Fengling Li
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
Fengling Li has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Lei Zhu
Tongji University, Shanghai, China
18 shared publications - Jingjing Li
University of Electronic Science and Technology of China, Chengdu, China
14 shared publications - Tianshi Wang
Tongji University, Shanghai, China
9 shared publications - Xiaojun Chang
University of Science and Technology of China, Hefei, China
5 shared publications - Heng Tao Shen
Tongji University, Shanghai, China
4 shared publications - Zheng Zhang
University of California Santa Barbara
4 shared publications
Latest Publications
- 5 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Composite Proxy-based Hierarchical Contrastive Hashing for Cross-modal Retrieval
Supervised cross-modal hashing retrieval leverages labeled information to map heterogeneous multimodal data into a unified hash space, enabling efficient and accurate similarity search. Proxy-based method directly projects labeled information into proxy hash codes and consequently leverages them to guide the hashing network training, achieving excellent retrieval performance. Although making impressive progress, these methods fail to capture label-to-label semantic relationships in multi-label data, i.e., semantic affinities between different labels and co-occurrence relations of different labels, which generally results in sub-optimal hash codes. To address this limitation, we propose a novel cross-modal hashing method, termed Composite Proxy-based Hierarchical Contrastive Hashing (CPHCH), which can capture complex semantic relationships by composite semantic proxies. Specifically, a Graph convolutional network-based Semantic Enhancement (GSE) module is first designed to explicitly capture the semantic similarities and co-occurrence relations between labels by integrating CLIP’s semantic priors with Pointwise Mutual Information (PMI) statistics. And then the learned semantic similarities and co-occurrence relationships are injected into the composite proxy hash codes learning, thereby enhancing their semantic discriminative ability. Finally, we propose a Hierarchy-aware Dynamic Contrastive Weighting Learning (HDCWL) module, which hierarchically weights the similarities between data-proxy hash codes using a Jaccard similarity matrix, ensuring prioritized alignment of fully matched samples while preserving fine-grained semantic differences in partially matched samples. Experimental results demonstrate that CPHCH significantly outperforms baseline methods on cross-modal retrieval tasks.
- 5 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Composite Proxy-based Hierarchical Contrastive Hashing for Cross-modal Retrieval
Supervised cross-modal hashing retrieval leverages labeled information to map heterogeneous multimodal data into a unified hash space, enabling efficient and accurate similarity search. Proxy-based method directly projects labeled information into proxy hash codes and consequently leverages them to guide the hashing network training, achieving excellent retrieval performance. Although making impressive progress, these methods fail to capture label-to-label semantic relationships in multi-label data, i.e., semantic affinities between different labels and co-occurrence relations of different labels, which generally results in sub-optimal hash codes. To address this limitation, we propose a novel cross-modal hashing method, termed Composite Proxy-based Hierarchical Contrastive Hashing (CPHCH), which can capture complex semantic relationships by composite semantic proxies. Specifically, a Graph convolutional network-based Semantic Enhancement (GSE) module is first designed to explicitly capture the semantic similarities and co-occurrence relations between labels by integrating CLIP’s semantic priors with Pointwise Mutual Information (PMI) statistics. And then the learned semantic similarities and co-occurrence relationships are injected into the composite proxy hash codes learning, thereby enhancing their semantic discriminative ability. Finally, we propose a Hierarchy-aware Dynamic Contrastive Weighting Learning (HDCWL) module, which hierarchically weights the similarities between data-proxy hash codes using a Jaccard similarity matrix, ensuring prioritized alignment of fully matched samples while preserving fine-grained semantic differences in partially matched samples. Experimental results demonstrate that CPHCH significantly outperforms baseline methods on cross-modal retrieval tasks.
