Chong Di
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Chong Di has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Shenghong Li
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China
6 shared publications - Pengyao Xu
Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
5 shared publications Shenghong Li
Shanghai Jiao Tong University
5 shared publications- Chao Chen
Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China
3 shared publications Fangqi Li
3 shared publications- Fangqi Li
Shanghai Jiao Tong University, Shanghai, China
2 shared publications
Latest Publications
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-12
Does multi-modal fusion always work - a multi-modal decoupled learning neural network (MDLNN) for the detection of fake news
The detection of fake news on social media is becoming progressively essential. Current multi-modal detection methods emphasize the learning of complementarity across heterogeneous modalities or the extraction of uncertainty within them to enhance integration, which neglects the coupling and dynamic characteristics of multi-modal content and the interactive mechanisms between them. Inspired by human logical inference perception, we propose a novel multi-modal decoupled learning neural network (MDLNN) to enhance comprehension of coupled multi-modal content. MDLNN primarily comprises three modules. The multi-modal feature extraction module with decoupled learning (MDL) aims at extracting detailed informative features from multi-modal content through a decoupled learning process and facilitates trusted integration at the feature level. The multi-modal feature fusion module with gating units (MGU) seeks to enhance the comprehension of multi-modal content by modeling three intricate interactive mechanisms of informative features and facilitates trusted integration at the decision level. The fake news detection module (FND) focuses on generating detection results and ensures event invariance for multi-modal joint features. Comprehensive qualitative and quantitative experiments on two datasets demonstrate the superior performance of MDLNN.
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-12
Does multi-modal fusion always work - a multi-modal decoupled learning neural network (MDLNN) for the detection of fake news
The detection of fake news on social media is becoming progressively essential. Current multi-modal detection methods emphasize the learning of complementarity across heterogeneous modalities or the extraction of uncertainty within them to enhance integration, which neglects the coupling and dynamic characteristics of multi-modal content and the interactive mechanisms between them. Inspired by human logical inference perception, we propose a novel multi-modal decoupled learning neural network (MDLNN) to enhance comprehension of coupled multi-modal content. MDLNN primarily comprises three modules. The multi-modal feature extraction module with decoupled learning (MDL) aims at extracting detailed informative features from multi-modal content through a decoupled learning process and facilitates trusted integration at the feature level. The multi-modal feature fusion module with gating units (MGU) seeks to enhance the comprehension of multi-modal content by modeling three intricate interactive mechanisms of informative features and facilitates trusted integration at the decision level. The fake news detection module (FND) focuses on generating detection results and ensures event invariance for multi-modal joint features. Comprehensive qualitative and quantitative experiments on two datasets demonstrate the superior performance of MDLNN.
- 22 September 2025
- Published by Elsevier in Measurement
- Vol. 257
Thrust force synthesis-based motion control for a voice-coil actuator on a reciprocating rig with lumped disturbing-force compensation
- 22 September 2025
- Published by Elsevier in Measurement
- Vol. 257
Thrust force synthesis-based motion control for a voice-coil actuator on a reciprocating rig with lumped disturbing-force compensation
- Open Access
- 9 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 700-704
Fall intention recognition based on semantic interval localization via hard attention for robot-assisted walking
In the care of the elderly or disabilities, fall prevention through wearable sensors has been a key research direction. However, previous studies mainly focused on the detection of the completed fall activity, and could not effectively recognize the action when it just happened. Therefore, based on the acceleration sensor, this article designs a network for acceleration signals, focusing on the recognition of fall action just occurred, so as to achieve the capture of the action before it is completed, which is called fall intention recognition. Inspired by the field of computer vision— fine-grained classification, the recognition of picture categories only needs to pay attention to the unique feature region of the category. Similarly, the recognition of an action does not need the entire and complete signal sequence, but only needs to pay attention to the semantic interval that is different from other activities. In other words, it is the segment when the fall action starts, because the acceleration data varies with the direction of the fall. At the same time, acceleration data, especially those collected on the body, are prone to external interference, so this article dose not abandon the pre-fall data, also combines with linear acceleration data, which considered all of them are distinguishing features of fall intention. It is verified on the UniMiB SHAR standard dataset, and the experimental results show that the fall intention recognition algorithm in this paper is effective.
