Wei 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
Wei Li has a total of 113 co-authors. Here are the top co-authors by number of shared publications:
- Yi Yu
Hiroshima University, Japan
10 shared publications Xiangyang Xue
School of Computer Science, Fudan University, Shanghai, P. R. China
9 shared publications- Xulong Zhang
Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China
9 shared publications Bilei Zhu
School of Computer Science, Fudan University, China
7 shared publications- Suhua Tang
The University of Electro-Communications, Tokyo, Japan
5 shared publications Jiale Qian
Fudan University
4 shared publications
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1073-1082
Teaching Audio-Language Models to Reason over Time
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1073-1082
Open AccessTeaching Audio-Language Models to Reason over Time
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1547-1552
Efficient Music Denoising with Channel Attention and Multi-Scale Sequence Encoding
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1547-1552
Open AccessEfficient Music Denoising with Channel Attention and Multi-Scale Sequence Encoding
- Open Access
- 16 September 2025
- Published by Scilight Press Pty Ltd in Transactions on Artificial Intelligence
- Vol. 1  (1) , 199-211
EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with Musical Feature Templates
The EMelodyGen system mainly focuses on melody generation in ABC notation controlled by emotional conditions. To overcome the scarcity of emotional labeled sheet music, we utilize statistical correlations derived from small-scale symbolic music datasets with emotion labels and music psychology conclusions to guide subsequent feature extraction, emotional control and automatic annotation. We then automatically annotate a large, well-structured sheet music collection with rough emotional labels, convert the annotated dataset into ABC notation format, and apply data augmentation to address label imbalance, resulting in the creation of a dataset named Rough4Q. We demonstrate that our system backbone pre-trained on Rough4Q can achieve up to 99% music21 parsing rate. Our emotional control parameters, categorized into directly modifiable, embedding, dual-stage, and guidance features, can be selected and assembled to design customized emotional control templates that can lead to a 91% alignment in emotional expression in blind listening tests. Ablation studies further validate the impact of these control conditions on emotional accuracy.
- 16 September 2025
- Published by Scilight Press Pty Ltd in Transactions on Artificial Intelligence
- Vol. 1  (1) , 199-211
Open AccessEMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with Musical Feature Templates
The EMelodyGen system mainly focuses on melody generation in ABC notation controlled by emotional conditions. To overcome the scarcity of emotional labeled sheet music, we utilize statistical correlations derived from small-scale symbolic music datasets with emotion labels and music psychology conclusions to guide subsequent feature extraction, emotional control and automatic annotation. We then automatically annotate a large, well-structured sheet music collection with rough emotional labels, convert the annotated dataset into ABC notation format, and apply data augmentation to address label imbalance, resulting in the creation of a dataset named Rough4Q. We demonstrate that our system backbone pre-trained on Rough4Q can achieve up to 99% music21 parsing rate. Our emotional control parameters, categorized into directly modifiable, embedding, dual-stage, and guidance features, can be selected and assembled to design customized emotional control templates that can lead to a 91% alignment in emotional expression in blind listening tests. Ablation studies further validate the impact of these control conditions on emotional accuracy.
- 23 July 2025
- Published by Springer Nature
- p. 13-23
Online Joint Beat and Downbeat Tracking with Time Series Forecasting Model
- 23 July 2025
- Published by Springer Nature
- p. 13-23
Online Joint Beat and Downbeat Tracking with Time Series Forecasting Model
- 23 July 2025
- Published by Springer Nature
- p. 1-12
Meta-Learning for Domain Generalization in Anomalous Sound Detection
- 23 July 2025
- Published by Springer Nature
- p. 1-12
Meta-Learning for Domain Generalization in Anomalous Sound Detection
- 23 July 2025
- Published by Springer Nature
- p. 97-109
Semi-supervised Self-learning Enhanced Music Emotion Recognition
- 23 July 2025
- Published by Springer Nature
- p. 97-109
Semi-supervised Self-learning Enhanced Music Emotion Recognition
- 23 July 2025
- Published by Springer Nature
- p. 83-95
Effective Denoising in Music-Present Pubs with Efficient Channel Attention
- 23 July 2025
- Published by Springer Nature
- p. 83-95
Effective Denoising in Music-Present Pubs with Efficient Channel Attention
- Open Access
- 5 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 82302-82311
Dialogue-to-Video Retrieval via Multi-Grained Attention Network
Dialogue-to-video retrieval is an interesting while challenging task, which exploits an AI agent to retrieve the video that matches and aligns with the conversational context between users. In particular, given a history of dialogue exchanges, the agent is expected to identify the most fitting video content that complements the ongoing conversation. The computational complexity posed by the processing of videos within deep neural networks encourages us to adapt CLIP, a cutting-edge large multi-modal models (LLMs), into the dialogue-video domain. On this basis, we propose a multi-grained attention network (MGAT), integrating query-scoring, dual-softmax and query-bank normalization techniques. We design a multi-grained attention module to optimize the inadequate modeling of conversation semantics in existing pre-trained models, dynamically assign weights during conversation feature extraction, and introduce conversation context features in multimodal alignment. Most importantly, fine-grained similarity by per-round query-frame scoring and coarse-grained similarity by high-level semantics of all rounds of dialogues for each video are respectively calculated, which are further learned via multi-grained attention mechanism. This approach effectively transfers CLIP’s text-image multimodal knowledge into the dialogue-video retrieval system, alleviating the need for resource-intensive and costly fine-tuning dialogue-video procedures. Extensive experiments on multiple datasets demonstrate that our method outperforms state-of-the-art approaches.