- Open Access
- 19 May 2026
- Published by Elsevier in Information Fusion
- Vol. 135
Internalizing reasoning via chain-of-thought and retrieval augmentation for multimodal sentiment analysis
- 19 May 2026
- Published by Elsevier in Information Fusion
- Vol. 135
Open AccessInternalizing reasoning via chain-of-thought and retrieval augmentation for multimodal sentiment analysis
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 5496-5508
Training-Free Open-Set Domain Adaptation With Vision-Language Models
With the prevalence of pre-trained vision-language models like CLIP, leveraging the generic knowledge embedded in CLIP for domain adaptation has proved to be a promising direction. However, most existing CLIP-based methods are limited to closed-set settings. This is primarily because CLIP needs the semantic labels of unknown classes for inference, thus making it not applicable to Open-Set Domain Adaptation (OSDA). To utilize the complementary roles of CLIP and the source model, our paper proposes a novel Semantic-guided Target Adaptation (SemTA) framework for OSDA in a training-free manner. Specifically, we introduce an unknown semantic discovery module. It uses the cluster centroids of the target data to obtain the semantic labels of unknown classes from the worldwide corpus. Then, the semantic-based inference can be performed with CLIP. Additionally, the dual sample attention mechanism is implemented to output sample-based inference. Representative features from both the source model and CLIP serve as the key to improve task specificity. Compared to previous OSDA methods which reject unknown data by confidence threshold, the proposed approach is more practical and offers better interpretability. Comprehensive evaluations on four benchmarks reveal our method sets a new state-of-the-art even without training. Our code will be publicly available soon.
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 5496-5508
Training-Free Open-Set Domain Adaptation With Vision-Language Models
With the prevalence of pre-trained vision-language models like CLIP, leveraging the generic knowledge embedded in CLIP for domain adaptation has proved to be a promising direction. However, most existing CLIP-based methods are limited to closed-set settings. This is primarily because CLIP needs the semantic labels of unknown classes for inference, thus making it not applicable to Open-Set Domain Adaptation (OSDA). To utilize the complementary roles of CLIP and the source model, our paper proposes a novel Semantic-guided Target Adaptation (SemTA) framework for OSDA in a training-free manner. Specifically, we introduce an unknown semantic discovery module. It uses the cluster centroids of the target data to obtain the semantic labels of unknown classes from the worldwide corpus. Then, the semantic-based inference can be performed with CLIP. Additionally, the dual sample attention mechanism is implemented to output sample-based inference. Representative features from both the source model and CLIP serve as the key to improve task specificity. Compared to previous OSDA methods which reject unknown data by confidence threshold, the proposed approach is more practical and offers better interpretability. Comprehensive evaluations on four benchmarks reveal our method sets a new state-of-the-art even without training. Our code will be publicly available soon.
- Open Access
- 9 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (4) , 1-22
Noise-Robust Generative Hashing for Cross-Modal Retrieval
Deep hashing has proven remarkable effectiveness for large-scale cross-modal retrieval, yet its performance is highly vulnerable to supervisory noise, such as mismatched cross-modal correspondences and incorrect category labels. Such noise is prevalent in real-world scenarios, where correspondence mismatches and label inaccuracies often coexist, posing significant challenges for learning accurate multimodal representations. Existing methods typically address only a single type of noise in isolation and neglect the potential value of noisy data, resulting in limited performance gains. To address these challenges, we propose Noise-Robust Generative Hashing (NRGH), a unified framework designed to accommodate various forms of noise inherent in cross-modal retrieval. Specifically, NRGH introduces a hash-driven noise estimation module that computes the confidence score for each multimodal sample by combining frozen auxiliary hash functions with a Gaussian mixture model. Guided by these confidence scores, NRGH performs data correction through two stages: generative text refinement and multi-label probability calibration. The former leverages a pre-trained vision-language model to generate descriptive captions that refine noisy textual information, while the latter corrects noisy labels using confidence-aware soft labels. Furthermore, a dynamic margin contrastive loss adaptively modulates the data contribution of each sample based on its confidence, enabling sample-level adaptive learning. Extensive experiments on benchmark datasets demonstrate that NRGH significantly exceeds state-of-the-art baselines in various noisy scenarios, delivering superior robustness and accuracy. Our source codes and datasets are available at https://github.com/xiaolaohuuu/NRGH .
