Shixiang Tang

Shixiang Tang

Auto-generated profile, based on publicly available information

Shixiang Tang

Shanghai Artificial Intelligence Laboratory

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2025
Verified
Conference Paper
Open access
PDF file
HSHaoyang Su
Haoyang Su
RCRenqi Chen
Renqi Chen
STShixiang Tang
Shixiang Tang
ZYZhenfei Yin
Zhenfei Yin
XZXinzhe Zheng
Xinzhe Zheng
NDNanqing Dong
Nanqing Dong
Haoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, Philip Torr, Bowen Zhou, Nanqing Dong. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

18 March 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YWYizhou Wang
Yizhou Wang
YWYixuan Wu
Yixuan Wu
WHWeizhen He
Weizhen He
XGXun Guo
Xun Guo
FZFeng Zhu
Feng Zhu
STShixiang Tang
Shixiang Tang
Human-centric perception tasks, e.g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis. There is a recent surge to develop human-centric foundation models that can benefit a broad range of human-centric perception tasks. While many human-centric foundation models have achieved success, they did not explore 3D and vision-language tasks for human-centric and required task-specific finetuning. These limitations restrict their application to more downstream tasks and situations. To tackle these problems, we present Hulk, the first multimodal human-centric generalist model, capable of addressing 2D vision, 3D vision, skeleton-based, and vision-language tasks without task-specific finetuning. The key to achieving this is condensing various task-specific heads into two general heads, one for discrete representations, e.g., languages, and the other for continuous representations, e.g., location coordinates. The outputs of two heads can be further stacked into four distinct input and output modalities. This uniform representation enables Hulk to treat diverse human-centric tasks as modality translation, integrating knowledge across a wide range of tasks. Comprehensive evaluations of Hulk on 12 benchmarks covering 8 human-centric tasks demonstrate the superiority of our proposed method, achieving state-of-the-art performance in 11 benchmarks.

6 December 2024
Verified
Book Chapter
Closed access
PDF file
SZSha Zhang
Sha Zhang
DHDi Huang
Di Huang
JDJiajun Deng
Jiajun Deng
STShixiang Tang
Shixiang Tang
WOWanli Ouyang
Wanli Ouyang
YZYanyong Zhang
Yanyong Zhang

1 January 2025 in Physics of Fluids
Verified
Journal Article
Closed access
WCWenbo Cao
Wenbo Cao
XSXianglin Shan
Xianglin Shan
STShixiang Tang
Shixiang Tang
WOWanli Ouyang
Wanli Ouyang
Weiwei ZhangWeiwei Zhang
Weiwei Zhang
Physics-informed neural networks (PINNs) have recently emerged as popular methods for solving forward and inverse problems governed by partial differential equations. However, PINNs still face significant challenges when solving high-Reynolds-number flows with multi-scale phenomena. In our previous work, we proposed time-stepping-oriented neural network (TSONN), which transforms the ill-conditioned optimization problem of PINNs into a series of well-conditioned sub-problems, successfully solving the three-dimensional laminar flow around a wing at a Reynolds number of 5000. In this paper, we extend TSONN to high-Reynolds-number wall-bounded turbulence around airfoils governed by the Reynolds-Averaged Navier–Stokes (RANS) equations with the Spalart–Allmaras (SA) turbulence model. Specifically, we propose a semi-coupled strategy to address the convergence issues caused by the turbulence model. This strategy updates certain terms in the turbulence model only during the outer iterations while freezing these terms in the inner iterations, thereby avoiding excessive gradients that could jeopardize network optimization. Using this strategy, we successfully solve turbulence around airfoils. Furthermore, we address a parametric problem with respect to the angle of attack. Our experimental results demonstrate that the computational cost of solving this parametric problem using TSONN is comparable to that of solving a single flow problem, highlighting its efficiency in solving parametric problems. To the best of our knowledge, this is the first time that a PINN-like method has been used to solve the RANS equations coupled complex turbulence model, paving the way for fluid-related engineering problems.

7 February 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
WHWeizhen He
Weizhen He
YDYiheng Deng
Yiheng Deng
YYYunfeng Yan
Yunfeng Yan
FZFeng Zhu
Feng Zhu
YWYizhou Wang
Yizhou Wang
STShixiang Tang
Shixiang Tang
Recently, person re-identification (ReID) has witnessed fast development due to its broad practical applications and proposed various settings, e.g., traditional ReID, clothes-changing ReID, and visible-infrared ReID. However, current studies primarily focus on single specific tasks, which limits model applicability in real-world scenarios. This paper aims to address this issue by introducing a novel instruct-ReID task that unifies 6 existing ReID tasks in one model and retrieves images based on provided visual or textual instructions. Instruct-ReID is the first exploration of a general ReID setting, where 6 existing ReID tasks can be viewed as special cases by assigning different instructions. To facilitate research in this new instruct-ReID task, we propose a large-scale OmniReID++ benchmark equipped with diverse data and comprehensive evaluation methods, e.g., task-specific and task-free evaluation settings. In the task-specific evaluation setting, gallery sets are categorized according to specific ReID tasks. We propose a novel baseline model, IRM, with an adaptive triplet loss to handle various retrieval tasks within a unified framework. For task-free evaluation setting, where target person images are retrieved from task-agnostic gallery sets, we further propose a new method called IRM++ with novel memory bank-assisted learning. Extensive evaluations of IRM and IRM++ on OmniReID++ benchmark demonstrate the superiority of our proposed methods, achieving state-of-the-art performance on 10 test sets.

23 July 2024 in Vicinagearth
Verified
Journal Article
Open access
PDF file
Yuenan HouYuenan Hou
Yuenan Hou
XHXiaoshui Huang
Xiaoshui Huang
STShixiang Tang
Shixiang Tang
THTong He
Tong He
WOWanli Ouyang
Wanli Ouyang
Recent years have witnessed a signifcant breakthrough in the 3D domain. To track the most recent advances in the 3D field, in this paper, we provide a comprehensive survey of recent advances in the 3D feld, which encompasses a wide collection of topics, including diverse pre-training strategies, backbone designs and downstream tasks. Compared to the previous literature review on point cloud, our survey is more comprehensive. Our survey consists of the 3D pre-training methods, various downstream tasks, popular benchmarks, evaluation metrics as well as several promising future directions. We hope the survey can serve as the cornerstone for both academia and industry.