Yinchao Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yinchao Ma has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Tianzhu Zhang
University of Science and Technology of China, Hefei, China
8 shared publications - Yuyang Tang
School of Information Science, University of Science and Technology of China, Hefei, China
4 shared publications - Jie Xiao
School of Information Science, University of Science and Technology of China, Hefei, China
3 shared publications - Dawei Yang
University of Science and Technology of China
2 shared publications Dengqing Yang
School of Information Science, University of Science and Technology of China, Hefei, China
2 shared publications- Jianfeng He
School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China
2 shared publications
Latest Publications
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 2249-2261
SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking
Visual tracking aims to automatically estimate the state of a target object in a video sequence, which is challenging especially in dynamic scenarios. Thus, numerous methods are proposed to introduce temporal cues to enhance tracking robustness. However, conventional CNN and Transformer architectures exhibit inherent limitations in modeling long-range temporal dependencies in visual tracking, often necessitating either complex customized modules or substantial computational costs to integrate temporal cues. Inspired by the success of the state space model, we propose a novel temporal modeling paradigm for visual tracking, termed State-aware Mamba Tracker (SMTrack), providing a neat pipeline for training and tracking without needing customized modules or substantial computational costs to build long-range temporal dependencies. It enjoys several merits. First, we propose a novel selective state-aware space model with state-wise parameters to capture more diverse temporal cues for robust tracking. Second, SMTrack facilitates long-range temporal interactions with linear computational complexity during training. Third, SMTrack enables each frame to interact with previously tracked frames via hidden state propagation and updating, which releases computational costs of handling temporal cues during tracking. Extensive experimental results demonstrate that SMTrack achieves promising performance with low computational costs.
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 2249-2261
SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking
Visual tracking aims to automatically estimate the state of a target object in a video sequence, which is challenging especially in dynamic scenarios. Thus, numerous methods are proposed to introduce temporal cues to enhance tracking robustness. However, conventional CNN and Transformer architectures exhibit inherent limitations in modeling long-range temporal dependencies in visual tracking, often necessitating either complex customized modules or substantial computational costs to integrate temporal cues. Inspired by the success of the state space model, we propose a novel temporal modeling paradigm for visual tracking, termed State-aware Mamba Tracker (SMTrack), providing a neat pipeline for training and tracking without needing customized modules or substantial computational costs to build long-range temporal dependencies. It enjoys several merits. First, we propose a novel selective state-aware space model with state-wise parameters to capture more diverse temporal cues for robust tracking. Second, SMTrack facilitates long-range temporal interactions with linear computational complexity during training. Third, SMTrack enables each frame to interact with previously tracked frames via hidden state propagation and updating, which releases computational costs of handling temporal cues during tracking. Extensive experimental results demonstrate that SMTrack achieves promising performance with low computational costs.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4941-4955
State Space Models for Long-Term Temporal Context in 3D Single Object Tracking
3D single object tracking (3D SOT) remains a challenging task due to the sparsity of point clouds, appearance variations caused by occlusions, and the difficulty of modeling long-term temporal context. Although recent Transformer-based approaches leverage memory mechanisms to propagate temporal information, their quadratic complexity and reliance on discrete historical snapshots limit both efficiency and temporal coherence. To address these limitations, we propose SSMTrack, a novel 3D SOT framework built upon state space models (SSMs), which efficiently models long-term temporal dependencies through a continuously evolving hidden state with linear complexity. Specifically, we introduce a serialization and bidirectional scanning (SBS) strategy to enhance intra-frame feature interactions and design a Target-Aware Encoder (TAE) to extract target cues while maintaining stable temporal representations. Furthermore, we propose a Temporal Causal Shape Learning (TCSL) mechanism that preserves critical historical information while adaptively integrating current inputs, progressively enriching target feature representations over time. Extensive experiments on three benchmark datasets demonstrate that SSMTrack achieves state-of-the-art performance with strong temporal coherence and high efficiency. The code will be released upon publication.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4941-4955
State Space Models for Long-Term Temporal Context in 3D Single Object Tracking
3D single object tracking (3D SOT) remains a challenging task due to the sparsity of point clouds, appearance variations caused by occlusions, and the difficulty of modeling long-term temporal context. Although recent Transformer-based approaches leverage memory mechanisms to propagate temporal information, their quadratic complexity and reliance on discrete historical snapshots limit both efficiency and temporal coherence. To address these limitations, we propose SSMTrack, a novel 3D SOT framework built upon state space models (SSMs), which efficiently models long-term temporal dependencies through a continuously evolving hidden state with linear complexity. Specifically, we introduce a serialization and bidirectional scanning (SBS) strategy to enhance intra-frame feature interactions and design a Target-Aware Encoder (TAE) to extract target cues while maintaining stable temporal representations. Furthermore, we propose a Temporal Causal Shape Learning (TCSL) mechanism that preserves critical historical information while adaptively integrating current inputs, progressively enriching target feature representations over time. Extensive experiments on three benchmark datasets demonstrate that SSMTrack achieves state-of-the-art performance with strong temporal coherence and high efficiency. The code will be released upon publication.
