Ming Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ming Li has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Sidan Du
Nanjing University
7 shared publications - Xuejiao Hu
School of Electronic Science and Engineering, Nanjing University, Nanjing, China
5 shared publications - Yang Li
Sichuan Agricultural University
5 shared publications - Jingzhao Dai
School of Electronic Science and Engineering Nanjing University Nanjing China
3 shared publications - Jinghao Cao
School of Electronic Science and Engineering, Nanjing University, Nanjing, China
2 shared publications Yang Li
School of Electronic Science and Engineering Nanjing University Nanjing China
2 shared publications
Latest Publications
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 6051-6066
Enhancing Multi-View Omnidirectional Depth Estimation With Semantic-Aware Cost Aggregation and Spatial Propagation
Omnidirectional depth estimation predicts 360-degree depth information using multiple fisheye cameras arranged in a surround-view configuration. However, due to the lack of reference panorama and differences between the predicted depth viewpoint and input cameras, it is challenging to construct and utilize semantic information to improve depth accuracy, resulting in limited accurate in complex regions such as non-overlapping, weak textures, object boundaries and occlusions. This paper proposes a novel model architecture that effectively extracts and leverages semantic information to enhance the accuracy of omnidirectional depth estimation. Specifically, the proposed algorithm combines the variance and mean of multi-view image features to construct the fused matching cost and utilize both geometry and semantic constraints. The model extracts 360-degree semantic context during matching cost aggregation, and predict the corresponding panoramas jointly with omnidirectional depth maps. A semantic-aware spatial propagation module is then employed to further refine the depth estimation. We leverage a multi-scale multi-task learning strategy to supervise the prediction of omnidirectional depth maps and panoramas jointly. The proposed approach achieves state-of-the-art performance on public datasets, and also demonstrates high-precision results on real-world data. The experiments with varying camera configurations validate the generalization ability and flexibility of the algorithm.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 6051-6066
Enhancing Multi-View Omnidirectional Depth Estimation With Semantic-Aware Cost Aggregation and Spatial Propagation
Omnidirectional depth estimation predicts 360-degree depth information using multiple fisheye cameras arranged in a surround-view configuration. However, due to the lack of reference panorama and differences between the predicted depth viewpoint and input cameras, it is challenging to construct and utilize semantic information to improve depth accuracy, resulting in limited accurate in complex regions such as non-overlapping, weak textures, object boundaries and occlusions. This paper proposes a novel model architecture that effectively extracts and leverages semantic information to enhance the accuracy of omnidirectional depth estimation. Specifically, the proposed algorithm combines the variance and mean of multi-view image features to construct the fused matching cost and utilize both geometry and semantic constraints. The model extracts 360-degree semantic context during matching cost aggregation, and predict the corresponding panoramas jointly with omnidirectional depth maps. A semantic-aware spatial propagation module is then employed to further refine the depth estimation. We leverage a multi-scale multi-task learning strategy to supervise the prediction of omnidirectional depth maps and panoramas jointly. The proposed approach achieves state-of-the-art performance on public datasets, and also demonstrates high-precision results on real-world data. The experiments with varying camera configurations validate the generalization ability and flexibility of the algorithm.
- Open Access
- 13 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
ALTSA: Adaptive Latent-space Teacher - Student Architecture for Emotion Recognition in Conversation
- 13 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessALTSA: Adaptive Latent-space Teacher - Student Architecture for Emotion Recognition in Conversation
- Open Access
- 5 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 139944-139952
OmniOcc: Cylindrical Voxel-Based Semantic Occupancy Prediction for Omnidirectional Vision Systems
Accurate 3D perception is essential for autonomous driving. Traditional methods often struggle with geometric ambiguity due to a lack of geometric prior. To address these challenges, we use omnidirectional depth estimation to introduce geometric prior. Based on the depth information, we propose a Sketch-Coloring framework OmniOcc. Additionally, our approach introduces a cylindrical voxel representation based on polar coordinate to better align with the radial nature of panoramic camera views. To address the lack of fisheye camera dataset in autonomous driving tasks, we also build a virtual scene dataset with six fisheye cameras. Experimental results demonstrate that our Sketch-Coloring network significantly enhances 3D perception performance.
