Hyperspectral Calibration Detection: A Novel Concept For Change Detection With Unsupervised Incremental Safe Pseudo-Labeling Implementation [0.03%]
超光谱校准检测：一种基于无监督增量安全伪标签实现的变化检测新概念
Chia-Hsiang Lin,Shih-Min Hsu,Ching-Yun Liang et al.
Chia-Hsiang Lin et al.
Hyperspectral change detection (HCD) has found numerous key applications, such as land cover monitoring. The majority of benchmark HCD algorithms are semi-supervised methods, and some of them can even achieve very low sample labeling rates....
Information-Bottleneck Guided Hybrid Neural Architecture Search for Temporal Action Detection in Untrimmed Videos [0.03%]
基于信息瓶颈的混合神经架构搜索方法在未修剪视频中进行时序动作检测任务
Yi Tang,Mansen Chen,Lepeng Chen et al.
Yi Tang et al.
Temporal Action Detection (TAD) in untrimmed videos requires effective spatial feature extraction for precise action classification and temporal feature modeling for accurate boundary localization. To achieve effective spatio-temporal featu...
SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection [0.03%]
SPEGNet：协同感知引导网络在伪装目标检测中的应用
Baber Jan,Saeed Anwar,Aiman H El-Maleh et al.
Baber Jan et al.
Camouflaged object detection segments objects with intrinsic similarity and edge disruption. Current detection methods rely on accumulated complex components. Each approach adds components such as boundary modules, attention mechanisms, and...
BRAINHash: Brain-inspired Region-Aligned Interaction Network for unsupervised cross-modal hashing [0.03%]
受脑启发的区域对齐交互网络无监督跨模性哈希算法(BRAINHash)
Hao Fu,Guanghua Gu,Yunchao Wei et al.
Hao Fu et al.
Unsupervised cross-modal hashing (UCMH) has attracted considerable attention owing to its minimal reliance on manual annotations and low retrieval latency. However, existing UCMH methods based on contrastive learning frameworks combined wit...
Qian Wang,Qun Li,Xue Li et al.
Qian Wang et al.
As a distributed machine learning paradigm, federated learning enables collaborative training among multiple clients while preserving data privacy. However, in practical applications, it faces the challenge of domain shift caused by data he...
Shizhe Hu,Jiahao Fan,Yucong Wu et al.
Shizhe Hu et al.
Multi-modal clustering aims to integrate complementary information from different modalities to uncover latent consistent structures and improve clustering performance. However, existing methods mainly rely on predictive (result) uncertaint...
STAFuse: Scene-Text Aggregation Guided Composite Degradation-Robust Infrared and Visible Image Fusion [0.03%]
基于场景文本聚合引导的复合退化鲁棒型红外与可见光图像融合方法(STAFuse)
Ting Lv,Hong Jiang,Yu Liu
Ting Lv
Infrared and visible image fusion aims to integrate complementary information from source images to generate high-quality fusion images that serve downstream tasks. However, the differentiated representation of image scene content, the unpr...
Self-Chained Dynamic Context Perception to Tracking by Natural Language Specification [0.03%]
自洽动态上下文感知的自然语言指令跟踪方法
Ding Ma,Zexu Zhang,Xiangqian Wu
Ding Ma
Vision-language cross-modal learning has significantly improved Tracking by Natural Language specification (TNL). Most existing TNL methods follow a Siamese-like matching paradigm, where visual search-region features and language-query feat...
Uncertainty-Guided Spatiotemporal Consistency Fusion Network for Infrared-Visible Video Fusion under Extremely Low-Light Conditions [0.03%]
极端低光条件下不确定性引导的红外视频时空一致性融合网络
Cheng Zhao,Tianyun Song,Zhiliang Wu et al.
Cheng Zhao et al.
Infrared-visible video fusion under extremely low-light conditions is critically important yet remains underexplored, largely due to the scarcity of high-quality datasets and challenges posed by spatiotemporal uncertainty and modality bias....
Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving [0.03%]
扩展大型视觉语言模型以应对自主驾驶中的多种互动任务
Zongchuang Zhao,Haoyu Fu,Dingkang Liang et al.
Zongchuang Zhao et al.
Large Vision-Language Models (LVLMs) have significantly advanced image understanding. Their comprehension and reasoning capabilities enable promising applications in autonomous driving scenarios. However, existing research typically focuses...