Aerial object detection plays a crucial role in numerous applications. However, most existing methods focus on detecting predefined object categories, limiting their applicability in real-world open scenarios. In this article, we extend aerial object detection to open scenarios through image–text collaboration and prop...
Guo-Ting Wei, Xia Yuan, Yu Liu et al.· IEEE Transactions on Geoscie...· 0 citations
ManiUnit is introduced, a manipulation skill dataset and benchmark built from 50 BEHAVIOR-1K activities that pairs each segment with an explicit subtask instruction; measures sensitivity to perturbations of the robot's starting base position or joint configuration; and defines local success conditions so that each skil...
Guo-Ting Wei, Da-Wei Yan, Xia Yuan et al.· 0 citations
Task-driven image restoration aims to improve both image quality and downstream task performance. However, existing methods predominantly focus on single degradation type and struggle to handle the diverse degradations encountered in real-world scenarios. Different degradations impose distinct restoration demands, and...
Yan-Jie Tu, Qing-Sen Yan, Axi Niu et al.· 0 citations
EGM-Det is proposed, an entropy-guided multimodal adaptive fusion framework for RGB-IR object detection that outperforms prior approaches by more than 10 percentage points on VEDAI and introduces cross-modal distillation to regularize the learned fusion gates and reduce fusion degradation.
Cun-Zheng Fan, Da-Wei Yan, Guan-Lin Wang et al.· 1 citation
Post-training quantization reduces the deployment cost of vision-language models (VLMs), but preserving multimodal capabilities at low bit widths remains challenging. Existing methods rely on modality- or token-level gradient statistics, which are susceptible to cross-sample variations in visual-to-textual token ratios...
Vision language models have achieved strong performance across a wide range of multimodal applications, yet their substantial computational and memory costs hinder efficient deployment. Visual token pruning and post-training quantization reduce inference overhead along two complementary dimensions, namely sequence leng...
This paper revisit VLM inference and presents a new efficient guidance scheme that complements similarity-based guidance, and proposes Cross Modal Residual (CMR), a training-free visual token compression method that combines CMR, text-attention relevance, and residual-space diversity to retain task-relevant and complem...
Congyang Ou, Rui-Ke Song, Yang Zhou et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.