no code implementations • 20 Oct 2023 • Xinyu Zhang, Li Wang, Zhiqiang Jiang, Kun Dai, Tao Xie, Lei Yang, Wenhao Yu, Yang shen, Jun Li
However, these methods only integrate long-range context information among keypoints with a fixed receptive field, which constrains the network from reconciling the importance of features with different receptive fields to realize complete image perception, hence limiting the matching accuracy.
1 code implementation • ICCV 2023 • Tao Xie, Kun Dai, Siyi Lu, Ke Wang, Zhiqiang Jiang, Jinghan Gao, Dedong Liu, Jie Xu, Lijun Zhao, Ruifeng Li
In this work, we seek to predict camera poses across scenes with a multi-task learning manner, where we view the localization of each scene as a new task.
1 code implementation • 14 Feb 2023 • Jianhua Yang, Kun Dai
Designing a real-time framework for the spatio-temporal action detection task is still a challenge.
1 code implementation • 12 Feb 2023 • Kun Dai, Tao Xie, Ke Wang, Zhiqiang Jiang, Ruifeng Li, Lijun Zhao
Local feature matching is an essential component in many visual applications.
1 code implementation • 8 Jan 2023 • Tao Xie, Kun Dai, Ke Wang, Ruifeng Li, Lijun Zhao
In this work, we propose DeepMatcher, a deep Transformer-based network built upon our investigation of local feature matching in detector-free methods.
no code implementations • CVPR 2023 • Tao Xie, Shiguang Wang, Ke Wang, Linqi Yang, Zhiqiang Jiang, Xingcheng Zhang, Kun Dai, Ruifeng Li, Jian Cheng
In this work, we show that it is feasible to perform multiple tasks concurrently on point cloud with a straightforward yet effective multi-task network.
no code implementations • ICCV 2023 • Tao Xie, Ke Wang, Siyi Lu, Yukun Zhang, Kun Dai, Xiaoyu Li, Jie Xu, Li Wang, Lijun Zhao, Xinyu Zhang, Ruifeng Li
Finally, we propose a sign-based gradient surgery to promote the training of CO-Net, thereby emphasizing the usage of task-shared parameters and guaranteeing that each task can be thoroughly optimized.