.

Segmentation Semantic Segmentation +2

Exploiting Spatial-Temporal Modelling and Multi-Modal Fusion for Human Action Recognition

no code implementations • 27 Jun 2018 • Dongliang He, Fu Li, Qijie Zhao, Xiang Long, Yi Fu, Shilei Wen

In this challenge, we propose spatial-temporal network (StNet) for better joint spatial-temporal modelling and comprehensively video understanding.

Action Recognition Temporal Action Localization +1