Parameter-Efficient Fine-Tuning (PEFT) has become a promising paradigm for Remote Sensing Image-Text Retrieval (RSITR), enabling the adaptation of large pre-trained models with a small number of trainable parameters. However, remote sensing image-text pairs exhibit heterogeneous structures: compositional caption repres...
Meng-Ru Ma, Shuo Liang, Wen-Ping Ma et al.· Proceedings of the 34th ACM...· 0 citations
Due to the homogeneous backgrounds and cluttered layouts of remote sensing (RS) imagery, fine-grained local entities are indispensable for preventing cross-modal semantic mismatch. However, existing parameter-efficient fine-tuning (PEFT) methods based on contrastive language-image pretraining (CLIP) encapsulate scenes...
Meng-Ru Ma, Jia-Xu Guo, Wen-Ping Ma et al.· IEEE Transactions on Geoscie...· 0 citations
Reasoning segmentation converts an implicit linguistic conclusion into a precise mask, requiring both semantic identification and spatial grounding. Existing MLLM-segmenter interfaces either use a special trigger or compress both signals into one context, although they receive different supervision and fail differently...
Lin-Nan Zhao, Xu Liu, Ling-Ling Li et al.· 0 citations
BRL is proposed, a novel adapter-based PEFT framework that facilitates hierarchical, bidirectional information flow within both token-mixing and channel-mixing layers of frozen foundation models, achieving state-of-the-art performance while requiring less than 0.5% backbone parameter updates.
Xiaoqiang Lu, Li-Cheng Jiao, Ling-Ling Li et al.· 0 citations
Multi-task visual grounding requires models to jointly understand linguistic semantics and perform accurate visual localization and segmentation. Despite the success of multimodal large language models, effectively adapting them to multiple grounding objectives remains challenging. Existing methods commonly enforce tas...
Xiaoqiang Lu, Li-Cheng Jiao, Long Sun et al.· arXiv.org· 1 citation
To relieve the problems of the lack of semantic alignment in the geometric representation space and insufficient modality-specific instruction calibration in infrared-visible image fusion (IVIF), we first propose a dynamic instruction-aware geometric representation (DIGR) for IVIF, which achieves semantic alignment bet...
Meng-Ru Ma, Yong-Zhe Wang, Wen-Ping Ma et al.· IEEE Transactions on Geoscie...· 0 citations
A multi-source collaborative training and class-aware fusion framework for Sim2Real 3D detection that indicates that a stable, interpretable collaboration among data sources is more valuable than unconstrained aggregation of model outputs.
Recently, the zero-shot image captioning (zero-shot IC) method based on pre-trained visual language models (VLMs) and large language models (LLMs) has made significant progress. However, how to adapt it to the zero-shot video captioning (zero-shot VC) scenario (without video-text paired supervision) has not been well e...
Qianyue Bao, Fang Liu, Licheng Jiao et al.· IEEE Transactions on Image P...· 0 citations
A five-dimensional analytical framework is introduced that clarifies how EI transforms isolated search trajectories into cumulative scientific insight, and identifies critical bottlenecks regarding evaluation, process traceability, and shared infrastructure.
Chao Wang, Lingling Li, Fang Liu et al.· 0 citations