1 code implementation • 12 Jan 2024 • Huiyuan Fu, Kuilong Cui, Chuanming Wang, Mengshi Qi, Huadong Ma
With the rapid advancements in deep learning technologies, person re-identification (ReID) has witnessed remarkable performance improvements.
no code implementations • 5 Jan 2024 • Yuxin Yang, Pengfei Zhu, Mengshi Qi, Huadong Ma
To uncover latent motion patterns in human behavior, we introduce a novel memory-based method, named Motion Pattern Priors Memory Network.
1 code implementation • 5 Jan 2024 • Qi An, Mengshi Qi, Huadong Ma
In recent years, there has been growing interest in the video-based action quality assessment (AQA).
no code implementations • 4 Jan 2024 • Chuanming Wang, Yuxin Yang, Mengshi Qi, Huadong Ma
Therefore, we pioneer a cloud-edge collaborative inference framework for ReID systems and particularly propose a distribution-aware correlation modeling network (DaCM) to make the desired image return to the cloud server as soon as possible via learning to model the spatial-temporal correlations among instances.
no code implementations • 1 Dec 2023 • Yaoyao Zhong, Mengshi Qi, Rui Wang, Yuhan Qiu, Yang Zhang, Huadong Ma
Video Internet of Things (VIoT) has shown full potential in collecting an unprecedented volume of video data.
no code implementations • 6 Jun 2023 • Haowen Wang, Zhengping Che, Yufan Yang, Mingyuan Wang, Zhiyuan Xu, XIUQUAN QIAO, Mengshi Qi, Feifei Feng, Jian Tang
Raw depth images captured in indoor scenarios frequently exhibit extensive missing values due to the inherent limitations of the sensors and environments.
no code implementations • 22 Mar 2023 • Wulian Yun, Mengshi Qi, Chuanming Wang, Huadong Ma
Weakly-supervised temporal action localization aims to locate action regions and identify action categories in untrimmed videos simultaneously by taking only video-level labels as the supervision.
Pseudo Label Weakly-supervised Temporal Action Localization +1
no code implementations • 20 Mar 2023 • Changsheng Lv, Mengshi Qi, Xia Li, Zhengyuan Yang, Huadong Ma
In this paper, we propose a novel model called SGFormer, Semantic Graph TransFormer for point cloud-based 3D scene graph generation.
no code implementations • ICCV 2023 • Pengfei Zhu, Mengshi Qi, Xia Li, Weijian Li, Huadong Ma
Predicting attention regions of interest is an important yet challenging task for self-driving systems.
no code implementations • 30 Apr 2022 • Wulian Yun, Mengshi Qi, Chuanming Wang, Huiyuan Fu, Huadong Ma
Meanwhile, we design a Multi-Scale Residual Structure to preserve multiple aspects of information at different stages, which contains a Temporal Features Aggregation Module to summarize the dynamic representation.
no code implementations • CVPR 2022 • Haowen Wang, Mingyuan Wang, Zhengping Che, Zhiyuan Xu, XIUQUAN QIAO, Mengshi Qi, Feifei Feng, Jian Tang
In this paper, we design a novel two-branch end-to-end fusion network, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map.
no code implementations • 21 Dec 2020 • Mengshi Qi, Edoardo Remelli, Mathieu Salzmann, Pascal Fua
Deep learning-solutions for hand-object 3D pose and shape estimation are now very effective when an annotated dataset is available to train them to handle the scenarios and lighting conditions they will encounter at test time.
Generative Adversarial Network Unsupervised Domain Adaptation
no code implementations • CVPR 2020 • Mengshi Qi, Jie Qin, Yu Wu, Yi Yang
Trajectory forecasting and imputation are pivotal steps towards understanding the movement of human and objects, which are quite challenging since the future trajectories and missing values in a temporal sequence are full of uncertainties, and the spatial-temporally contextual correlation is hard to model.
no code implementations • CVPR 2019 • Mengshi Qi, Yunhong Wang, Jie Qin, Annan Li
In recent years, scene parsing has captured increasing attention in computer vision.
no code implementations • CVPR 2019 • Mengshi Qi, Weijian Li, Zhengyuan Yang, Yunhong Wang, Jiebo Luo
Scene graph generation refers to the task of automatically mapping an image into a semantic structural graph, which requires correctly labeling each extracted object and their interaction relationships.
no code implementations • ECCV 2018 • Mengshi Qi, Jie Qin, Annan Li, Yunhong Wang, Jiebo Luo, Luc van Gool
Group activity recognition plays a fundamental role in a variety of applications, e. g. sports video analysis and intelligent surveillance.