Bing Su
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
Bing Su has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Ji-Rong Wen
Gaoling School of Artificial Intelligence, Renmin University of China, China
9 shared publications - Jiangmeng Li
Institute of Software, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China
8 shared publications - Wenwen Qiang
Institute of Software, Chinese Academy of Sciences, Beijing, China
8 shared publications - Hui Xiong
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and The Hong Kong University of Science and Technology, Hong Kong SAR, China
7 shared publications - Changwen Zheng
Institute of Software Chinese Academy of Sciences Beijing Beijing China
6 shared publications Xiaoqing Ding
State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China
5 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 10866-10876
Biological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 10866-10876
Open AccessBiological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction
- 3 February 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (3) , 100
Uniformity Preserving Transfer for Visual Prompt Tuning under Long-tailed Distribution
- 3 February 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (3) , 100
Uniformity Preserving Transfer for Visual Prompt Tuning under Long-tailed Distribution
- Open Access
Regulatory DNA sequence Design with Reinforcement Learning
Cis-regulatory elements (CREs), such as promoters and enhancers, are relatively short DNA sequences that directly regulate gene expression. The fitness of CREs, measured by their ability to modulate gene expression, highly depends on the nucleotide sequences, especially specific motifs known as transcription factor binding sites (TFBSs). Designing high-fitness CREs is crucial for therapeutic and bioengineering applications. Current CRE design methods are limited by two major drawbacks: (1) they typically rely on iterative optimization strategies that modify existing sequences and are prone to local optima, and (2) they lack the guidance of biological prior knowledge in sequence optimization. In this paper, we address these limitations by proposing a generative approach that leverages reinforcement learning (RL) to fine-tune a pre-trained autoregressive (AR) model. Our method incorporates data-driven biological priors by deriving computational inference-based rewards that simulate the addition of activator TFBSs and removal of repressor TFBSs, which are then integrated into the RL process. We evaluate our method on promoter design tasks in two yeast media conditions and enhancer design tasks for three human cell types, demonstrating its ability to generate high-fitness CREs while maintaining sequence diversity. The code is available at https://github.com/yangzhao1230/TACO.
Open AccessRegulatory DNA sequence Design with Reinforcement Learning
Cis-regulatory elements (CREs), such as promoters and enhancers, are relatively short DNA sequences that directly regulate gene expression. The fitness of CREs, measured by their ability to modulate gene expression, highly depends on the nucleotide sequences, especially specific motifs known as transcription factor binding sites (TFBSs). Designing high-fitness CREs is crucial for therapeutic and bioengineering applications. Current CRE design methods are limited by two major drawbacks: (1) they typically rely on iterative optimization strategies that modify existing sequences and are prone to local optima, and (2) they lack the guidance of biological prior knowledge in sequence optimization. In this paper, we address these limitations by proposing a generative approach that leverages reinforcement learning (RL) to fine-tune a pre-trained autoregressive (AR) model. Our method incorporates data-driven biological priors by deriving computational inference-based rewards that simulate the addition of activator TFBSs and removal of repressor TFBSs, which are then integrated into the RL process. We evaluate our method on promoter design tasks in two yeast media conditions and enhancer design tasks for three human cell types, demonstrating its ability to generate high-fitness CREs while maintaining sequence diversity. The code is available at https://github.com/yangzhao1230/TACO.
- 22 February 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (7) , 4134-4157
Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks
- 22 February 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (7) , 4134-4157
Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks
- 31 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
Variational global clue inference for weakly supervised video moment retrieval
- 31 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
Variational global clue inference for weakly supervised video moment retrieval
- Open Access
Spatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction
Human motion prediction (HMP) involves forecasting future human motion based on historical data. Graph Convolutional Networks (GCNs) have garnered widespread attention in this field for their proficiency in capturing relationships among joints in human motion. However, existing GCN-based methods tend to focus on either temporal-domain or spatial-domain features, or they combine spatio-temporal features without fully leveraging the complementarity and cross-dependency of these two features. In this paper, we propose the Spatial-Temporal Multi-Subgraph Graph Convolutional Network (STMS-GCN) to capture complex spatio-temporal dependencies in human motion. Specifically, we decouple the modeling of temporal and spatial dependencies, enabling cross-domain knowledge transfer at multiple scales through a spatio-temporal information consistency constraint mechanism. Besides, we utilize multiple subgraphs to extract richer motion information and enhance the learning associations of diverse subgraphs through a homogeneous information constraint mechanism. Extensive experiments on the standard HMP benchmarks demonstrate the superiority of our method.
Open AccessSpatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction
Human motion prediction (HMP) involves forecasting future human motion based on historical data. Graph Convolutional Networks (GCNs) have garnered widespread attention in this field for their proficiency in capturing relationships among joints in human motion. However, existing GCN-based methods tend to focus on either temporal-domain or spatial-domain features, or they combine spatio-temporal features without fully leveraging the complementarity and cross-dependency of these two features. In this paper, we propose the Spatial-Temporal Multi-Subgraph Graph Convolutional Network (STMS-GCN) to capture complex spatio-temporal dependencies in human motion. Specifically, we decouple the modeling of temporal and spatial dependencies, enabling cross-domain knowledge transfer at multiple scales through a spatio-temporal information consistency constraint mechanism. Besides, we utilize multiple subgraphs to extract richer motion information and enhance the learning associations of diverse subgraphs through a homogeneous information constraint mechanism. Extensive experiments on the standard HMP benchmarks demonstrate the superiority of our method.
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 2544-2557
Instance-Specific Semantic Augmentation for Long-Tailed Image Classification
Recent long-tailed classification methods generally adopt the two-stage pipeline and focus on learning the classifier to tackle the imbalanced data in the second stage via re-sampling or re-weighting, but the classifier is easily prone to overconfidence in head classes. Data augmentation is a natural way to tackle this issue. Existing augmentation methods either perform low-level transformations or apply the same semantic transformation for all instances. However, meaningful augmentations for different instances should be different. In this paper, we propose feature-level augmentation (FLA) and pixel-level augmentation (PLA) learning methods for long-tailed image classification. In the first stage, the feature space is learned from the original imbalanced data. In the second stage, we model the semantic within-class transformation range for each instance by a specific Gaussian distribution and design a semantic transformation generator (STG) to predict the distribution from the instance itself. We train STG by constructing ground-truth distributions for instances of head classes in the feature space. In the third stage, for FLA, we generate instance-specific transformations by STG to obtain feature augmentations of tail classes for fine-tuning the classifier. For PLA, we use STG to guide pixel-level augmentations for fine-tuning the backbone. The proposed augmentation strategy can be combined with different existing long-tail classification methods. Extensive experiments on five imbalanced datasets show the effectiveness of our method.
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 2544-2557
Instance-Specific Semantic Augmentation for Long-Tailed Image Classification
Recent long-tailed classification methods generally adopt the two-stage pipeline and focus on learning the classifier to tackle the imbalanced data in the second stage via re-sampling or re-weighting, but the classifier is easily prone to overconfidence in head classes. Data augmentation is a natural way to tackle this issue. Existing augmentation methods either perform low-level transformations or apply the same semantic transformation for all instances. However, meaningful augmentations for different instances should be different. In this paper, we propose feature-level augmentation (FLA) and pixel-level augmentation (PLA) learning methods for long-tailed image classification. In the first stage, the feature space is learned from the original imbalanced data. In the second stage, we model the semantic within-class transformation range for each instance by a specific Gaussian distribution and design a semantic transformation generator (STG) to predict the distribution from the instance itself. We train STG by constructing ground-truth distributions for instances of head classes in the feature space. In the third stage, for FLA, we generate instance-specific transformations by STG to obtain feature augmentations of tail classes for fine-tuning the classifier. For PLA, we use STG to guide pixel-level augmentations for fine-tuning the backbone. The proposed augmentation strategy can be combined with different existing long-tail classification methods. Extensive experiments on five imbalanced datasets show the effectiveness of our method.
- Open Access
Supporting Vision-Language Model Inference with Confounder-pruning Knowledge Prompt
Vision-language models are pre-trained by aligning image-text pairs in a common space to deal with open-set visual concepts. To boost the transferability of the pre-trained models, recent works adopt fixed or learnable prompts, i.e., classification weights are synthesized from natural language describing task-relevant categories, to reduce the gap between tasks in the training and test phases. However, how and what prompts can improve inference performance remains unclear. In this paper, we explicitly clarify the importance of including semantic information in prompts, while existing prompting methods generate prompts without exploring the semantic information of textual labels. Manually constructing prompts with rich semantics requires domain expertise and is extremely time-consuming. To cope with this issue, we propose a semantic-aware prompt learning method, namely CPKP, which retrieves an ontological knowledge graph by treating the textual label as a query to extract task-relevant semantic information. CPKP further introduces a double-tier confounder-pruning procedure to refine the derived semantic information. The graph-tier confounders are gradually identified and phased out, inspired by the principle of Granger causality. The feature-tier confounders are demolished by following the maximum entropy principle in information theory. Empirically, the evaluations demonstrate the effectiveness of CPKP, e.g., with two shots, CPKP outperforms the manual-prompt method by 4.64% and the learnable-prompt method by 1.09% on average, and the superiority of CPKP in domain generalization compared to benchmark approaches. Our implementation is available at https://github.com/Mowenyii/CPKP.
Open AccessSupporting Vision-Language Model Inference with Confounder-pruning Knowledge Prompt
Vision-language models are pre-trained by aligning image-text pairs in a common space to deal with open-set visual concepts. To boost the transferability of the pre-trained models, recent works adopt fixed or learnable prompts, i.e., classification weights are synthesized from natural language describing task-relevant categories, to reduce the gap between tasks in the training and test phases. However, how and what prompts can improve inference performance remains unclear. In this paper, we explicitly clarify the importance of including semantic information in prompts, while existing prompting methods generate prompts without exploring the semantic information of textual labels. Manually constructing prompts with rich semantics requires domain expertise and is extremely time-consuming. To cope with this issue, we propose a semantic-aware prompt learning method, namely CPKP, which retrieves an ontological knowledge graph by treating the textual label as a query to extract task-relevant semantic information. CPKP further introduces a double-tier confounder-pruning procedure to refine the derived semantic information. The graph-tier confounders are gradually identified and phased out, inspired by the principle of Granger causality. The feature-tier confounders are demolished by following the maximum entropy principle in information theory. Empirically, the evaluations demonstrate the effectiveness of CPKP, e.g., with two shots, CPKP outperforms the manual-prompt method by 4.64% and the learnable-prompt method by 1.09% on average, and the superiority of CPKP in domain generalization compared to benchmark approaches. Our implementation is available at https://github.com/Mowenyii/CPKP.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3954-3964
Synthesizing Long-Term Human Motions with Diffusion Models via Coherent Sampling
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3954-3964
Open AccessSynthesizing Long-Term Human Motions with Diffusion Models via Coherent Sampling
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5302-5310
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5302-5310
Open AccessZero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization