1 code implementation • CVPR 2020 • Sida Peng, Wen Jiang, Huaijin Pi, Xiuli Li, Hujun Bao, Xiaowei Zhou
Based on deep snake, we develop a two-stage pipeline for instance segmentation: initial contour proposal and contour deformation, which can handle errors in object localization.
Ranked #2 on Semantic Contour Prediction on Sbd val
1 code implementation • 17 Jul 2022 • Zizhang Li, Mengmeng Wang, Huaijin Pi, Kechun Xu, Jianbiao Mei, Yong liu
However, the redundant parameters within the network structure can cause a large model size when scaling up for desirable performance.
Ranked #4 on Video Reconstruction on UVG
no code implementations • 1 Jan 2021 • Hanqing Yang, Huaijin Pi, SABA GHORBANI BARZEGAR, Yu Zhang
This paper analyzes the serious false positive problem in OSOD and proposes a Focus on Classification One-Shot Object Detection (FOC OSOD) framework, which is improved in two important aspects: (1) classification cascade head with the fixed IoU threshold can enhance the robustness of classification by comparing multiple close regions; (2) classification region deformation on the query feature and the reference feature to obtain a more effective comparison region.
no code implementations • 15 Nov 2021 • Huaijin Pi, Huiyu Wang, Yingwei Li, Zizhang Li, Alan Yuille
In order to effectively search in this huge architecture space, we propose Hierarchical Sampling for better training of the supernet.
no code implementations • ICCV 2023 • Huaijin Pi, Sida Peng, Minghui Yang, Xiaowei Zhou, Hujun Bao
This paper presents a novel approach to generating the 3D motion of a human interacting with a target object, with a focus on solving the challenge of synthesizing long-range and diverse motions, which could not be fulfilled by existing auto-regressive models or path planning-based methods.