Ting Liu
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
Ting Liu has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Yuzhuo Fu
Shanghai Jiao Tong University
12 shared publications - Suncheng Xiang
Shanghai Jiao Tong University
11 shared publications - Jingsheng Gao
Shanghai Jiao Tong University, Shanghai, China
7 shared publications - Dahong Qian
Shanghai Jiao Tong University
3 shared publications - Jiacheng Ruan
Shanghai Jiao Tong University
3 shared publications - Mingye Xie
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
3 shared publications
Latest Publications
- 11 December 2025
- Published by Springer Nature in Machine Learning
- Vol. 115 (1) , 1
DiverSeed: Integrating Active Learning for Target Domain Data Generation in Instruction Tuning
- 11 December 2025
- Published by Springer Nature in Machine Learning
- Vol. 115 (1) , 1
DiverSeed: Integrating Active Learning for Target Domain Data Generation in Instruction Tuning
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4251-4260
MPI-CD: Multi-Path Information Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4251-4260
Open AccessMPI-CD: Multi-Path Information Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8835-8844
GIST: Improving Parameter Efficient Fine-Tuning via Knowledge Interaction
Recently, the Parameter Efficient Fine-Tuning (PEFT) method, which adjusts or introduces fewer trainable parameters to calibrate pre-trained models on downstream tasks, has been a hot research topic. However, existing PEFT methods within the traditional fine-tuning framework have two main shortcomings: 1) They overlook the explicit association between trainable parameters and downstream knowledge. 2) They neglect the interaction between the intrinsic task-agnostic knowledge of pre-trained models and the task-specific knowledge of downstream tasks. These oversights lead to insufficient utilization of knowledge and suboptimal performance. To address these issues, we propose a novel fine-tuning framework, named GIST, that can be seamlessly integrated into the current PEFT methods in a plug-and-play manner. Specifically, our framework first introduces a trainable token, called the Gist token, when applying PEFT methods on downstream tasks. This token serves as an aggregator of the task-specific knowledge learned by the PEFT methods and builds an explicit association with downstream tasks. Furthermore, to facilitate explicit interaction between task-agnostic and task-specific knowledge, we introduce the concept of knowledge interaction via a Bidirectional Kullback-Leibler Divergence objective. As a result, PEFT methods within our framework can enable the pre-trained model to understand downstream tasks more comprehensively by fully leveraging both types of knowledge. Extensive experiments on the 35 datasets demonstrate the universality and scalability of our framework. Notably, the PEFT method within our GIST framework achieves up to a 2.25% increase on the VTAB-1K benchmark with an addition of just 0.8K parameters (0.009‰ of ViT-B/16). The code is available at https://github.com/JCruan519/GIST.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8835-8844
Open AccessGIST: Improving Parameter Efficient Fine-Tuning via Knowledge Interaction
Recently, the Parameter Efficient Fine-Tuning (PEFT) method, which adjusts or introduces fewer trainable parameters to calibrate pre-trained models on downstream tasks, has been a hot research topic. However, existing PEFT methods within the traditional fine-tuning framework have two main shortcomings: 1) They overlook the explicit association between trainable parameters and downstream knowledge. 2) They neglect the interaction between the intrinsic task-agnostic knowledge of pre-trained models and the task-specific knowledge of downstream tasks. These oversights lead to insufficient utilization of knowledge and suboptimal performance. To address these issues, we propose a novel fine-tuning framework, named GIST, that can be seamlessly integrated into the current PEFT methods in a plug-and-play manner. Specifically, our framework first introduces a trainable token, called the Gist token, when applying PEFT methods on downstream tasks. This token serves as an aggregator of the task-specific knowledge learned by the PEFT methods and builds an explicit association with downstream tasks. Furthermore, to facilitate explicit interaction between task-agnostic and task-specific knowledge, we introduce the concept of knowledge interaction via a Bidirectional Kullback-Leibler Divergence objective. As a result, PEFT methods within our framework can enable the pre-trained model to understand downstream tasks more comprehensively by fully leveraging both types of knowledge. Extensive experiments on the 35 datasets demonstrate the universality and scalability of our framework. Notably, the PEFT method within our GIST framework achieves up to a 2.25% increase on the VTAB-1K benchmark with an addition of just 0.8K parameters (0.009‰ of ViT-B/16). The code is available at https://github.com/JCruan519/GIST.
- 14 August 2024
- Published by Springer Nature
- p. 475-486
Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition
- 14 August 2024
- Published by Springer Nature
- p. 475-486
Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition
- 6 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (28) , 70883-70906
Toward an end-to-end implicit addressee modeling for dialogue disentanglement
- 6 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (28) , 70883-70906
Toward an end-to-end implicit addressee modeling for dialogue disentanglement
- Open Access
- 9 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (3) , 1-17
Rethinking Person Re-Identification via Semantic-based Pretraining
Pretraining is a dominant paradigm in computer vision. Generally, supervised ImageNet pretraining is commonly used to initialize the backbones of person re-identification (Re-ID) models. However, recent works show a surprising result that CNN-based pretraining on ImageNet has limited impacts on Re-ID system due to the large domain gap between ImageNet and person Re-ID data. To seek an alternative to traditional pretraining, here we investigate semantic-based pretraining as another method to utilize additional textual data against ImageNet pretraining. Specifically, we manually construct a diversified FineGPR-C caption dataset for the first time on person Re-ID events. Based on it, a pure semantic-based pretraining approach named VTBR is proposed to adopt dense captions to learn visual representations with fewer images. We train convolutional neural networks from scratch on the captions of FineGPR-C dataset, and then transfer them to downstream Re-ID tasks. Comprehensive experiments conducted on benchmark datasets show that our VTBR can achieve competitive performance compared with ImageNet pretraining—despite using up to 1.4× fewer images, revealing its potential in Re-ID pretraining. Our source code is also publicly available at https://github.com/JeremyXSC/VTBR .
