Ming‐Ming Cheng

53k citations
253 papers · 40k · 43 hit papers · h-index 86

Impact in

    • Visual Attention and Saliency Detection
    • Advanced Neural Network Applications
    • Video Surveillance and Tracking Methods
    • Medical Image Segmentation Techniques
    • Advanced Image and Video Retrieval Techniques
    • Generative Adversarial Networks and Image Synthesis
    • Remote-Sensing Image Classification

Papers in

Ming‐Ming Cheng

232 papers receiving 39.4k citations

Ming‐Ming Cheng's Hit Papers

YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection 2025 · 104 citations
1040+1+3Years since publication5001k1.5k

Peers

Ming‐Ming Cheng
Comparison fields: 5 of 163
  • Computer Vision and Pattern Recognition 31k
  • Media Technology 1.7k
  • Artificial Intelligence 3.1k
  • Industrial and Manufacturing Engineering 832
  • Computer Graphics and Computer-Aided Design 346
Replace Jingdong Wang with:
Jingdong Wang China
In So Kweon South Korea
Iasonas Kokkinos France
Georgia Gkioxari United States
Jian Zhong Sun China
Xinggang Wang China
Joon‐Young Lee South Korea
Bharath Hariharan United States
Stephen Ching-Feng Lin China
Qi Chuan Tian China
Ming‐Ming Cheng relative to Jingdong Wang China Jingdong Wang's profile →
Citations per field
00.5×1.5×2×2.3×
Jingdong Wang · 1×
Citations per year

Countries citing papers authored by Ming‐Ming Cheng

Since Specialization
Citations

This map shows the geographic impact of Ming‐Ming Cheng's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Ming‐Ming Cheng with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ming‐Ming Cheng more than expected).

Fields of papers citing papers by Ming‐Ming Cheng

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Ming‐Ming Cheng. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Ming‐Ming Cheng. The network helps show where Ming‐Ming Cheng may publish in the future.

Co-authors

The 25 scholars most cited alongside Ming‐Ming Cheng, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Ming‐Ming Cheng Line = papers co-authored together Ming‐Ming Cheng links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown

Showing the 20 most-cited of 253 papers — load more, or switch the sort, to bring in the rest.

#Work
1
Res2Net: A New Multi-Scale Backbone Architecture
Hit paper breakdown →
20192585
2
Global contrast based salient region detection
Hit paper breakdown →
20112466
3
Global Contrast Based Salient Region Detection
Hit paper breakdown →
20142059
4
Attention mechanisms in computer vision: A survey
Hit paper breakdown →
20221769
5
Structure-Measure: A New Way to Evaluate Foreground Maps
Hit paper breakdown →
20171533
6
Enhanced-alignment Measure for Binary Foreground Map Evaluation
Hit paper breakdown →
20181275
7
EGNet: Edge Guidance Network for Salient Object Detection
Hit paper breakdown →
20191005
8
Deeply Supervised Salient Object Detection with Short Connections
Hit paper breakdown →
2017909
9
A Simple Pooling-Based Design for Real-Time Salient Object Detection
Hit paper breakdown →
2019902
10
BING: Binarized Normed Gradients for Objectness Estimation at 300fps
Hit paper breakdown →
2014820
11
Struck: Structured Output Tracking with Kernels
Hit paper breakdown →
2015800
12
Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
Hit paper breakdown →
2017688
13
Visual attention network
Hit paper breakdown →
2023683
14
Richer Convolutional Features for Edge Detection
Hit paper breakdown →
2017640
15
Camouflaged Object Detection
Hit paper breakdown →
2020619
16
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization
Hit paper breakdown →
2021609
17
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
Hit paper breakdown →
2020595
18
Richer Convolutional Features for Edge Detection
Hit paper breakdown →
2018575
19
Large Selective Kernel Network for Remote Sensing Object Detection
Hit paper breakdown →
2023565
20
Deeply Supervised Salient Object Detection with Short Connections
Hit paper breakdown →
2018554

About Ming‐Ming Cheng

Ming‐Ming Cheng is a scholar working on Computer Vision and Pattern Recognition, Computer Graphics and Computer-Aided Design, Artificial Intelligence, Computational Mechanics and Aerospace Engineering, having authored 253 papers that have together received 40k indexed citations. Recurring topics across this work include Advanced Neural Network Applications (90 papers), Visual Attention and Saliency Detection (53 papers), Domain Adaptation and Few-Shot Learning (27 papers), Generative Adversarial Networks and Image Synthesis (25 papers), 3D Shape Modeling and Analysis (23 papers), Computer Graphics and Visualization Techniques (15 papers), Medical Image Segmentation Techniques (10 papers) and Advanced Image and Video Retrieval Techniques (9 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (31k citations), Media Technology (1.7k citations), Artificial Intelligence (3.1k citations), Industrial and Manufacturing Engineering (832 citations) and Computer Graphics and Computer-Aided Design (346 citations). Ming‐Ming Cheng has collaborated with scholars based in China, United Kingdom and United States. Frequent co-authors include Shi‐Min Hu, Philip H. S. Torr, Deng-Ping Fan, Qibin Hou, Niloy J. Mitra, Xiaolei Huang, Yun Liu, Ali Borji, Jiangjiang Liu and Shanghua Gao. Their work appears in journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Image Processing, Computational Visual Media, International Journal of Computer Vision and ACM Transactions on Graphics.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact