Junxin Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junxin Lu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Shiliang Sun
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China
2 shared publications - Yongbin Gao
Shanghai University of Engineering Science
2 shared publications - Chenmou Wu
Shanghai University of Engineering Science
1 shared publication Daimeng Wei
Huawei Translation Services Center
1 shared publication- Hamido Fujita
Malaysia-Japan International Institute of Technology, University Teknologi Malaysia, Kuala Lumpur, Malaysia
1 shared publication - Hui Yang
Huawei Translation Services Center
1 shared publication
Latest Publications
- 10 September 2026
- Published by Springer Nature
- p. 216-234
Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation
- 10 September 2026
- Published by Springer Nature
- p. 216-234
Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation
- 20 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
ClauseRoute: Risk-aware clause-guided routing for retrieval-augmented legal reasoning
- 20 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
ClauseRoute: Risk-aware clause-guided routing for retrieval-augmented legal reasoning
- Open Access
- 30 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (10) , 1-26
Monocular Depth and Ego-motion Estimation with Scale Based on Superpixel and Normal Constraints
Three-dimensional perception in intelligent virtual and augmented reality (VR/AR) and autonomous vehicles (AV) applications is critical and attracting significant attention. The self-supervised monocular depth and ego-motion estimation serves as a more intelligent learning approach that provides the required scene depth and location for 3D perception. However, the existing self-supervised learning methods suffer from scale ambiguity, boundary blur, and imbalanced depth distribution, limiting the practical applications of VR/AR and AV. In this article, we propose a new self-supervised learning framework based on superpixel and normal constraints to address these problems. Specifically, we formulate a novel 3D edge structure consistency loss to alleviate the boundary blur of depth estimation. To address the scale ambiguity of estimated depth and ego-motion, we propose a novel surface normal network for efficient camera height estimation. The surface normal network is composed of a deep fusion module and a full-scale hierarchical feature aggregation module. Meanwhile, to realize the global smoothing and boundary discriminability of the predicted normal map, we introduce a novel fusion loss which is based on the consistency constraints of the normal in edge domains and superpixel regions. Experiments are conducted on several benchmarks, and the results illustrate that the proposed approach outperforms the state-of-the-art methods in depth, ego-motion, and surface normal estimation.
- 30 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (10) , 1-26
Open AccessMonocular Depth and Ego-motion Estimation with Scale Based on Superpixel and Normal Constraints
Three-dimensional perception in intelligent virtual and augmented reality (VR/AR) and autonomous vehicles (AV) applications is critical and attracting significant attention. The self-supervised monocular depth and ego-motion estimation serves as a more intelligent learning approach that provides the required scene depth and location for 3D perception. However, the existing self-supervised learning methods suffer from scale ambiguity, boundary blur, and imbalanced depth distribution, limiting the practical applications of VR/AR and AV. In this article, we propose a new self-supervised learning framework based on superpixel and normal constraints to address these problems. Specifically, we formulate a novel 3D edge structure consistency loss to alleviate the boundary blur of depth estimation. To address the scale ambiguity of estimated depth and ego-motion, we propose a novel surface normal network for efficient camera height estimation. The surface normal network is composed of a deep fusion module and a full-scale hierarchical feature aggregation module. Meanwhile, to realize the global smoothing and boundary discriminability of the predicted normal map, we introduce a novel fusion loss which is based on the consistency constraints of the normal in edge domains and superpixel regions. Experiments are conducted on several benchmarks, and the results illustrate that the proposed approach outperforms the state-of-the-art methods in depth, ego-motion, and surface normal estimation.
- 1 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33, 3353-3368
PAMK: Prototype Augmented Multi-Teacher Knowledge Transfer Network for Continual Zero-Shot Learning
Continual zero-shot learning (CZSL) aims to develop a model that accumulates historical knowledge to recognize unseen tasks, while eliminating catastrophic forgetting for seen tasks when learning new tasks. However, existing CZSL methods, while mitigating catastrophic forgetting for old tasks, often lead to negative transfer problem for new tasks by over-focusing on accumulating old knowledge and neglecting the plasticity of the model for learning new tasks. To tackle these problems, we propose PAMK, a prototype augmented multi-teacher knowledge transfer network that strikes a trade-off between recognition stability for old tasks and generalization plasticity for new tasks. PAMK consists of a prototype augmented contrastive generation (PACG) module and a multi-teacher knowledge transfer (MKT) module. To reduce the cumulative semantic decay of the class representation embedding and mitigate catastrophic forgetting, we propose a continual prototype augmentation strategy based on relevance scores in PACG. Furthermore, by introducing the prototype augmented semantic-visual contrastive loss, PACG promotes intra-class compactness for all classes across all tasks. MKT effectively accumulates semantic knowledge learned from old tasks to recognize new tasks via the proposed multi-teacher knowledge transfer, eliminating the negative transfer problem. Extensive experiments on various CZSL settings demonstrate the superior performance of PAMK compared to state-of-the-art methods. In particular, in the practical task-free CZSL setting, PAMK achieves impressive gains of 3.28%, 3.09% and 3.71% in mean harmonic accuracy on the CUB, AWA1, and AWA2 datasets, respectively.
- 1 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33, 3353-3368
PAMK: Prototype Augmented Multi-Teacher Knowledge Transfer Network for Continual Zero-Shot Learning
Continual zero-shot learning (CZSL) aims to develop a model that accumulates historical knowledge to recognize unseen tasks, while eliminating catastrophic forgetting for seen tasks when learning new tasks. However, existing CZSL methods, while mitigating catastrophic forgetting for old tasks, often lead to negative transfer problem for new tasks by over-focusing on accumulating old knowledge and neglecting the plasticity of the model for learning new tasks. To tackle these problems, we propose PAMK, a prototype augmented multi-teacher knowledge transfer network that strikes a trade-off between recognition stability for old tasks and generalization plasticity for new tasks. PAMK consists of a prototype augmented contrastive generation (PACG) module and a multi-teacher knowledge transfer (MKT) module. To reduce the cumulative semantic decay of the class representation embedding and mitigate catastrophic forgetting, we propose a continual prototype augmentation strategy based on relevance scores in PACG. Furthermore, by introducing the prototype augmented semantic-visual contrastive loss, PACG promotes intra-class compactness for all classes across all tasks. MKT effectively accumulates semantic knowledge learned from old tasks to recognize new tasks via the proposed multi-teacher knowledge transfer, eliminating the negative transfer problem. Extensive experiments on various CZSL settings demonstrate the superior performance of PAMK compared to state-of-the-art methods. In particular, in the practical task-free CZSL setting, PAMK achieves impressive gains of 3.28%, 3.09% and 3.71% in mean harmonic accuracy on the CUB, AWA1, and AWA2 datasets, respectively.
- 1 May 2021
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 77
Line-based visual odometry using local gradient fitting
- 1 May 2021
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 77
Line-based visual odometry using local gradient fitting