Xiaoming Tao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaoming Tao has a total of 262 co-authors. Here are the top co-authors by number of shared publications:
- Yiping Duan
Department of Electronic Engineering, Tsinghua University, Beijing, China
31 shared publications Jianhua Lu
Department of Electronic Engineering, Tsinghua University, Beijing 100084, P.R. China
21 shared publications- Zhijin Qin
Tsinghua University
19 shared publications - Yanjun Qin
School of Computer Science and Technology, Xinjiang University, Urumqi, China
11 shared publications - Liejun Wang
School of Computer Science and Technology, Xinjiang University, Urumqi 830046, China
10 shared publications - Mai Xu
Beihang University
10 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4366-4375
Multimodal Object--Attribute--Relation Graph Construction for Explicit Scene Representation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4366-4375
Open AccessMultimodal Object--Attribute--Relation Graph Construction for Explicit Scene Representation
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10277-10286
From Decoupled Heads to Self-Correcting Inference: SCOPE for Training-Free Open-Vocabulary Segmentation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10277-10286
Open AccessFrom Decoupled Heads to Self-Correcting Inference: SCOPE for Training-Free Open-Vocabulary Segmentation
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 20479-20491
Task-Aware Joint Source-Channel Coding for Robust Vibrotactile Transmission
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 20479-20491
Task-Aware Joint Source-Channel Coding for Robust Vibrotactile Transmission
- 5 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
One-Identity-One-Key: Region-aware Watermark for Proactive Deepfake Detection and Robust Source Tracing
Proactive forensic methods based on watermarking have attracted increasing attention as an effective paradigm for deepfake detection and source tracing. However, the existing methods still have shortcomings in encryption security, robustness and detection performance when dealing with complex forgery. In this paper, we propose a region-aware watermarking based proactive deepfake detection framework named Segfacemark. Building on global watermark embedding, this method explicitly models the sensitivity of various semantic facial regions to tampering. By employing region-wise partitioning and redundant embedding, the framework strengthens the protection of key facial areas, thereby comprehensively enhancing watermark robustness. In addition, the proposed framework employs a dynamic encryption mechanism that derives personalized keys from identity features to encrypt structural features, thereby realizing a “one-identity–one-key” watermark generation strategy and significantly enhancing system security and robustness against forgery. In the detection stage, the dual verification mechanism of identity decryption consistency and global region-aware watermark consistency not only improves detection accuracy but also enables forgery type identification, and further enhances the interpretability of deepfake detection results through region-aware watermarks. Experimental results show that the proposed method achieves high accuracy and robustness in deepfake detection, while preserving visual fidelity. The code will be released at: https://github.com/vpsg-research/Segfacemark.
- 5 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
One-Identity-One-Key: Region-aware Watermark for Proactive Deepfake Detection and Robust Source Tracing
Proactive forensic methods based on watermarking have attracted increasing attention as an effective paradigm for deepfake detection and source tracing. However, the existing methods still have shortcomings in encryption security, robustness and detection performance when dealing with complex forgery. In this paper, we propose a region-aware watermarking based proactive deepfake detection framework named Segfacemark. Building on global watermark embedding, this method explicitly models the sensitivity of various semantic facial regions to tampering. By employing region-wise partitioning and redundant embedding, the framework strengthens the protection of key facial areas, thereby comprehensively enhancing watermark robustness. In addition, the proposed framework employs a dynamic encryption mechanism that derives personalized keys from identity features to encrypt structural features, thereby realizing a “one-identity–one-key” watermark generation strategy and significantly enhancing system security and robustness against forgery. In the detection stage, the dual verification mechanism of identity decryption consistency and global region-aware watermark consistency not only improves detection accuracy but also enables forgery type identification, and further enhances the interpretability of deepfake detection results through region-aware watermarks. Experimental results show that the proposed method achieves high accuracy and robustness in deepfake detection, while preserving visual fidelity. The code will be released at: https://github.com/vpsg-research/Segfacemark.
- 4 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-16
Distributed Deep Joint Source-Channel Coding of Videos in Unmanned Aerial Vehicle Networks
In unmanned aerial vehicle (UAV) networks, efficient video transmission is crucial for applications such as surveillance, disaster response, and remote sensing, yet it remains challenging due to limited computational resources and energy constraints. This paper presents a novel video transmission framework that simultaneously enhances communication quality and energy efficiency in resource-constrained UAV networks. To address computational limitations while ensuring high-quality video reconstruction, we design a joint source–channel coding (JSCC) scheme with a lightweight encoder that incorporates distributed video coding. To further improve system endurance, we employ deep reinforcement learning (DRL) to dynamically optimize relay node selection. Simulation results demonstrate that the proposed lightweight feature extraction model requires only 1.81% of the complexity of deep contextual video compression (DCVC) and 16.56% of low-complexity deep video compression (L-DVC), while achieving comparable or superior reconstruction performance under diverse channel conditions. Moreover, the proposed scheme significantly improves energy efficiency, thereby extending UAV hover time compared to the baseline.
- 4 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-16
Distributed Deep Joint Source-Channel Coding of Videos in Unmanned Aerial Vehicle Networks
In unmanned aerial vehicle (UAV) networks, efficient video transmission is crucial for applications such as surveillance, disaster response, and remote sensing, yet it remains challenging due to limited computational resources and energy constraints. This paper presents a novel video transmission framework that simultaneously enhances communication quality and energy efficiency in resource-constrained UAV networks. To address computational limitations while ensuring high-quality video reconstruction, we design a joint source–channel coding (JSCC) scheme with a lightweight encoder that incorporates distributed video coding. To further improve system endurance, we employ deep reinforcement learning (DRL) to dynamically optimize relay node selection. Simulation results demonstrate that the proposed lightweight feature extraction model requires only 1.81% of the complexity of deep contextual video compression (DCVC) and 16.56% of low-complexity deep video compression (L-DVC), while achieving comparable or superior reconstruction performance under diverse channel conditions. Moreover, the proposed scheme significantly improves energy efficiency, thereby extending UAV hover time compared to the baseline.
