2 papers
cs.CV2026
LDDR: Linear-DPP Dynamic-Resolution Frame Sampling for Video MLLMs
Jingfeng Chen, Jiawen Qian, Wendi Deng +5
Multimodal large language models, when used for long video understanding, require selecting an informative frame set from massive and redundant candidates. Limited by the model's v…
cs.AI2024
MCSFF: Multi-modal Consistency and Specificity Fusion Framework for Entity Alignment
Wei Ai, Wen Deng, Hongyi Chen +3
Multi-modal entity alignment (MMEA) is essential for enhancing knowledge graphs and improving information retrieval and question-answering systems. Existing methods often focus on…