Qun Song
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
Qun Song has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Rui Tan
Nanyang Technological University
13 shared publications - Jianping Wang
City University of Hong Kong, Hong Kong, China
6 shared publications - Zhenyu Yan
The Chinese University of Hong Kong, Hong Kong SAR, China
4 shared publications - Xiangzhong Luo
Southeast University, Nanjing, China
3 shared publications - Zimo Ma
College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore
3 shared publications - David K. Y. Yau
Singapore University of Technology & Design, Singapore, Singapore
2 shared publications
Latest Publications
- Open Access
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 175-176
Demo: Zero-Shot Acoustic SLAM on Smartphones
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 175-176
Open AccessDemo: Zero-Shot Acoustic SLAM on Smartphones
- Open Access
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 492-505
ZA-SLAM: Leveraging Vision-Language Model for Zero-Shot Acoustic SLAM
Existing acoustic indoor location sensing systems are limited by the need for extensive data collection and model retraining in unseen environments. This paper introduces ZA-SLAM, a novel zero-shot acoustic Simultaneous Localization and Mapping (SLAM) system that can be deployed in unseen environments without model retraining. Our core idea is to train an acoustic encoder that inherits the generalization capabilities of pre-trained Vision-Language Models (VLMs), which show superiority in tasks like zero-shot visual SLAM. To achieve this goal, we perform Acoustic-Visual Feature Alignment to enable the acoustic encoder to generate features aligned with visual features from VLMs. To select high-quality images for effective alignment, we design a Semantic-Guided Image Selection that filters out low-quality collected images caused by factors like abrupt view changes, occlusions, and uninformative views. Furthermore, we address the challenge of false positive loop closures in structurally similar locations with the Learning-Based Trajectory Reachability Matching that validates loop closures leveraging IMU trajectory features. Extensive real-world experiments demonstrate that our system achieves comparable SLAM performance to retraining-based acoustic SLAM, and much improved performance compared to existing zero-shot Wi-Fi and geomagnetic SLAM systems. Our system achieves a mean mapping error of 0.56 m and a localization error of 0.78 m across multiple unseen environments.
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 492-505
Open AccessZA-SLAM: Leveraging Vision-Language Model for Zero-Shot Acoustic SLAM
Existing acoustic indoor location sensing systems are limited by the need for extensive data collection and model retraining in unseen environments. This paper introduces ZA-SLAM, a novel zero-shot acoustic Simultaneous Localization and Mapping (SLAM) system that can be deployed in unseen environments without model retraining. Our core idea is to train an acoustic encoder that inherits the generalization capabilities of pre-trained Vision-Language Models (VLMs), which show superiority in tasks like zero-shot visual SLAM. To achieve this goal, we perform Acoustic-Visual Feature Alignment to enable the acoustic encoder to generate features aligned with visual features from VLMs. To select high-quality images for effective alignment, we design a Semantic-Guided Image Selection that filters out low-quality collected images caused by factors like abrupt view changes, occlusions, and uninformative views. Furthermore, we address the challenge of false positive loop closures in structurally similar locations with the Learning-Based Trajectory Reachability Matching that validates loop closures leveraging IMU trajectory features. Extensive real-world experiments demonstrate that our system achieves comparable SLAM performance to retraining-based acoustic SLAM, and much improved performance compared to existing zero-shot Wi-Fi and geomagnetic SLAM systems. Our system achieves a mean mapping error of 0.56 m and a localization error of 0.78 m across multiple unseen environments.
- Open Access
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 239-243
Depth Priors-informed Purification Defense for Car-Borne LiDAR Vehicle Detection
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 239-243
Open AccessDepth Priors-informed Purification Defense for Car-Borne LiDAR Vehicle Detection
- 5 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
Knowledge-aware replay for multi-label class-incremental learning
- 5 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
Knowledge-aware replay for multi-label class-incremental learning
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3251-3265
Asymmetry Vulnerability and Physical Attacks on Online Map Construction for Autonomous Driving
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3251-3265
Open AccessAsymmetry Vulnerability and Physical Attacks on Online Map Construction for Autonomous Driving
- Open Access
- 26 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 24 (5s) , 1-26
Dynamic Layer Routing Defense for Real-Time Embedded Vision
Deep neural networks have advanced the perception and decision-making functions of smart embedded systems, such as car-borne driver assistance. Deploying these embedded neural networks often faces two challenges: (i) security vulnerabilities to adversarial examples that can be deployed in the perceived physical environment; (ii) limited computational resources coupled with dynamic conditions that necessitate real-time adaptation of model execution. However, these two challenges are often addressed separately in existing research. This article presents LeapNet, which aims to address both challenges simultaneously. It comprises two versions: LeapNet-1 and LeapNet-2. LeapNet-1 employs dynamic layer routing to counteract adaptive adversarial-example attacks and reduce computational redundancy. Building upon LeapNet-1, LeapNet-2 further adapts its layer routing configurations in real time to meet the frame processing rate requirements under dynamic conditions while maintaining defense performance. Extensive experiments on various representative datasets, neural network models, and adaptive attacks demonstrate the superiority of LeapNet over existing defense methods. On-road tests with a real-time car-borne traffic sign recognition system validate its effectiveness in maintaining frame processing rate under dynamic conditions.