- 20 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 319
Assisted refinement network based on channel information interaction for camouflaged object detection
- 20 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 319
Assisted refinement network based on channel information interaction for camouflaged object detection
- Open Access
Movable-Antenna Empowered Backscatter ISAC: Toward Geometry-Adaptive, Low-Power Networks
Backscatter-based integrated sensing and communication (B-ISAC) elevates passive tags into information-bearing scatterers, offering an ultra-low-power path toward dual-function wireless systems. However, this promise is fundamentally undermined by a cascaded backscattering link that suffers from severe double fading and is exquisitely sensitive to geometric misalignment. This article tackles this geometric bottleneck by integrating movable antenna systems (MAS) at the transceiver side. MAS provides real-time, controllable spatial degrees of freedom through sub-wavelength antenna repositioning, enabling active reconfiguration of the cascaded channel without modifying passive tags or consuming additional spectrum. We position this solution within a unified ISAC-backscatter communication-B-ISAC evolution, describe the resulting MAS-assisted B-ISAC architecture and operating principles, and demonstrate its system-level gains through comparative analysis and numerical results. Finally, we showcase the potential of this geometry-adaptive paradigm across key IoT application scenarios, pointing toward future motion-aware wireless networks.
Open AccessMovable-Antenna Empowered Backscatter ISAC: Toward Geometry-Adaptive, Low-Power Networks
Backscatter-based integrated sensing and communication (B-ISAC) elevates passive tags into information-bearing scatterers, offering an ultra-low-power path toward dual-function wireless systems. However, this promise is fundamentally undermined by a cascaded backscattering link that suffers from severe double fading and is exquisitely sensitive to geometric misalignment. This article tackles this geometric bottleneck by integrating movable antenna systems (MAS) at the transceiver side. MAS provides real-time, controllable spatial degrees of freedom through sub-wavelength antenna repositioning, enabling active reconfiguration of the cascaded channel without modifying passive tags or consuming additional spectrum. We position this solution within a unified ISAC-backscatter communication-B-ISAC evolution, describe the resulting MAS-assisted B-ISAC architecture and operating principles, and demonstrate its system-level gains through comparative analysis and numerical results. Finally, we showcase the potential of this geometry-adaptive paradigm across key IoT application scenarios, pointing toward future motion-aware wireless networks.
- 14 January 2026
- Published by Springer Nature
- p. 222-236
Bias-Unlearning in MABSA: A Causal Framework with Cross-Modal Counterfactual Inference
- 14 January 2026
- Published by Springer Nature
- p. 222-236
Bias-Unlearning in MABSA: A Causal Framework with Cross-Modal Counterfactual Inference
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2984-2995
Deep Video Coding With Bit-Depth Scalability
Deep video coding techniques have achieved significant advancements, leading to enhanced compression performance. However, existing approaches are primarily optimized for 8-bit content, thereby limiting their effectiveness in scenarios with different bit-depths. In this paper, we propose a deep bit-depth scalable video codec (DB-SVC) that supports two-layer scalability for different bit-depths. First, we design a base layer (BL) for low bit-depth (LBD) videos, incorporating a dual-stage multi-scale feature extraction module (DFEM) to enhance compression efficiency while providing reference features for subsequent coding. Second, we introduce an inter-layer bit-depth enhancement module (IBEM) that refines the bit-depth of BL reconstructed frames by leveraging interlayer information, thus enhancing the reference quality without increasing coding overhead. Third, we design an enhancement layer (EL) tailored for high bit-depth (HBD) videos, employing a bit-depth residual compression (BRC) method to achieve a more accurate reconstruction of HBD videos. DB-SVC supports progressive decoding of LBD and HBD videos, accommodating diverse display requirements. Experimental results demonstrate that DB-SVC outperforms state-of-the-art codecs in LBD and HBD scenarios. At the same PSNR/MS-SSIM levels, DB-SVC achieves average bit-rate savings of 11.94%/53.35% for 8-bit videos and 55.98%/73.16% for 10-bit videos while comparing with VTM13.2, showcasing its superior compression performance.
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2984-2995
Deep Video Coding With Bit-Depth Scalability
Deep video coding techniques have achieved significant advancements, leading to enhanced compression performance. However, existing approaches are primarily optimized for 8-bit content, thereby limiting their effectiveness in scenarios with different bit-depths. In this paper, we propose a deep bit-depth scalable video codec (DB-SVC) that supports two-layer scalability for different bit-depths. First, we design a base layer (BL) for low bit-depth (LBD) videos, incorporating a dual-stage multi-scale feature extraction module (DFEM) to enhance compression efficiency while providing reference features for subsequent coding. Second, we introduce an inter-layer bit-depth enhancement module (IBEM) that refines the bit-depth of BL reconstructed frames by leveraging interlayer information, thus enhancing the reference quality without increasing coding overhead. Third, we design an enhancement layer (EL) tailored for high bit-depth (HBD) videos, employing a bit-depth residual compression (BRC) method to achieve a more accurate reconstruction of HBD videos. DB-SVC supports progressive decoding of LBD and HBD videos, accommodating diverse display requirements. Experimental results demonstrate that DB-SVC outperforms state-of-the-art codecs in LBD and HBD scenarios. At the same PSNR/MS-SSIM levels, DB-SVC achieves average bit-rate savings of 11.94%/53.35% for 8-bit videos and 55.98%/73.16% for 10-bit videos while comparing with VTM13.2, showcasing its superior compression performance.