James Liang
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
Research Subjects
James Liang has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Dongfang Liu
Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY, USA
4 shared publications - Xiangyu Zhang
Purdue University, West Lafayette, USA
2 shared publications - Alexander C. Loui
Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY, USA
1 shared publication Chijioke Chukwudi
Department of Surgery, Massachusetts General Hospital, USA
1 shared publication- David Simpson
North Shore Hospital, Auckland, New Zealand
1 shared publication - Eileen Merriman
Haematology Department North Shore Hospital Auckland New Zealand
1 shared publication
Latest Publications
- Open Access
- 9 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
AutoCue: Multimodal LLM-Assisted Externalization of Implicit Inputs as Instructional Visual Cues in Screencast Tutorials
- 9 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessAutoCue: Multimodal LLM-Assisted Externalization of Implicit Inputs as Instructional Visual Cues in Screencast Tutorials
- 13 March 2025
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 265, 108705
Advancing hierarchical neural networks with scale-aware pyramidal feature learning for medical image dense prediction
- 13 March 2025
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 265, 108705
Advancing hierarchical neural networks with scale-aware pyramidal feature learning for medical image dense prediction
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 2678-2692
Tripartite Feature Enhanced Pyramid Network for Dense Prediction
Learning pyramidal feature representations is important for many dense prediction tasks ( e.g ., object detection, semantic segmentation) that demand multi-scale visual understanding. Feature Pyramid Network (FPN) is a well-known architecture for multi-scale feature learning, however, intrinsic weaknesses in feature extraction and fusion impede the production of informative features. This work addresses the weaknesses of FPN through a novel tripartite feature enhanced pyramid network (TFPN), with three distinct and effective designs. First, we develop a feature reference module with lateral connections to adaptively extract bottom-up features with richer details for feature pyramid construction. Second, we design a feature calibration module between adjacent layers that calibrates the upsampled features to be spatially aligned, allowing for feature fusion with accurate correspondences. Third, we introduce a feature feedback module in FPN, which creates a communication channel from the feature pyramid back to the bottom-up backbone and doubles the encoding capacity, enabling the entire architecture to generate incrementally more powerful representations. The TFPN is extensively evaluated over four popular dense prediction tasks, i.e ., object detection, instance segmentation, panoptic segmentation, and semantic segmentation. The results demonstrate that TFPN consistently and significantly outperforms the vanilla FPN. Our code is available at https://github.com/jamesliang819.
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 2678-2692
Tripartite Feature Enhanced Pyramid Network for Dense Prediction
Learning pyramidal feature representations is important for many dense prediction tasks ( e.g ., object detection, semantic segmentation) that demand multi-scale visual understanding. Feature Pyramid Network (FPN) is a well-known architecture for multi-scale feature learning, however, intrinsic weaknesses in feature extraction and fusion impede the production of informative features. This work addresses the weaknesses of FPN through a novel tripartite feature enhanced pyramid network (TFPN), with three distinct and effective designs. First, we develop a feature reference module with lateral connections to adaptively extract bottom-up features with richer details for feature pyramid construction. Second, we design a feature calibration module between adjacent layers that calibrates the upsampled features to be spatially aligned, allowing for feature fusion with accurate correspondences. Third, we introduce a feature feedback module in FPN, which creates a communication channel from the feature pyramid back to the bottom-up backbone and doubles the encoding capacity, enabling the entire architecture to generate incrementally more powerful representations. The TFPN is extensively evaluated over four popular dense prediction tasks, i.e ., object detection, instance segmentation, panoptic segmentation, and semantic segmentation. The results demonstrate that TFPN consistently and significantly outperforms the vanilla FPN. Our code is available at https://github.com/jamesliang819.
- Open Access
Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks
Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the security of such systems. Traditional adversarial training method requires ground-truth labels hence cannot be directly applied to self-supervised MDE that does not have ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) ignore the domain knowledge of MDE and can hardly achieve optimal performance. In this work, we propose a novel adversarial training method for self-supervised MDE models based on view synthesis without using ground-truth depth. We improve adversarial robustness against physical-world attacks using L0-norm-bounded perturbation in training. We compare our method with supervised learning based and contrastive learning based methods that are tailored for MDE. Results on two representative MDE networks show that we achieve better robustness against various adversarial attacks with nearly no benign performance degradation.
Open AccessAdversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks
Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the security of such systems. Traditional adversarial training method requires ground-truth labels hence cannot be directly applied to self-supervised MDE that does not have ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) ignore the domain knowledge of MDE and can hardly achieve optimal performance. In this work, we propose a novel adversarial training method for self-supervised MDE models based on view synthesis without using ground-truth depth. We improve adversarial robustness against physical-world attacks using L0-norm-bounded perturbation in training. We compare our method with supervised learning based and contrastive learning based methods that are tailored for MDE. Results on two representative MDE networks show that we achieve better robustness against various adversarial attacks with nearly no benign performance degradation.
- 23 October 2022
- Published by Springer Nature
- p. 514-532
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
- 23 October 2022
- Published by Springer Nature
- p. 514-532
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
- Open Access
- 16 November 2012
- Published by American Society of Hematology in Blood
- Vol. 120 (21) , 4049
Once Weekly Subcutanous Bortezomib with Cyclophosphamide and Dexamethasone Is Well Tolerated and Effective As Initial Treatment in Symptomatic Multiple Myeloma
Abstract 4049
- 16 November 2012
- Published by American Society of Hematology in Blood
- Vol. 120 (21) , 4049
Open AccessOnce Weekly Subcutanous Bortezomib with Cyclophosphamide and Dexamethasone Is Well Tolerated and Effective As Initial Treatment in Symptomatic Multiple Myeloma
Abstract 4049