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (3) , 3820-3833
State Space Models for Natural Language Tracking: Exploring Context-Adaptive Language Cues
Natural language tracking aims to locate the target of a video based on a language description. The rich contextual information inside the language and video sequence is essential to describe the target movements and appearance variations. However, existing natural language trackers design a fixed-length memory to store historical target information, which merely uses limited context information and necessitates manually designed modules, resulting in sub-optimal localization performance and numerous computational costs. Inspired by the success of the state space model, we propose a novel Context-adaptive Mamba Tracker (CMTrack). It enjoys several merits. First, we propose a novel context-aware state space model that enables language features to serve as hidden states to interact with relevant image features adaptively. Second, CMTrack transfers the hidden states frame-by-frame to continuously incorporate contextual target information into language features, enabling context-adaptive language cues. Third, the proposed context-adaptive language cues can effectively capture the long-range behavior of the target and guide the tracker in locating the target accurately without any extra design. Finally, CMTrack provides a neat pipeline for training and tracking with linear complexity. Experimental results demonstrate that CMTrack achieves new state-of-the-art performance.
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (3) , 3820-3833
State Space Models for Natural Language Tracking: Exploring Context-Adaptive Language Cues
Natural language tracking aims to locate the target of a video based on a language description. The rich contextual information inside the language and video sequence is essential to describe the target movements and appearance variations. However, existing natural language trackers design a fixed-length memory to store historical target information, which merely uses limited context information and necessitates manually designed modules, resulting in sub-optimal localization performance and numerous computational costs. Inspired by the success of the state space model, we propose a novel Context-adaptive Mamba Tracker (CMTrack). It enjoys several merits. First, we propose a novel context-aware state space model that enables language features to serve as hidden states to interact with relevant image features adaptively. Second, CMTrack transfers the hidden states frame-by-frame to continuously incorporate contextual target information into language features, enabling context-adaptive language cues. Third, the proposed context-adaptive language cues can effectively capture the long-range behavior of the target and guide the tracker in locating the target accurately without any extra design. Finally, CMTrack provides a neat pipeline for training and tracking with linear complexity. Experimental results demonstrate that CMTrack achieves new state-of-the-art performance.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1554-1572
UniSOT: A Unified Framework for Multi-Modality Single Object Tracking
Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference modalities enable various human-machine interactions, and different video modalities are demanded in complex scenarios to enhance tracking robustness. Existing trackers are designed for single or several video modalities with single or several reference modalities, which leads to separate model designs and limits practical applications. Practically, a unified tracker is needed to handle various requirements. To the best of our knowledge, there is still no tracker that can perform tracking with these above reference modalities across these video modalities simultaneously. Thus, in this paper, we present a unified tracker, UniSOT, for different combinations of three reference modalities and four video modalities with uniform parameters. Extensive experimental results on 18 visual tracking, vision-language tracking and RGB+X tracking benchmarks demonstrate that UniSOT shows superior performance against modality-specific counterparts. Notably, UniSOT outperforms previous counterparts by over 3.0% AUC on TNL2K across all three reference modalities and outperforms Un-Track by over 2.0% main metric across all three RGB+X video modalities.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1554-1572
UniSOT: A Unified Framework for Multi-Modality Single Object Tracking
Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference modalities enable various human-machine interactions, and different video modalities are demanded in complex scenarios to enhance tracking robustness. Existing trackers are designed for single or several video modalities with single or several reference modalities, which leads to separate model designs and limits practical applications. Practically, a unified tracker is needed to handle various requirements. To the best of our knowledge, there is still no tracker that can perform tracking with these above reference modalities across these video modalities simultaneously. Thus, in this paper, we present a unified tracker, UniSOT, for different combinations of three reference modalities and four video modalities with uniform parameters. Extensive experimental results on 18 visual tracking, vision-language tracking and RGB+X tracking benchmarks demonstrate that UniSOT shows superior performance against modality-specific counterparts. Notably, UniSOT outperforms previous counterparts by over 3.0% AUC on TNL2K across all three reference modalities and outperforms Un-Track by over 2.0% main metric across all three RGB+X video modalities.
