The reasoning capabilities of vision-language models (VLMs) can be limited by incomplete or inaccurate visual observations in the general domain. In unmanned aerial vehicle (UAV) scenes, small targets, subtle attributes, and changing viewpoints further complicate perception and understanding. Therefore, we introduce Dr...
Jia-He Wu, Bing Cao, Xing-Yue Guo et al.· 0 citations
Generative inbetweening aims to synthesize temporally coherent intermediate frames between a start frame and a target frame. Although pretrained image-to-video diffusion models provide strong priors for large-motion inbetweening, they are not explicitly designed to reach a specified target frame. They may therefore gen...
Zhi-Yu Xu, Wei Shang, Yu-Shen Xu et al.· 0 citations
The results support order-aware progressive consolidation followed by reciprocal transfer as a viable mechanism for detector-society evolution as a viable mechanism for detector-society evolution.
Wei-Hao Li, Yun-Qi Zhu, Zhi-He Fan et al.· arXiv.org· 0 citations
UAV vision-language navigation (UAV-VLN) is commonly evaluated as goal reaching, but inspection-oriented deployment requires the agent to stop within a valid inspection region and avoid falsely confirming visually or semantically similar distractors. This requirement exposes a key weakness in existing coarse-to-fine UA...
Senhao Wang, Yi-Ming Sun, Jia-Xuan He et al.· 0 citations
The proposed UniDiffFusion framework is trained in a progressive manner to decouple fusion learning, degradation-aware restoration, and application-specific adaptation, thereby reducing interference among heterogeneous objectives.
Xing-Xin Xu, Si-Qi Zhao, Xin Li et al.· 0 citations
AIR-Fusion is proposed, a parameter-efficient adaptation of a frozen, restoration-capable latent diffusion backbone for degraded IVIF without full fine-tuning, transferring restoration priors for robust fusion.
Bing Cao, Qiang Zhang, Xing-Xin Xu et al.· Proceedings of the Thirty-Fi...· 0 citations
This work proposes HSO-GAT, a topology-adaptive hyperbolic graph attention network that unifies geometric adaptation and message propagation and establishes the monotonic sensitivity of edge-level HSO to degree imbalance and analyzes the validity and radial scaling properties of node-adaptive hyperbolic mappings.
Hai-Fang Cao, Bo-An Tao, Xi-Yuan Gao et al.· 0 citations
This work proposes Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion (SAGE), a unified framework integrating frequency equalization, hierarchical alignment, and subband fusion.
Ti-Ming Li, Yi-Ming Sun, Bo-An Tao et al.· 0 citations
This work proposes COllabOrative Knowledge Extraction and integRation (COOKER) method for GDIL to mine inter-domain relationships and uncover the potential of domain-agnostic representations, which significantly outperforms existing baselines.
Jialu Li, Yu Wang, Wanyu Lin et al.· Proceedings of the 32nd ACM...· 0 citations
This work revisits multi-modal fusion from the perspective of socialized learning and proposes adapter to DINOv3 (A2DINOv3), a multi-expert collaboration framework with a Socialized Collaboration Protocol (SCP), where RGB and infrared branches are modeled as heterogeneous experts that independently preserve their speci...
Jiekang Feng, Zhi-He Fan, Yun-Qi Zhu et al.· 0 citations
Graph Domain Incremental Learning (GDIL) aims to acquire knowledge from a continuous stream of graph domains while mitigating catastrophic forgetting. While parameter-isolation methods leveraging graph parameter-efficient adaptation show promise, prompt-based techniques struggle to adapt to GDIL, and low-rank adaptatio...
Jialu Li, Yu Wang, Wanyu Lin et al.· Proceedings of the 32nd ACM...· 0 citations
This work proposes Socialized Division and Collaboration as a reformulation of continual learning that decomposes session learning across specialized models in response to optimization conflicts, while enabling coordinated collaboration and introduces an energy-based session-model compatibility criterion grounded in He...
Xinjie Yao, Zhi-He Fan, Yun-Qi Zhu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.