- 9 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (4) , 1-22
Open AccessNoise-Robust Generative Hashing for Cross-Modal Retrieval
Deep hashing has proven remarkable effectiveness for large-scale cross-modal retrieval, yet its performance is highly vulnerable to supervisory noise, such as mismatched cross-modal correspondences and incorrect category labels. Such noise is prevalent in real-world scenarios, where correspondence mismatches and label inaccuracies often coexist, posing significant challenges for learning accurate multimodal representations. Existing methods typically address only a single type of noise in isolation and neglect the potential value of noisy data, resulting in limited performance gains. To address these challenges, we propose Noise-Robust Generative Hashing (NRGH), a unified framework designed to accommodate various forms of noise inherent in cross-modal retrieval. Specifically, NRGH introduces a hash-driven noise estimation module that computes the confidence score for each multimodal sample by combining frozen auxiliary hash functions with a Gaussian mixture model. Guided by these confidence scores, NRGH performs data correction through two stages: generative text refinement and multi-label probability calibration. The former leverages a pre-trained vision-language model to generate descriptive captions that refine noisy textual information, while the latter corrects noisy labels using confidence-aware soft labels. Furthermore, a dynamic margin contrastive loss adaptively modulates the data contribution of each sample based on its confidence, enabling sample-level adaptive learning. Extensive experiments on benchmark datasets demonstrate that NRGH significantly exceeds state-of-the-art baselines in various noisy scenarios, delivering superior robustness and accuracy. Our source codes and datasets are available at https://github.com/xiaolaohuuu/NRGH .
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2654-2667
PIC-CMH: Efficient Prompt-Infused Continual Cross-Modal Hashing
Cross-modal hashing models face significant challenges in handling continuous data growth, particularly in balancing the plasticity to learn new knowledge and the stability to retain prior cross-modal knowledge. Existing studies partially address this by maintaining previous mappings or extending hash codes, but struggle to reconcile plasticity and stability while requiring heavy parameter optimization. To tackle this, we propose an efficient Prompt-Infused Continual Cross-Modal Hashing (PIC-CMH) approach designed for hash learning with the continuous growth of multi-modal data and emerging knowledge. Specifically, PIC-CMH introduces a finite set of learnable multi-modal prompts, including global and task-specific expert prompts, which work in synergy with multi-modal representations. All prompts are optimized with the hash functions via backpropagation after Gaussian initialization. Global prompts stay learnable throughout, linking tasks, while expert prompts are updated only within their tasks, facilitating knowledge acquisition and mitigating catastrophic forgetting in continual learning. By freezing the pre-trained models used for multi-modal representations, continual learning is confined to the lightweight multi-modal prompts and hash functions, significantly reducing computational overhead. Extensive experiments demonstrate that PIC-CMH effectively addresses the stability-plasticity trade-off in cross-modal hash learning, delivering high retrieval accuracy with low computational cost and a simple yet efficient architecture. The source codes and datasets are available at https://github.com/styx29-0/PIC-CMH.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2654-2667
PIC-CMH: Efficient Prompt-Infused Continual Cross-Modal Hashing
Cross-modal hashing models face significant challenges in handling continuous data growth, particularly in balancing the plasticity to learn new knowledge and the stability to retain prior cross-modal knowledge. Existing studies partially address this by maintaining previous mappings or extending hash codes, but struggle to reconcile plasticity and stability while requiring heavy parameter optimization. To tackle this, we propose an efficient Prompt-Infused Continual Cross-Modal Hashing (PIC-CMH) approach designed for hash learning with the continuous growth of multi-modal data and emerging knowledge. Specifically, PIC-CMH introduces a finite set of learnable multi-modal prompts, including global and task-specific expert prompts, which work in synergy with multi-modal representations. All prompts are optimized with the hash functions via backpropagation after Gaussian initialization. Global prompts stay learnable throughout, linking tasks, while expert prompts are updated only within their tasks, facilitating knowledge acquisition and mitigating catastrophic forgetting in continual learning. By freezing the pre-trained models used for multi-modal representations, continual learning is confined to the lightweight multi-modal prompts and hash functions, significantly reducing computational overhead. Extensive experiments demonstrate that PIC-CMH effectively addresses the stability-plasticity trade-off in cross-modal hash learning, delivering high retrieval accuracy with low computational cost and a simple yet efficient architecture. The source codes and datasets are available at https://github.com/styx29-0/PIC-CMH.