- 26 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 24 (5s) , 1-26
Open AccessDynamic Layer Routing Defense for Real-Time Embedded Vision
Deep neural networks have advanced the perception and decision-making functions of smart embedded systems, such as car-borne driver assistance. Deploying these embedded neural networks often faces two challenges: (i) security vulnerabilities to adversarial examples that can be deployed in the perceived physical environment; (ii) limited computational resources coupled with dynamic conditions that necessitate real-time adaptation of model execution. However, these two challenges are often addressed separately in existing research. This article presents LeapNet, which aims to address both challenges simultaneously. It comprises two versions: LeapNet-1 and LeapNet-2. LeapNet-1 employs dynamic layer routing to counteract adaptive adversarial-example attacks and reduce computational redundancy. Building upon LeapNet-1, LeapNet-2 further adapts its layer routing configurations in real time to meet the frame processing rate requirements under dynamic conditions while maintaining defense performance. Extensive experiments on various representative datasets, neural network models, and adaptive attacks demonstrate the superiority of LeapNet over existing defense methods. On-road tests with a real-time car-borne traffic sign recognition system validate its effectiveness in maintaining frame processing rate under dynamic conditions.
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 431-444
Dynamic Defense for Car-Borne LiDAR Vehicle Detection
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 431-444
Open AccessDynamic Defense for Car-Borne LiDAR Vehicle Detection
- Open Access
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 652-653
Poster Abstract: Mobile Vision Dynamic Layer Dropping against Adversarial Attacks
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 652-653
Open AccessPoster Abstract: Mobile Vision Dynamic Layer Dropping against Adversarial Attacks
- Open Access
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 710-711
Demo Abstract: Parameterized Stochastic Ensemble Defense for Object Detection
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 710-711
Open AccessDemo Abstract: Parameterized Stochastic Ensemble Defense for Object Detection
- 10 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (6) , 6634-6649
Indoor Smartphone SLAM With Acoustic Echoes
Indoor self-localization has become a highly desirable system function for smartphones. The existing systems based on imaging, radio frequency, and geomagnetic sensing may have sub-optimal performance when their limiting factors prevail. In this paper, we present a new indoor simultaneous localization and mapping (SLAM) system that is based on the smartphone's built-in audio hardware and inertial measurement unit (IMU). Our system uses a smartphone's loudspeaker to emit near-inaudible chirps and then the microphone to record the acoustic echoes from the indoor environment. The echoes contain the smartphone's location information with sub-meter granularity. To enable SLAM, we apply contrastive learning to train an echoic location feature (ELF) extractor, such that the loop closures on the smartphone's trajectory can be accurately detected from the associated ELF trace. The detection results effectively regulate the IMU-based trajectory reconstruction. The reconstructed trajectories are used for trajectory map superimposition and room geometry reconstruction . Extensive experiments show that our SLAM achieves median localization errors of $\text{0.1}\,\text{m}$ , $\text{0.53}\,\text{m}$ , and $\text{0.4}\,\text{m}$ in a living room, an office, and a shopping mall, and outperforms both the Wi-Fi and geomagnetic SLAM systems. The room geometry reconstruction achieves up to 4× lower errors compared with the latest echo-based approaches.
- 10 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (6) , 6634-6649
Indoor Smartphone SLAM With Acoustic Echoes
Indoor self-localization has become a highly desirable system function for smartphones. The existing systems based on imaging, radio frequency, and geomagnetic sensing may have sub-optimal performance when their limiting factors prevail. In this paper, we present a new indoor simultaneous localization and mapping (SLAM) system that is based on the smartphone's built-in audio hardware and inertial measurement unit (IMU). Our system uses a smartphone's loudspeaker to emit near-inaudible chirps and then the microphone to record the acoustic echoes from the indoor environment. The echoes contain the smartphone's location information with sub-meter granularity. To enable SLAM, we apply contrastive learning to train an echoic location feature (ELF) extractor, such that the loop closures on the smartphone's trajectory can be accurately detected from the associated ELF trace. The detection results effectively regulate the IMU-based trajectory reconstruction. The reconstructed trajectories are used for trajectory map superimposition and room geometry reconstruction . Extensive experiments show that our SLAM achieves median localization errors of $\text{0.1}\,\text{m}$ , $\text{0.53}\,\text{m}$ , and $\text{0.4}\,\text{m}$ in a living room, an office, and a shopping mall, and outperforms both the Wi-Fi and geomagnetic SLAM systems. The room geometry reconstruction achieves up to 4× lower errors compared with the latest echo-based approaches.