- 5 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 139944-139952
Open AccessOmniOcc: Cylindrical Voxel-Based Semantic Occupancy Prediction for Omnidirectional Vision Systems
Accurate 3D perception is essential for autonomous driving. Traditional methods often struggle with geometric ambiguity due to a lack of geometric prior. To address these challenges, we use omnidirectional depth estimation to introduce geometric prior. Based on the depth information, we propose a Sketch-Coloring framework OmniOcc. Additionally, our approach introduces a cylindrical voxel representation based on polar coordinate to better align with the radial nature of panoramic camera views. To address the lack of fisheye camera dataset in autonomous driving tasks, we also build a virtual scene dataset with six fisheye cameras. Experimental results demonstrate that our Sketch-Coloring network significantly enhances 3D perception performance.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Robust and Flexible Omnidirectional Depth Estimation With Multiple 360‐Degree Cameras
Omnidirectional depth estimation has received much attention from researchers in recent years. However, challenges arise due to camera soiling and variations in camera layouts, affecting the robustness and flexibility of the algorithm. In this paper, we use the geometric constraints and redundant information of multiple 360 cameras to achieve robust and flexible multi‐view omnidirectional depth estimation. We implement two algorithms, in which the two‐stage algorithm obtains initial depth maps by pairwise stereo matching of multiple cameras and fuses the multiple depth maps for the final depth estimation; the one‐stage algorithm adopts spherical sweeping based on hypothetical depths to construct a uniform spherical matching cost of the multi‐camera images and obtain the depth. Additionally, a generalized epipolar equirectangular projection is introduced to simplify the spherical epipolar constraints. To overcome panorama distortion, a spherical feature extractor is implemented. Furthermore, a synthetic 360 dataset of outdoor road scenes is presented, which takes soiled camera lenses and glare into consideration and is more consistent with the real‐world environment. Experiments show that our two algorithms achieve state‐of‐the‐art performance, accurately predicting depth maps even when provided with soiled panorama inputs. The flexibility of the algorithms is experimentally validated in terms of camera layouts and numbers.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Open AccessRobust and Flexible Omnidirectional Depth Estimation With Multiple 360‐Degree Cameras
Omnidirectional depth estimation has received much attention from researchers in recent years. However, challenges arise due to camera soiling and variations in camera layouts, affecting the robustness and flexibility of the algorithm. In this paper, we use the geometric constraints and redundant information of multiple 360 cameras to achieve robust and flexible multi‐view omnidirectional depth estimation. We implement two algorithms, in which the two‐stage algorithm obtains initial depth maps by pairwise stereo matching of multiple cameras and fuses the multiple depth maps for the final depth estimation; the one‐stage algorithm adopts spherical sweeping based on hypothetical depths to construct a uniform spherical matching cost of the multi‐camera images and obtain the depth. Additionally, a generalized epipolar equirectangular projection is introduced to simplify the spherical epipolar constraints. To overcome panorama distortion, a spherical feature extractor is implemented. Furthermore, a synthetic 360 dataset of outdoor road scenes is presented, which takes soiled camera lenses and glare into consideration and is more consistent with the real‐world environment. Experiments show that our two algorithms achieve state‐of‐the‐art performance, accurately predicting depth maps even when provided with soiled panorama inputs. The flexibility of the algorithms is experimentally validated in terms of camera layouts and numbers.
- 10 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 765-769
Distribution-Aware Activity Boundary Representation for Online Detection of Action Start in Untrimmed Videos
The Online Detection of Action Start (ODAS) has attracted the attention of researchers because of its practical applications in areas such as security and emergency response. However, online detection of activity boundaries remains a challenging task due to the inherent ambiguity of boundary definition and the significant imbalance in the number of boundaries and nonboundary points. To address this issue, this study proposes a novel Distribution-aware Activity Boundary Representation (DABR) method that utilizes a continuous probability density function to smooth the probability of moments near activity boundaries. The proposed DABR reduces the penalty for detecting moments near ground-truth boundary points, while increasing the number of samples related to boundary points. Additionally, we introduce a two-stage framework that incorporates class-informed information in temporal localization for more efficient activity boundary localization. Extensive experiments demonstrate that our method achieves state-of-the-art results on two standard datasets, particularly exhibiting a significant improvement of 11.5% at average p-mAP on the THUMOS'14 dataset.
- 10 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 765-769
Distribution-Aware Activity Boundary Representation for Online Detection of Action Start in Untrimmed Videos
The Online Detection of Action Start (ODAS) has attracted the attention of researchers because of its practical applications in areas such as security and emergency response. However, online detection of activity boundaries remains a challenging task due to the inherent ambiguity of boundary definition and the significant imbalance in the number of boundaries and nonboundary points. To address this issue, this study proposes a novel Distribution-aware Activity Boundary Representation (DABR) method that utilizes a continuous probability density function to smooth the probability of moments near activity boundaries. The proposed DABR reduces the penalty for detecting moments near ground-truth boundary points, while increasing the number of samples related to boundary points. Additionally, we introduce a two-stage framework that incorporates class-informed information in temporal localization for more efficient activity boundary localization. Extensive experiments demonstrate that our method achieves state-of-the-art results on two standard datasets, particularly exhibiting a significant improvement of 11.5% at average p-mAP on the THUMOS'14 dataset.