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 12207-12218
Meta-Semantic Induction for Generalized Cross-Modal Hashing
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 12207-12218
Meta-Semantic Induction for Generalized Cross-Modal Hashing
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 12170-12181
From Incomplete to Valuable: Partial Cross-Modal Hashing via Coarse-to-Fine Semantic Completion
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 12170-12181
From Incomplete to Valuable: Partial Cross-Modal Hashing via Coarse-to-Fine Semantic Completion
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 7125-7139
Prompt-Driven Bit Extension Hashing for Continual Cross-Modal Retrieval
Continual cross-modal hashing is critical for efficient retrieval across heterogeneous modalities in dynamic environments. Yet, existing approaches primarily focus on mitigating catastrophic forgetting, while overlooking two key challenges: 1) the hash collision arising from the excessive utilization of the Hamming space across tasks, and 2) the absence of consistency modeling for cross-modal dynamic associations. To address these challenges, we introduce Prompt-driven Bit Extension Hashing (PBEH), a novel framework that dynamically extends hash codes to prevent hash collisions and capture evolving modality-aligned semantics in continuously expanding multi-modal data. Specifically, PBEH first adaptively initializes a set of modality-shared prompts for each task, which are jointly optimized with the hashing functions to enhance model plasticity and retain task-specific knowledge, enabling continual cross-modal semantic alignment. In parallel, a dynamic Hamming space extension mechanism allocates dedicated capacity per task, alleviating bottlenecks and inter-task collisions. During retrieval, queries are encoded via the extended hash functions and matched to stored codes using a truncated strategy for compatibility. To ensure efficiency and semantic stability, only the prompts and hashing functions are updated while the pre-trained backbone remains frozen. Extensive experiments demonstrate that PBEH achieves superior and stable performance in continual cross-modal retrieval with substantially reduced computational overhead. The source codes and datasets are available at https://github.com/Liuwwhh/PBEH.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 7125-7139
Prompt-Driven Bit Extension Hashing for Continual Cross-Modal Retrieval
Continual cross-modal hashing is critical for efficient retrieval across heterogeneous modalities in dynamic environments. Yet, existing approaches primarily focus on mitigating catastrophic forgetting, while overlooking two key challenges: 1) the hash collision arising from the excessive utilization of the Hamming space across tasks, and 2) the absence of consistency modeling for cross-modal dynamic associations. To address these challenges, we introduce Prompt-driven Bit Extension Hashing (PBEH), a novel framework that dynamically extends hash codes to prevent hash collisions and capture evolving modality-aligned semantics in continuously expanding multi-modal data. Specifically, PBEH first adaptively initializes a set of modality-shared prompts for each task, which are jointly optimized with the hashing functions to enhance model plasticity and retain task-specific knowledge, enabling continual cross-modal semantic alignment. In parallel, a dynamic Hamming space extension mechanism allocates dedicated capacity per task, alleviating bottlenecks and inter-task collisions. During retrieval, queries are encoded via the extended hash functions and matched to stored codes using a truncated strategy for compatibility. To ensure efficiency and semantic stability, only the prompts and hashing functions are updated while the pre-trained backbone remains frozen. Extensive experiments demonstrate that PBEH achieves superior and stable performance in continual cross-modal retrieval with substantially reduced computational overhead. The source codes and datasets are available at https://github.com/Liuwwhh/PBEH.