- 9 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 700-704
Open AccessFall intention recognition based on semantic interval localization via hard attention for robot-assisted walking
In the care of the elderly or disabilities, fall prevention through wearable sensors has been a key research direction. However, previous studies mainly focused on the detection of the completed fall activity, and could not effectively recognize the action when it just happened. Therefore, based on the acceleration sensor, this article designs a network for acceleration signals, focusing on the recognition of fall action just occurred, so as to achieve the capture of the action before it is completed, which is called fall intention recognition. Inspired by the field of computer vision— fine-grained classification, the recognition of picture categories only needs to pay attention to the unique feature region of the category. Similarly, the recognition of an action does not need the entire and complete signal sequence, but only needs to pay attention to the semantic interval that is different from other activities. In other words, it is the segment when the fall action starts, because the acceleration data varies with the direction of the fall. At the same time, acceleration data, especially those collected on the body, are prone to external interference, so this article dose not abandon the pre-fall data, also combines with linear acceleration data, which considered all of them are distinguishing features of fall intention. It is verified on the UniMiB SHAR standard dataset, and the experimental results show that the fall intention recognition algorithm in this paper is effective.
- Open Access
- 9 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 621-625
S-RRT*: An improved real-time robot path planning algorithm using sector offset sampling
In order to solve the problem of real-time path planning, the algorithm based on sampling is widely used in this field. The RRT* algorithm, as a variant of the RRT algorithm, provides asymptotic optimality. In view of the real-time path planning problem, most of the previous researches directly start from the perspective of compression environment and changing RRT* rewire strategy, but ignore the influence of RRT* sampling blindness on path planning, resulting in slow algorithm convergence speed and high path redundancy. In order to overcome these problems, S-RRT* is proposed in this paper. S-RRT* is an improvement of RT-RRT*. In order to reduce the inefficiency of tree expansion, S-RRT* adopts the sector space probability weight sampling strategy and bias strategy. In terms of path optimization, the way of connecting new nodes to the tree is improved and a new rewiring algorithm from the root node is proposed to shorten the path length. The simulation results show that our algorithm is effective in most environments and provides a new way to solve the real-time path planning problem.
- 9 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 621-625
Open AccessS-RRT*: An improved real-time robot path planning algorithm using sector offset sampling
In order to solve the problem of real-time path planning, the algorithm based on sampling is widely used in this field. The RRT* algorithm, as a variant of the RRT algorithm, provides asymptotic optimality. In view of the real-time path planning problem, most of the previous researches directly start from the perspective of compression environment and changing RRT* rewire strategy, but ignore the influence of RRT* sampling blindness on path planning, resulting in slow algorithm convergence speed and high path redundancy. In order to overcome these problems, S-RRT* is proposed in this paper. S-RRT* is an improvement of RT-RRT*. In order to reduce the inefficiency of tree expansion, S-RRT* adopts the sector space probability weight sampling strategy and bias strategy. In terms of path optimization, the way of connecting new nodes to the tree is improved and a new rewiring algorithm from the root node is proposed to shorten the path length. The simulation results show that our algorithm is effective in most environments and provides a new way to solve the real-time path planning problem.
- 29 October 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 282
Learning automata-accelerated greedy algorithms for stochastic submodular maximization
- 29 October 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 282
Learning automata-accelerated greedy algorithms for stochastic submodular maximization
- 22 September 2023
- Published by Springer Nature
- p. 65-76
An Auxiliary Modality Based Text-Image Matching Methodology for Fake News Detection
- 22 September 2023
- Published by Springer Nature
- p. 65-76
An Auxiliary Modality Based Text-Image Matching Methodology for Fake News Detection
- 1 July 2022
- Published by Springer Nature
- p. 207-214
An Efficient Learning Automaton Scheme for Massive-Action Environments
- 1 July 2022
- Published by Springer Nature
- p. 207-214
An Efficient Learning Automaton Scheme for Massive-Action Environments
- 30 March 2022
- Published by Springer Nature
- p. 516-524
An Efficient Learning Automaton Scheme for Massive-Action Environments
- 30 March 2022
- Published by Springer Nature
- p. 516-524
An Efficient Learning Automaton Scheme for Massive-Action Environments
- 27 March 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 34 (9) , 6811-6824
A novel reduced parameter s-model of estimator learning automata in the switching non-stationary environment
- 27 March 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 34 (9) , 6811-6824
A novel reduced parameter s-model of estimator learning automata in the switching non-stationary environment