Kaifang Long
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
Kaifang Long has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Lianbo Ma
Northeastern University, Shenyang, China
3 shared publications - Guoyang Xie
Department of Intelligent Manufacturing CATL Ningde China
2 shared publications - Han Zhao
Shandong Normal University, Jinan, China
1 shared publication - Hui Yu
National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China
1 shared publication - Hui Yu
Shandong Normal University
1 shared publication - Jian Cheng
Research Institute of Mine Artificial Intelligence, Chinese Institute of Coal Science, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7060-7069
Understanding and Overcoming Cross-modal Fusion Bias in Multimodal Anomaly Detection From A Fisher Information Perspective
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7060-7069
Open AccessUnderstanding and Overcoming Cross-modal Fusion Bias in Multimodal Anomaly Detection From A Fisher Information Perspective
- 22 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 5458-5472
Enhancing Multimodal Learning via Hierarchical Fusion Architecture Search With Inconsistency Mitigation
The design of effective multimodal feature fusion strategies is the key task for multimodal learning, which often requires huge computational costs with extensive expertise. In this paper, we seek to enhance multimodal learning via hierarchical fusion architecture search with inconsistency mitigation. Different from previous works, our Hierarchical Fusion Multimodal Neural Architecture Search (HF-MNAS) considers the inconsistency in modalities and labels, and fine-grained exploitation in multi-level fusion architectures. Specifically, it disentangles the hierarchical fusion problem into two-level (macro- and micro-level) search spaces. In the macro-level search space, the high-level and low-level features are extracted and then connected in a fine-grained way, where the inconsistency mitigation module is designed to minimize discrepancies between modalities and labels in cell outputs. In the micro-level search space, we find that different intermediate nodes in the cells exhibit different importance degrees. Then, we propose an importance-based node selection mechanism to form the optimal cells for feature fusion. We evaluate HF-MNAS on a series of multimodal classification tasks. Empirical evidence shows that HF-MNAS achieves competitive trade-off performance across accuracy, search time, and inference speed. In particular, HF-MNAS consumes minimal computational cost compared with state-of-the-art MNASs. Furthermore, we theoretically and experimentally verify that the modality-label inconsistency deteriorates the overall fusion performance of models such as accuracy and F1 score, and demonstrate that the proposed inconsistency mitigation module could effectively mitigate this phenomenon.
- 22 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 5458-5472
Enhancing Multimodal Learning via Hierarchical Fusion Architecture Search With Inconsistency Mitigation
The design of effective multimodal feature fusion strategies is the key task for multimodal learning, which often requires huge computational costs with extensive expertise. In this paper, we seek to enhance multimodal learning via hierarchical fusion architecture search with inconsistency mitigation. Different from previous works, our Hierarchical Fusion Multimodal Neural Architecture Search (HF-MNAS) considers the inconsistency in modalities and labels, and fine-grained exploitation in multi-level fusion architectures. Specifically, it disentangles the hierarchical fusion problem into two-level (macro- and micro-level) search spaces. In the macro-level search space, the high-level and low-level features are extracted and then connected in a fine-grained way, where the inconsistency mitigation module is designed to minimize discrepancies between modalities and labels in cell outputs. In the micro-level search space, we find that different intermediate nodes in the cells exhibit different importance degrees. Then, we propose an importance-based node selection mechanism to form the optimal cells for feature fusion. We evaluate HF-MNAS on a series of multimodal classification tasks. Empirical evidence shows that HF-MNAS achieves competitive trade-off performance across accuracy, search time, and inference speed. In particular, HF-MNAS consumes minimal computational cost compared with state-of-the-art MNASs. Furthermore, we theoretically and experimentally verify that the modality-label inconsistency deteriorates the overall fusion performance of models such as accuracy and F1 score, and demonstrate that the proposed inconsistency mitigation module could effectively mitigate this phenomenon.
- 23 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (6) , 2828-2839
Text-Image Scene Graph Fusion for Multimodal Named Entity Recognition
With the popularity and widespread use of social media platforms such as Twitter and Facebook, massive amounts of text and image information posted by a variety of users have flooded these social media platforms. Thus, multi-modal named entity recognition (MNER) has become a research hotspot for the task of extracting named entities from multi-modal data. Empirically, the visual clues unrelated to text data may introduce uncertain or even negative impacts on the named entity recognition. The considerations of the relevance of multi-modal data have been ignored in the previous studies. In this paper, to effectively measure the relationship between text data and visual cues for improving the accuracy of named entities, we propose a text image scene graph fusion (TISGF) approach with a text-image similarity assessment module (TISA) and a text-image fusion module (TIF) for MNER. Specifically, we first construct two (visual and textual) scene graphs to exploit the joint features of objects and relations in text and image and encode the two scene graphs separately using a specific encoder pair. In this way, we can obtain both object-level and relationship-level cross-modal features. Subsequently, TISA is used to compute the similarity of the image and text data and to determine the proportion of visual information that will be retained for fusion. Finally, we use TIF to achieve a unified multi-modal representation of each word and predict the entity type using CRF. Extensive experiment results on two public datasets demonstrate the effectiveness and competitiveness of our proposed method for the MNER task.