- Open Access
- 6 January 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (2) , 517
CasOmniMVS: Cascade Omnidirectional Depth Estimation with Dynamic Spherical Sweeping
Estimating 360 depth from multiple cameras has been a challenging problem. However, existing methods often adopt a fixed-step spherical sweeping approach with densely sampled spheres and use numerous 3D convolutions in networks, which limits the speed of algorithms in practice. Additionally, obtaining high-precision depth maps of real scenes poses a challenge for the existing algorithms. In this paper, we design a cascade architecture using a dynamic spherical sweeping method that progressively refines the depth estimation from coarse to fine over multiple stages. The proposed method adaptively adjusts sweeping intervals and ranges based on the predicted depth and the uncertainty from the previous stage, resulting in a more efficient cost aggregation performance. The experimental results demonstrated that our method achieved state-of-the-art accuracy with reduced GPU memory usage and time consumption compared to the other methods. Furthermore, we illustrate that our method achieved satisfactory performance on real-world data, despite being trained on synthetic data, indicating its generalization potential and practical applicability.- 6 January 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (2) , 517
Open AccessCasOmniMVS: Cascade Omnidirectional Depth Estimation with Dynamic Spherical Sweeping
Estimating 360 depth from multiple cameras has been a challenging problem. However, existing methods often adopt a fixed-step spherical sweeping approach with densely sampled spheres and use numerous 3D convolutions in networks, which limits the speed of algorithms in practice. Additionally, obtaining high-precision depth maps of real scenes poses a challenge for the existing algorithms. In this paper, we design a cascade architecture using a dynamic spherical sweeping method that progressively refines the depth estimation from coarse to fine over multiple stages. The proposed method adaptively adjusts sweeping intervals and ranges based on the predicted depth and the uncertainty from the previous stage, resulting in a more efficient cost aggregation performance. The experimental results demonstrated that our method achieved state-of-the-art accuracy with reduced GPU memory usage and time consumption compared to the other methods. Furthermore, we illustrate that our method achieved satisfactory performance on real-world data, despite being trained on synthetic data, indicating its generalization potential and practical applicability. - 26 January 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (17) , 25615-25650
The multi-learning for food analyses in computer vision: a survey
- 26 January 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (17) , 25615-25650
The multi-learning for food analyses in computer vision: a survey
- 2 November 2022
- Published by Springer Nature
- p. 197-213
MODE: Multi-view Omnidirectional Depth Estimation with 360$^\circ $ Cameras- 2 November 2022
- Published by Springer Nature
- p. 197-213
MODE: Multi-view Omnidirectional Depth Estimation with 360$^\circ $ Cameras- 24 March 2022
- Published by Elsevier in Neurocomputing
- Vol. 491, 395-413
Online human action detection and anticipation in videos: A survey
- 24 March 2022
- Published by Elsevier in Neurocomputing
- Vol. 491, 395-413
Online human action detection and anticipation in videos: A survey
- 1 July 2011
- Published by Trans Tech Publications, Ltd. in Advanced Materials Research
- Vol. 298, 7-12
A New Model of Discribing the Band Gap Bowing of III Nitride Alloys
In the paper, a model is developed to discribe the band gap energy of Ⅲ nitride alloys. A new parameter A is used to discribe the band gap bowing. The new bowing parameter A is obtained by fitting the experimental values of the band gap energy. AAlGaN =0.46, AInGaN =0.59 and AInAlN =1.90 are obtained by fitting the experimental values of the band gap energy for AlGaN, InGaN and InAlN, respectively. The model is also suitable to discribe the band gap energy of other Ⅲ-Ⅴ ternary alloys.
- 1 July 2011
- Published by Trans Tech Publications, Ltd. in Advanced Materials Research
- Vol. 298, 7-12
A New Model of Discribing the Band Gap Bowing of III Nitride Alloys
In the paper, a model is developed to discribe the band gap energy of Ⅲ nitride alloys. A new parameter A is used to discribe the band gap bowing. The new bowing parameter A is obtained by fitting the experimental values of the band gap energy. AAlGaN =0.46, AInGaN =0.59 and AInAlN =1.90 are obtained by fitting the experimental values of the band gap energy for AlGaN, InGaN and InAlN, respectively. The model is also suitable to discribe the band gap energy of other Ⅲ-Ⅴ ternary alloys.