- 5 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 82302-82311
Open AccessDialogue-to-Video Retrieval via Multi-Grained Attention Network
Dialogue-to-video retrieval is an interesting while challenging task, which exploits an AI agent to retrieve the video that matches and aligns with the conversational context between users. In particular, given a history of dialogue exchanges, the agent is expected to identify the most fitting video content that complements the ongoing conversation. The computational complexity posed by the processing of videos within deep neural networks encourages us to adapt CLIP, a cutting-edge large multi-modal models (LLMs), into the dialogue-video domain. On this basis, we propose a multi-grained attention network (MGAT), integrating query-scoring, dual-softmax and query-bank normalization techniques. We design a multi-grained attention module to optimize the inadequate modeling of conversation semantics in existing pre-trained models, dynamically assign weights during conversation feature extraction, and introduce conversation context features in multimodal alignment. Most importantly, fine-grained similarity by per-round query-frame scoring and coarse-grained similarity by high-level semantics of all rounds of dialogues for each video are respectively calculated, which are further learned via multi-grained attention mechanism. This approach effectively transfers CLIP’s text-image multimodal knowledge into the dialogue-video retrieval system, alleviating the need for resource-intensive and costly fine-tuning dialogue-video procedures. Extensive experiments on multiple datasets demonstrate that our method outperforms state-of-the-art approaches.
- Top Cited PapersOpen Access
- 24 March 2025
- Published by Ubiquity Press, Ltd. in Transactions of the International Society for Music Information Retrieval
- Vol. 8  (1) , 22-38
CCMusic: An Open and Diverse Database for Chinese Music Information Retrieval Research
Data are crucial in various computer‑related fields, including music information retrieval (MIR), an interdisciplinary area bridging computer science and music. This paper introduces CCMusic, an open and diverse database comprising multiple datasets specifically designed for tasks related to Chinese music, highlighting our focus on this culturally rich domain. The database integrates both published and unpublished datasets, with steps taken such as data cleaning, label refinement, and data structure unification to ensure data consistency and create ready‑to‑use versions. We conduct benchmark evaluations for all datasets using a unified evaluation framework developed specifically for this purpose. This publicly available framework supports both classification and detection tasks, ensuring standardized and reproducible results across all datasets. The database is hosted on HuggingFace and ModelScope, two open and multifunctional data and model hosting platforms, ensuring ease of accessibility and usability.
- 24 March 2025
- Published by Ubiquity Press, Ltd. in Transactions of the International Society for Music Information Retrieval
- Vol. 8  (1) , 22-38
Top Cited PapersOpen AccessCCMusic: An Open and Diverse Database for Chinese Music Information Retrieval Research
Data are crucial in various computer‑related fields, including music information retrieval (MIR), an interdisciplinary area bridging computer science and music. This paper introduces CCMusic, an open and diverse database comprising multiple datasets specifically designed for tasks related to Chinese music, highlighting our focus on this culturally rich domain. The database integrates both published and unpublished datasets, with steps taken such as data cleaning, label refinement, and data structure unification to ensure data consistency and create ready‑to‑use versions. We conduct benchmark evaluations for all datasets using a unified evaluation framework developed specifically for this purpose. This publicly available framework supports both classification and detection tasks, ensuring standardized and reproducible results across all datasets. The database is hosted on HuggingFace and ModelScope, two open and multifunctional data and model hosting platforms, ensuring ease of accessibility and usability.
- Open Access
- 28 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 39753-39764
Adversarial Contrastive Autoencoder With Shared Attention for Audio-Visual Correlation Learning
Cross-modal audio-visual correlation learning has been an active research topic, which aims to embed audio and visual feature sequences into a common subspace where their correlation is maximized. The challenge of audio-visual correlation learning lies in two major aspects: i) audio and visual feature sequences respectively contain different patterns belonging to different feature spaces, and ii) semantic mismatch between audio and visual sequences inevitably happens during cross-modal matching. Most existing methods only take the first aspect into account, therefore facing the difficulty in distinguishing matched and mismatched semantic correlations between audio and visual sequences. In this work, an adversarial contrastive autoencoder with a shared attention network (ACASA) is proposed for correlation learning in audio-visual retrieval. In particular, the proposed shared attention mechanism is parameterized, in which local salient information is enhanced to contribute to the final feature representation. Simultaneously, adversarial contrastive learning is exploited to maximize semantic feature consistency and improve the ability to distinguish matched and mismatched samples. Both inter-modal and intra-modal semantic information are utilized to supervise the model to learn more discriminative feature representation. Extensive experiments on the VEGAS and AVE datasets demonstrate that the proposed ACASA method outperforms state-of-the-art approaches in cross-modal audio-visual retrieval.
- 28 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 39753-39764
Open AccessAdversarial Contrastive Autoencoder With Shared Attention for Audio-Visual Correlation Learning
Cross-modal audio-visual correlation learning has been an active research topic, which aims to embed audio and visual feature sequences into a common subspace where their correlation is maximized. The challenge of audio-visual correlation learning lies in two major aspects: i) audio and visual feature sequences respectively contain different patterns belonging to different feature spaces, and ii) semantic mismatch between audio and visual sequences inevitably happens during cross-modal matching. Most existing methods only take the first aspect into account, therefore facing the difficulty in distinguishing matched and mismatched semantic correlations between audio and visual sequences. In this work, an adversarial contrastive autoencoder with a shared attention network (ACASA) is proposed for correlation learning in audio-visual retrieval. In particular, the proposed shared attention mechanism is parameterized, in which local salient information is enhanced to contribute to the final feature representation. Simultaneously, adversarial contrastive learning is exploited to maximize semantic feature consistency and improve the ability to distinguish matched and mismatched samples. Both inter-modal and intra-modal semantic information are utilized to supervise the model to learn more discriminative feature representation. Extensive experiments on the VEGAS and AVE datasets demonstrate that the proposed ACASA method outperforms state-of-the-art approaches in cross-modal audio-visual retrieval.