- 23 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (6) , 2828-2839
Text-Image Scene Graph Fusion for Multimodal Named Entity Recognition
With the popularity and widespread use of social media platforms such as Twitter and Facebook, massive amounts of text and image information posted by a variety of users have flooded these social media platforms. Thus, multi-modal named entity recognition (MNER) has become a research hotspot for the task of extracting named entities from multi-modal data. Empirically, the visual clues unrelated to text data may introduce uncertain or even negative impacts on the named entity recognition. The considerations of the relevance of multi-modal data have been ignored in the previous studies. In this paper, to effectively measure the relationship between text data and visual cues for improving the accuracy of named entities, we propose a text image scene graph fusion (TISGF) approach with a text-image similarity assessment module (TISA) and a text-image fusion module (TIF) for MNER. Specifically, we first construct two (visual and textual) scene graphs to exploit the joint features of objects and relations in text and image and encode the two scene graphs separately using a specific encoder pair. In this way, we can obtain both object-level and relationship-level cross-modal features. Subsequently, TISA is used to compute the similarity of the image and text data and to determine the proportion of visual information that will be retained for fusion. Finally, we use TIF to achieve a unified multi-modal representation of each word and predict the entity type using CRF. Extensive experiment results on two public datasets demonstrate the effectiveness and competitiveness of our proposed method for the MNER task.
- Open Access
- 23 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (3) , 1-16
Deep Neural Network with Embedding Fusion for Chinese Named Entity Recognition
Chinese Named Entity Recognition (NER) is an essential task in natural language processing, and its performance directly impacts the downstream tasks. The main challenges in Chinese NER are the high dependence of named entities on context and the lack of word boundary information. Therefore, how to integrate relevant knowledge into the corresponding entity has become the primary task for Chinese NER. Both the lattice LSTM model and the WC-LSTM model did not make excellent use of contextual information. Additionally, the lattice LSTM model had a complex structure and did not exploit the word information well. To address the preceding problems, we propose a Chinese NER method based on the deep neural network with multiple ways of embedding fusion. First, we use a convolutional neural network to combine the contextual information of the input sequence and apply a self-attention mechanism to integrate lexicon knowledge, compensating for the lack of word boundaries. The word feature, context feature, bigram feature, and bigram context feature are obtained for each character. Second, four different features are used to fuse information at the embedding layer. As a result, four different word embeddings are obtained through cascading. Last, the fused feature information is input to the encoding and decoding layer. Experiments on three datasets show that our model can effectively improve the performance of Chinese NER.
- 23 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (3) , 1-16
Open AccessDeep Neural Network with Embedding Fusion for Chinese Named Entity Recognition
Chinese Named Entity Recognition (NER) is an essential task in natural language processing, and its performance directly impacts the downstream tasks. The main challenges in Chinese NER are the high dependence of named entities on context and the lack of word boundary information. Therefore, how to integrate relevant knowledge into the corresponding entity has become the primary task for Chinese NER. Both the lattice LSTM model and the WC-LSTM model did not make excellent use of contextual information. Additionally, the lattice LSTM model had a complex structure and did not exploit the word information well. To address the preceding problems, we propose a Chinese NER method based on the deep neural network with multiple ways of embedding fusion. First, we use a convolutional neural network to combine the contextual information of the input sequence and apply a self-attention mechanism to integrate lexicon knowledge, compensating for the lack of word boundaries. The word feature, context feature, bigram feature, and bigram context feature are obtained for each character. Second, four different features are used to fuse information at the embedding layer. As a result, four different word embeddings are obtained through cascading. Last, the fused feature information is input to the encoding and decoding layer. Experiments on three datasets show that our model can effectively improve the performance of Chinese NER.
- Open Access
Application of Data Encryption in Chinese Named Entity Recognition
Recently, with the continuous development of deep learning, the performance of named entity recognition tasks has been dramatically improved. However, the privacy and the confidentiality of data in some specific fields, such as biomedical and military, cause insufficient data to support the training of deep neural networks. In this paper, we propose an encryption learning framework to address the problems of data leakage and inconvenient disclosure of sensitive data in certain domains. We introduce multiple encryption algorithms to encrypt training data in the named entity recognition task for the first time. In other words, we train the deep neural network using the encrypted data. We conduct experiments on six Chinese datasets, three of which are constructed by ourselves. The experimental results show that the encryption method achieves satisfactory results. The performance of some models trained with encrypted data even exceeds the performance of the unencrypted method, which verifies the effectiveness of the introduced encryption method and solves the problem of data leakage to a certain extent.
Open AccessApplication of Data Encryption in Chinese Named Entity Recognition
Recently, with the continuous development of deep learning, the performance of named entity recognition tasks has been dramatically improved. However, the privacy and the confidentiality of data in some specific fields, such as biomedical and military, cause insufficient data to support the training of deep neural networks. In this paper, we propose an encryption learning framework to address the problems of data leakage and inconvenient disclosure of sensitive data in certain domains. We introduce multiple encryption algorithms to encrypt training data in the named entity recognition task for the first time. In other words, we train the deep neural network using the encrypted data. We conduct experiments on six Chinese datasets, three of which are constructed by ourselves. The experimental results show that the encryption method achieves satisfactory results. The performance of some models trained with encrypted data even exceeds the performance of the unencrypted method, which verifies the effectiveness of the introduced encryption method and solves the problem of data leakage to a certain extent.