Mingsheng Long

Mingsheng Long

Auto-generated profile, based on publicly available information

Mingsheng Long

Tsinghua University

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
5 April 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YWYunbo Wang
Yunbo Wang
HWHaixu Wu
Haixu Wu
JZJianjin Zhang
Jianjin Zhang
ZGZhifeng Gao
Zhifeng Gao
JWJianmin Wang
Jianmin Wang
MLMingsheng Long
Mingsheng Long
The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical context, where the visual dynamics are believed to have modular structures that can be learned with compositional subsystems. This paper models these structures by presenting PredRNN, a new recurrent network, in which a pair of memory cells are explicitly decoupled, operate in nearly independent transition manners, and finally form unified representations of the complex environment. Concretely, besides the original memory cell of LSTM, this network is featured by a zigzag memory flow that propagates in both bottom-up and top-down directions across all layers, enabling the learned visual dynamics at different levels of RNNs to communicate. It also leverages a memory decoupling loss to keep the memory cells from learning redundant features. We further propose a new curriculum learning strategy to force PredRNN to learn long-term dynamics from context frames, which can be generalized to most sequence-to-sequence models. We provide detailed ablation studies to verify the effectiveness of each component. Our approach is shown to obtain highly competitive results on five datasets for both action-free and action-conditioned predictive learning scenarios.

5 September 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
MLMingsheng Long
Mingsheng Long
YCYue Cao
Yue Cao
ZCZhangjie Cao
Zhangjie Cao
JWJianmin Wang
Jianmin Wang
MJMichael I. Jordan
Michael I. Jordan
Domain adaptation generalizes a learning machine across source domain and target domain under different distributions. Recent studies reveal that deep neural networks can learn transferable features generalizing well to similar novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, feature transferability drops significantly in higher task-specific layers with increasing domain discrepancy. To formally reduce the dataset shift and enhance the feature transferability in task-specific layers, this paper presents a novel framework for deep adaptation networks, which generalizes deep convolutional neural networks to domain adaptation. The framework embeds the deep features of all task-specific layers to reproducing kernel Hilbert spaces (RKHSs) and optimally match different domain distributions. The deep features are made more transferable by exploring low-density separation of target-unlabeled data and very deep architectures, while the domain discrepancy is further reduced using multiple kernel learning for maximal testing power of kernel embedding matching. This leads to a minimax game framework that learns transferable features with statistical guarantees, and scales linearly with unbiased estimate of kernel embedding. Extensive empirical evidence shows that the proposed networks yield state-of-the-art results on standard visual domain adaptation benchmarks.

5 July 2023 in Nature
Verified
Journal Article
Open access
PDF file
YZYuchen Zhang
Yuchen Zhang
MLMingsheng Long
Mingsheng Long
KCKaiyuan Chen
Kaiyuan Chen
LXLanxiang Xing
Lanxiang Xing
RJRonghua Jin
Ronghua Jin
JWJianmin Wang
Jianmin Wang
Extreme precipitation is a considerable contributor to meteorological disasters and there is a great need to mitigate its socioeconomic effects through skilful nowcasting that has high resolution, long lead times and local details1–3. Current methods are subject to blur, dissipation, intensity or location errors, with physics-based numerical methods struggling to capture pivotal chaotic dynamics such as convective initiation4 and data-driven learning methods failing to obey intrinsic physical laws such as advective conservation5. We present NowcastNet, a nonlinear nowcasting model for extreme precipitation that unifies physical-evolution schemes and conditional-learning methods into a neural-network framework with end-to-end forecast error optimization. On the basis of radar observations from the USA and China, our model produces physically plausible precipitation nowcasts with sharp multiscale patterns over regions of 2,048 km × 2,048 km and with lead times of up to 3 h. In a systematic evaluation by 62 professional meteorologists from across China, our model ranks first in 71% of cases against the leading methods. NowcastNet provides skilful forecasts at light-to-heavy rain rates, particularly for extreme-precipitation events accompanied by advective or convective processes that were previously considered intractable.

12 November 2020
Verified
Book Chapter
Closed access
PDF file
YJYing Jin
Ying Jin
XWXimei Wang
Ximei Wang
MLMingsheng Long
Mingsheng Long
JWJianmin Wang
Jianmin Wang

7 October 2018
Verified
Book Chapter
Closed access
PDF file
ZCZhangjie Cao
Zhangjie Cao
LMLijia Ma
Lijia Ma
MLMingsheng Long
Mingsheng Long
JWJianmin Wang
Jianmin Wang

5 June 2023 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
HWHaixu Wu
Haixu Wu
HZHang Zhou
Hang Zhou
MLMingsheng Long
Mingsheng Long
JWJianmin Wang
Jianmin Wang