- 7 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 2954-2969
Dynamic Bit-Wise Semantic Transformer Hashing for Multi-Modal Retrieval
Multi-modal hashing aims to succinctly encode heterogeneous modalities into binary hash codes, facilitating efficient multimedia retrieval characterized by low storage demands and high retrieval speed. Despite the commendable achievements of existing methods, they still face three crucial challenges: 1) Inadequate bridging of the heterogeneous modality gap through coarse, global feature-level alignment and fusion. 2) The erosion of bit independence and consequent limitations on the semantic representation capacity of hash codes during feature-level hash code learning. 3) The insufficiency of binary label-based pairwise semantic preservation strategies in capturing intricate fine-grained semantic correlations within multi-modal data. To address these challenges, this paper introduces the Dynamic Bit-wise Semantic Transformer Hashing (DBSTH) framework. Remarkably, it treats each hash bit as a unique semantic concept, facilitating concept-level alignment of heterogeneous modalities. This safeguards bit independence and augments representation capabilities. Specifically, we devise a dynamic unit fusion strategy for the adaptive combination of local multi-modal information units, facilitating the acquisition of bit-wise semantic concepts. Subsequently, we incorporate a transformer encoder to refine these concepts by uncovering latent correlations among distinct concepts. Finally, we perform the multi-modal alignment and fusion on the fine-grained concept-level, independently encoding each concept to its corresponding hash bit. To provide enhanced guidance for concept learning, a label prototype learning mechanism is introduced, which learns prototype embeddings for all categories through the consideration of co-occurrence priors. This mechanism effectively captures fine-grained explicit semantic correlations and generates supervising hash codes. Additionally, to improve the robustness of the hashing model in handling noisy multi-modal data, a masked concept learning strategy is introduced, facilitating the acquisition of resilient semantic concepts. Extensive experiments conducted on three widely tested multi-modal retrieval datasets demonstrate the superiority of our method in conventional, noisy, and open-set retrieval scenarios.
- 7 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 2954-2969
Dynamic Bit-Wise Semantic Transformer Hashing for Multi-Modal Retrieval
Multi-modal hashing aims to succinctly encode heterogeneous modalities into binary hash codes, facilitating efficient multimedia retrieval characterized by low storage demands and high retrieval speed. Despite the commendable achievements of existing methods, they still face three crucial challenges: 1) Inadequate bridging of the heterogeneous modality gap through coarse, global feature-level alignment and fusion. 2) The erosion of bit independence and consequent limitations on the semantic representation capacity of hash codes during feature-level hash code learning. 3) The insufficiency of binary label-based pairwise semantic preservation strategies in capturing intricate fine-grained semantic correlations within multi-modal data. To address these challenges, this paper introduces the Dynamic Bit-wise Semantic Transformer Hashing (DBSTH) framework. Remarkably, it treats each hash bit as a unique semantic concept, facilitating concept-level alignment of heterogeneous modalities. This safeguards bit independence and augments representation capabilities. Specifically, we devise a dynamic unit fusion strategy for the adaptive combination of local multi-modal information units, facilitating the acquisition of bit-wise semantic concepts. Subsequently, we incorporate a transformer encoder to refine these concepts by uncovering latent correlations among distinct concepts. Finally, we perform the multi-modal alignment and fusion on the fine-grained concept-level, independently encoding each concept to its corresponding hash bit. To provide enhanced guidance for concept learning, a label prototype learning mechanism is introduced, which learns prototype embeddings for all categories through the consideration of co-occurrence priors. This mechanism effectively captures fine-grained explicit semantic correlations and generates supervising hash codes. Additionally, to improve the robustness of the hashing model in handling noisy multi-modal data, a masked concept learning strategy is introduced, facilitating the acquisition of resilient semantic concepts. Extensive experiments conducted on three widely tested multi-modal retrieval datasets demonstrate the superiority of our method in conventional, noisy, and open-set retrieval scenarios.