2025
Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning
Shiping Ge, Qiang Chen, Zhiwei Jiang, Yafeng Yin, Qin Liu, Ziyao Chen, Qing Gu
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI Oral, CCF-A) 2025
We propose a novel implicit location-caption alignment paradigm based on complementary masking, which addresses the problem of unavailable supervision on event localization in the WSDVC task.
Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning
Shiping Ge, Qiang Chen, Zhiwei Jiang, Yafeng Yin, Qin Liu, Ziyao Chen, Qing Gu
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI Oral, CCF-A) 2025
We propose a novel implicit location-caption alignment paradigm based on complementary masking, which addresses the problem of unavailable supervision on event localization in the WSDVC task.
Fine-Grained Alignment Network for Zero-Shot Cross-Modal Retrieval
Shiping Ge, Zhiwei Jiang, Yafeng Yin, Cong Wang, Zifeng Cheng, Qing Gu
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM, CCF-B) 2025
We propose a novel end-to-end ZS-CMR framework FGAN, which can learn fine-grained alignment-aware representation for data of different modalities.
Fine-Grained Alignment Network for Zero-Shot Cross-Modal Retrieval
Shiping Ge, Zhiwei Jiang, Yafeng Yin, Cong Wang, Zifeng Cheng, Qing Gu
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM, CCF-B) 2025
We propose a novel end-to-end ZS-CMR framework FGAN, which can learn fine-grained alignment-aware representation for data of different modalities.
2024
A Debiased Nearest Neighbors Framework for Multi-Label Text Classification
Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Zhaoling Chen, Cong Wang, Shiping Ge, Qiguo Huang, Qing Gu
arXiv:2408.03202 Under review. 2024
We propose a DENN framework for MLTC, using debiased contrastive learning to adjust the biased embedding space for better 𝑘NN retrieval and using debiased confidence estimation to estimate the confidence of 𝑘NN.
A Debiased Nearest Neighbors Framework for Multi-Label Text Classification
Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Zhaoling Chen, Cong Wang, Shiping Ge, Qiguo Huang, Qing Gu
arXiv:2408.03202 Under review. 2024
We propose a DENN framework for MLTC, using debiased contrastive learning to adjust the biased embedding space for better 𝑘NN retrieval and using debiased confidence estimation to estimate the confidence of 𝑘NN.
Short Video Ordering via Position Decoding and Successor Prediction
Shiping Ge, Qiang Chen, Zhiwei Jiang, Yafeng Yin, Ziyao Chen, Qing Gu
Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR, CCF-A) 2024
We introduce a novel Short Video Ordering (SVO) task, curate a dedicated multimodal dataset for this task and present the performance of some benchmark methods.
Short Video Ordering via Position Decoding and Successor Prediction
Shiping Ge, Qiang Chen, Zhiwei Jiang, Yafeng Yin, Ziyao Chen, Qing Gu
Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR, CCF-A) 2024
We introduce a novel Short Video Ordering (SVO) task, curate a dedicated multimodal dataset for this task and present the performance of some benchmark methods.
Multi-Prompting Decoder Helps Better Language Understanding
Zifeng Cheng, Zhaoling Chen, Zhiwei Jiang, Yafeng Yin, Shiping Ge, Yuliang Liu, Qing Gu
arXiv:2406.06279 Under review. 2024
We propose an output-side PLMs adaptation framework, multi-prompting decoder, for few-shot classification.
Multi-Prompting Decoder Helps Better Language Understanding
Zifeng Cheng, Zhaoling Chen, Zhiwei Jiang, Yafeng Yin, Shiping Ge, Yuliang Liu, Qing Gu
arXiv:2406.06279 Under review. 2024
We propose an output-side PLMs adaptation framework, multi-prompting decoder, for few-shot classification.
2023
Learning Event-Specific Localization Preferences for Audio-Visual Event Localization
Shiping Ge, Zhiwei Jiang, Yafeng Yin, Cong Wang, Zifeng Cheng, Qing Gu
Proceedings of the 31st ACM International Conference on Multimedia (ACMMM, CCF-A) 2023
We propose a new event-aware double-branch localization paradigm to utilize event preferences for more accurate audio-visual event localization.
Learning Event-Specific Localization Preferences for Audio-Visual Event Localization
Shiping Ge, Zhiwei Jiang, Yafeng Yin, Cong Wang, Zifeng Cheng, Qing Gu
Proceedings of the 31st ACM International Conference on Multimedia (ACMMM, CCF-A) 2023
We propose a new event-aware double-branch localization paradigm to utilize event preferences for more accurate audio-visual event localization.
Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring
Cong Wang, Zhiwei Jiang, Yafeng Yin, Zifeng Cheng, Shiping Ge, Qing Gu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL, CCF-A) 2023
To aggregate these inconsistent quality signals into a unified supervision, we view the AES task as a ranking problem, and design a special Deep Pairwise Rank Aggregation (DPRA) loss for training.
Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring
Cong Wang, Zhiwei Jiang, Yafeng Yin, Zifeng Cheng, Shiping Ge, Qing Gu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL, CCF-A) 2023
To aggregate these inconsistent quality signals into a unified supervision, we view the AES task as a ranking problem, and design a special Deep Pairwise Rank Aggregation (DPRA) loss for training.
Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning
Cong Wang, Zhiwei Jiang, Yafeng Yin, Zifeng Cheng, Shiping Ge, Qing Gu
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI, CCF-A) 2023
We propose a constrained proxies learning method to explicitly control the global layout of classes in high-dimensional feature space, making it more suitable for ordinal classifcation.
Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning
Cong Wang, Zhiwei Jiang, Yafeng Yin, Zifeng Cheng, Shiping Ge, Qing Gu
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI, CCF-A) 2023
We propose a constrained proxies learning method to explicitly control the global layout of classes in high-dimensional feature space, making it more suitable for ordinal classifcation.
Learning Robust Multi-Modal Representation for Multi-Label Emotion Recognition via Adversarial Masking and Perturbation
Shiping Ge, Zhiwei Jiang, Cong Wang, Zifeng Cheng, Yafeng Yin, Qing Gu
Proceedings of the ACM Web Conference (WWW, CCF-A) 2023
We design a simple encoder-decoder style multi-modal emotion recognition model, and combine it with our specially-designed adversarial training strategies to learn more robust multi-modal representation for multi-label emotion recognition.
Learning Robust Multi-Modal Representation for Multi-Label Emotion Recognition via Adversarial Masking and Perturbation
Shiping Ge, Zhiwei Jiang, Cong Wang, Zifeng Cheng, Yafeng Yin, Qing Gu
Proceedings of the ACM Web Conference (WWW, CCF-A) 2023
We design a simple encoder-decoder style multi-modal emotion recognition model, and combine it with our specially-designed adversarial training strategies to learn more robust multi-modal representation for multi-label emotion recognition.
A Consistent Dual-MRC Framework for Emotion-cause Pair Extraction
Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Cong Wang, Shiping Ge, Qing Gu
ACM Transactions on Information Systems (TOIS, CCF-A) 2023
We propose a Consistent Dual-MRC (CD-MRC) framework to extract emotion-cause pairs in a dual-direction way, which enables a more comprehensive coverage of all pairing cases.
A Consistent Dual-MRC Framework for Emotion-cause Pair Extraction
Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Cong Wang, Shiping Ge, Qing Gu
ACM Transactions on Information Systems (TOIS, CCF-A) 2023
We propose a Consistent Dual-MRC (CD-MRC) framework to extract emotion-cause pairs in a dual-direction way, which enables a more comprehensive coverage of all pairing cases.
2022
Siamese Adversarial Network for Image Classification of Heavy Mineral Grains
Huizhen Hao, Zhiwei Jiang, Shiping Ge, Cong Wang, Qing Gu
Computers & Geosciences 2022
A Siamese Adversarial Network model (SAN) is proposed for the image classification of heavy mineral grains.
Siamese Adversarial Network for Image Classification of Heavy Mineral Grains
Huizhen Hao, Zhiwei Jiang, Shiping Ge, Cong Wang, Qing Gu
Computers & Geosciences 2022
A Siamese Adversarial Network model (SAN) is proposed for the image classification of heavy mineral grains.
2021
SiamFuseNet: A Pseudo-Siamese Network for Detritus Detection from Polarized Microscopic Images of River Sands
Cong Wang, Shiping Ge, Zhiwei Jiang, Huizhen Hao, Qing Gu
Computers & Geosciences 2021
A pesudo-siamese network named SiamFuseNet is proposed for the detritus detection.
SiamFuseNet: A Pseudo-Siamese Network for Detritus Detection from Polarized Microscopic Images of River Sands
Cong Wang, Shiping Ge, Zhiwei Jiang, Huizhen Hao, Qing Gu
Computers & Geosciences 2021
A pesudo-siamese network named SiamFuseNet is proposed for the detritus detection.
Dual-Input Attention Network for Automatic Identification of Detritus from River Sands
Shiping Ge, Cong Wang, Zhiwei Jiang, Huizhen Hao, Qing Gu
Computers & Geosciences 2021
A novel network architecture named DANet is proposed for the identification of detritus from river sands.
Dual-Input Attention Network for Automatic Identification of Detritus from River Sands
Shiping Ge, Cong Wang, Zhiwei Jiang, Huizhen Hao, Qing Gu
Computers & Geosciences 2021
A novel network architecture named DANet is proposed for the identification of detritus from river sands.