- 22 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (10) , 10339-10352
Semantic-Aware Network for Natural Language Tracking
Natural language tracking aims to locate the position of a target specified by a natural language description. Existing methods are trained on vision-language datasets with a small number of language descriptions, which may lead to limited semantic generalization. Moreover, they extract visual and language features separately, which limits visual-semantic capabilities. To overcome these limitations, we propose a novel semantic-aware tracking framework, SATrack, which integrates a semantic-aware attention module and a cross-modal aggregation module. The proposed SATrack enjoys several merits. First, the semantic-aware attention module utilizes language semantics as a bridge to build associations between visual features, enabling stronger visual-semantic capabilities. Second, the cross-modal aggregation module transfers the semantic knowledge of CLIP into the tracking framework for semantic generalization. Extensive experimental results demonstrate that SATrack outperforms previous state-of-the-art trackers on four natural language tracking benchmarks.
- 22 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (10) , 10339-10352
Semantic-Aware Network for Natural Language Tracking
Natural language tracking aims to locate the position of a target specified by a natural language description. Existing methods are trained on vision-language datasets with a small number of language descriptions, which may lead to limited semantic generalization. Moreover, they extract visual and language features separately, which limits visual-semantic capabilities. To overcome these limitations, we propose a novel semantic-aware tracking framework, SATrack, which integrates a semantic-aware attention module and a cross-modal aggregation module. The proposed SATrack enjoys several merits. First, the semantic-aware attention module utilizes language semantics as a bridge to build associations between visual features, enabling stronger visual-semantic capabilities. Second, the cross-modal aggregation module transfers the semantic knowledge of CLIP into the tracking framework for semantic generalization. Extensive experimental results demonstrate that SATrack outperforms previous state-of-the-art trackers on four natural language tracking benchmarks.
- 23 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 6773-6786
Learning Adaptive Conceptual Prototypes for 3D Single Object Tracking
3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous driving. It remains a challenging problem due to the incompleteness and the sparsity of points caused by occlusion and limited sensor capabilities. Previous methods design various modules to propagate target perceptual cues to the current frame for target localization. However, perceptual cues may contain less information for occluded or distant objects, which brings great challenges to estimating the target state accurately. To address the above limitations, we propose a novel 3D SOT framework based on the adaptive conceptual prototypes named ACPTrack, which first learns the conceptual prototype from the prior knowledge of the category structure, and then associates weak perceptual cues with the learned conceptual prototypes to improve tracking performance. The proposed ACPTrack enjoys several merits. First, we propose a universal learning method of adaptive conceptual prototype, which can quickly adapt to target-specific structure with given perceptual cues. Second, we design two modules based on the conceptual prototype for structure completion and positioning refinement, which can exploit the rich structure information of the conceptual prototype to deal with sparse and incomplete targets for robust tracking. Third, our framework is generic and compatible with various 3D trackers and brings consistent performance gains. Extensive experiments validate that our method achieves competitive performance on three large-scale datasets.
- 23 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 6773-6786
Learning Adaptive Conceptual Prototypes for 3D Single Object Tracking
3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous driving. It remains a challenging problem due to the incompleteness and the sparsity of points caused by occlusion and limited sensor capabilities. Previous methods design various modules to propagate target perceptual cues to the current frame for target localization. However, perceptual cues may contain less information for occluded or distant objects, which brings great challenges to estimating the target state accurately. To address the above limitations, we propose a novel 3D SOT framework based on the adaptive conceptual prototypes named ACPTrack, which first learns the conceptual prototype from the prior knowledge of the category structure, and then associates weak perceptual cues with the learned conceptual prototypes to improve tracking performance. The proposed ACPTrack enjoys several merits. First, we propose a universal learning method of adaptive conceptual prototype, which can quickly adapt to target-specific structure with given perceptual cues. Second, we design two modules based on the conceptual prototype for structure completion and positioning refinement, which can exploit the rich structure information of the conceptual prototype to deal with sparse and incomplete targets for robust tracking. Third, our framework is generic and compatible with various 3D trackers and brings consistent performance gains. Extensive experiments validate that our method achieves competitive performance on three large-scale datasets.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3036-3046
A Unified Transformer-based Tracker for Anti-UAV Tracking