- 9 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (3) , 1-17
Open AccessRethinking Person Re-Identification via Semantic-based Pretraining
Pretraining is a dominant paradigm in computer vision. Generally, supervised ImageNet pretraining is commonly used to initialize the backbones of person re-identification (Re-ID) models. However, recent works show a surprising result that CNN-based pretraining on ImageNet has limited impacts on Re-ID system due to the large domain gap between ImageNet and person Re-ID data. To seek an alternative to traditional pretraining, here we investigate semantic-based pretraining as another method to utilize additional textual data against ImageNet pretraining. Specifically, we manually construct a diversified FineGPR-C caption dataset for the first time on person Re-ID events. Based on it, a pure semantic-based pretraining approach named VTBR is proposed to adopt dense captions to learn visual representations with fewer images. We train convolutional neural networks from scratch on the captions of FineGPR-C dataset, and then transfer them to downstream Re-ID tasks. Comprehensive experiments conducted on benchmark datasets show that our VTBR can achieve competitive performance compared with ImageNet pretraining—despite using up to 1.4× fewer images, revealing its potential in Re-ID pretraining. Our source code is also publicly available at https://github.com/JeremyXSC/VTBR .
- Top Cited Papers
- 1 October 2023
- Published by Springer Nature
- p. 481-490
EGE-UNet: An Efficient Group Enhanced UNet for Skin Lesion Segmentation
- 1 October 2023
- Published by Springer Nature
- p. 481-490
Top Cited PapersEGE-UNet: An Efficient Group Enhanced UNet for Skin Lesion Segmentation
- 9 August 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (8) , 22837-22854
Editing outdoor scenes with a large annotated synthetic dataset
- 9 August 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (8) , 22837-22854
Editing outdoor scenes with a large annotated synthetic dataset
- 6 July 2023
- Published by Springer Nature in Machine Learning
- Vol. 113 (4) , 1921-1939
Deep multimodal representation learning for generalizable person re-identification
- 6 July 2023
- Published by Springer Nature in Machine Learning
- Vol. 113 (4) , 1921-1939
Deep multimodal representation learning for generalizable person re-identification
- Open Access
- 7 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (5s) , 1-20
Less Is More: Learning from Synthetic Data with Fine-Grained Attributes for Person Re-Identification
Person re-identification (ReID) plays an important role in applications such as public security and video surveillance. Recently, learning from synthetic data [ 9 ], which benefits from the popularity of the synthetic data engine, has attracted great attention from the public. However, existing datasets are limited in quantity, diversity, and realisticity, and cannot be efficiently used for the ReID problem. To address this challenge, we manually construct a large-scale person dataset named FineGPR with fine-grained attribute annotations. Moreover, aiming to fully exploit the potential of FineGPR and promote the efficient training from millions of synthetic data, we propose an attribute analysis pipeline called AOST based on the traditional machine learning algorithm, which dynamically learns attribute distribution in a real domain, then eliminates the gap between synthetic and real-world data and thus is freely deployed to new scenarios. Experiments conducted on benchmarks demonstrate that FineGPR with AOST outperforms (or is on par with) existing real and synthetic datasets, which suggests its feasibility for the ReID task and proves the proverbial less-is-more principle. Our synthetic FineGPR dataset is publicly available at https://github.com/JeremyXSC/FineGPR .
- 7 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (5s) , 1-20
Open AccessLess Is More: Learning from Synthetic Data with Fine-Grained Attributes for Person Re-Identification
Person re-identification (ReID) plays an important role in applications such as public security and video surveillance. Recently, learning from synthetic data [ 9 ], which benefits from the popularity of the synthetic data engine, has attracted great attention from the public. However, existing datasets are limited in quantity, diversity, and realisticity, and cannot be efficiently used for the ReID problem. To address this challenge, we manually construct a large-scale person dataset named FineGPR with fine-grained attribute annotations. Moreover, aiming to fully exploit the potential of FineGPR and promote the efficient training from millions of synthetic data, we propose an attribute analysis pipeline called AOST based on the traditional machine learning algorithm, which dynamically learns attribute distribution in a real domain, then eliminates the gap between synthetic and real-world data and thus is freely deployed to new scenarios. Experiments conducted on benchmarks demonstrate that FineGPR with AOST outperforms (or is on par with) existing real and synthetic datasets, which suggests its feasibility for the ReID task and proves the proverbial less-is-more principle. Our synthetic FineGPR dataset is publicly available at https://github.com/JeremyXSC/FineGPR .