A collaborative optimization framework for efficient long-sequence Audio-Visual understanding
Open Access
- 9 April 2026
- journal article
- Published by Elsevier in Expert Systems with Applications
- Vol. 323
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Hainan Province (625RC794)
- Education Department of Hainan Province (Hnky2025ZD-17)
This publication has 26 references indexed in Scilit:
- Enhanced recommendation with hypergraph mixture of expertsExpert Systems with Applications, 2025
- Mosaic: Composite projection pruning for resource-efficient LLMsFuture Generation Computer Systems, 2025
- Guiding Audio-Visual Question Answering with Collective Question ReasoningInternational Journal of Computer Vision, 2025
- Towards enhanced LLM pretraining: Dynamic checkpoint merging via generation qualityInformation Fusion, 2025
- KFF: K-feature fusion token merging for vision transformerExpert Systems with Applications, 2025
- Efficient token pruning in Vision Transformers using an attention-based Multilayer NetworkExpert Systems with Applications, 2025
- CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question AnsweringInternational Journal of Computer Vision, 2024
- Construction safety inspection with contrastive language-image pre-training (CLIP) image captioning and attentionAutomation in Construction, 2024
- Audio-visual event localization with dual temporal-aware scene understanding and image-text knowledge bridgingComplex & Intelligent Systems, 2024
- Leveraging Contrastive Language–Image Pre-Training and Bidirectional Cross-attention for Multimodal Keyword SpottingEngineering Applications of Artificial Intelligence, 2024