Recently, the need for advanced anti-UAV techniques is increasing due to the rising threat of unauthorized drone intrusion. Object tracking, specifically in thermal infrared (TIR) videos, offers a potential solution to this issue. However, the tracked target often suffers dramatic scale variation, frequent target disappearance, and camera movement which severely influence tracking performance. Therefore, we propose a Unified Transformer-based Tracker, dubbed UTTracker, which contains the following four modules. Firstly, a multi-region local tracking module is designed with temporal cues for tackling target appearance variation and multi-region search for tracking targets in multi proposals. Complementarily, a global detection module is introduced to meet the challenge of target frequent disappearance. Meanwhile, a background correction module is incorporated to align the backgrounds between adjacent frames for alleviating camera movement. Particularly, a dynamic small object detection module for tracking the small target that lacks appearance information. Thanks to the designed modules, our UTTracker can achieve robust UAV tracking in TIR scenarios. Numerous experiments on the 1st and 2nd anti-UAV benchmarks demonstrate the effectiveness of UTTracker. Notably, UTTracker is the foundation of the 2nd-place winning entry in the 3rd Anti-UAV Challenge.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3036-3046
A Unified Transformer-based Tracker for Anti-UAV Tracking
Recently, the need for advanced anti-UAV techniques is increasing due to the rising threat of unauthorized drone intrusion. Object tracking, specifically in thermal infrared (TIR) videos, offers a potential solution to this issue. However, the tracked target often suffers dramatic scale variation, frequent target disappearance, and camera movement which severely influence tracking performance. Therefore, we propose a Unified Transformer-based Tracker, dubbed UTTracker, which contains the following four modules. Firstly, a multi-region local tracking module is designed with temporal cues for tackling target appearance variation and multi-region search for tracking targets in multi proposals. Complementarily, a global detection module is introduced to meet the challenge of target frequent disappearance. Meanwhile, a background correction module is incorporated to align the backgrounds between adjacent frames for alleviating camera movement. Particularly, a dynamic small object detection module for tracking the small target that lacks appearance information. Thanks to the designed modules, our UTTracker can achieve robust UAV tracking in TIR scenarios. Numerous experiments on the 1st and 2nd anti-UAV benchmarks demonstrate the effectiveness of UTTracker. Notably, UTTracker is the foundation of the 2nd-place winning entry in the 3rd Anti-UAV Challenge.
- 16 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (10) , 11443-11457
Adaptive Part Mining for Robust Visual Tracking
Visual tracking aims to estimate object state in a video sequence, which is challenging when facing drastic appearance changes. Most existing trackers conduct tracking with divided parts to handle appearance variations. However, these trackers commonly divide target objects into regular patches by a hand-designed splitting way, which is too coarse to align object parts well. Besides, a fixed part detector is difficult to partition targets with arbitrary categories and deformations. To address the above issues, we propose a novel adaptive part mining tracker (APMT) for robust tracking via a transformer architecture, including an object representation encoder, an adaptive part mining decoder, and an object state estimation decoder. The proposed APMT enjoys several merits. First, in the object representation encoder, object representation is learned by distinguishing target object from background regions. Second, in the adaptive part mining decoder, we introduce multiple part prototypes to adaptively capture target parts through cross-attention mechanisms for arbitrary categories and deformations. Third, in the object state estimation decoder, we propose two novel strategies to effectively handle appearance variations and distractors. Extensive experimental results demonstrate that our APMT achieves promising results with high FPS. Notably, our tracker is ranked the first place in the VOT-STb2022 challenge.
- 16 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (10) , 11443-11457
Adaptive Part Mining for Robust Visual Tracking
Visual tracking aims to estimate object state in a video sequence, which is challenging when facing drastic appearance changes. Most existing trackers conduct tracking with divided parts to handle appearance variations. However, these trackers commonly divide target objects into regular patches by a hand-designed splitting way, which is too coarse to align object parts well. Besides, a fixed part detector is difficult to partition targets with arbitrary categories and deformations. To address the above issues, we propose a novel adaptive part mining tracker (APMT) for robust tracking via a transformer architecture, including an object representation encoder, an adaptive part mining decoder, and an object state estimation decoder. The proposed APMT enjoys several merits. First, in the object representation encoder, object representation is learned by distinguishing target object from background regions. Second, in the adaptive part mining decoder, we introduce multiple part prototypes to adaptively capture target parts through cross-attention mechanisms for arbitrary categories and deformations. Third, in the object state estimation decoder, we propose two novel strategies to effectively handle appearance variations and distractors. Extensive experimental results demonstrate that our APMT achieves promising results with high FPS. Notably, our tracker is ranked the first place in the VOT-STb2022 challenge.