中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共36条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
Enhanced Dual-Pattern Matching With Vision-Language Representation for Out-of-Distribution Detection 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2025, 卷号: 47, 期号: 11, 页码: 9673-9687
作者:  Xiang, Xiang;  Xu, Zhuo;  Zhang, Zihan;  Zeng, Zhigang;  Chen, Xilin
收藏  |  浏览/下载：13/0  |  提交时间：2025/12/03
Visualization  Adaptation models  Training  Data models  Computational modeling  Feature extraction  Pattern matching  Tuning  Robustness  Data mining  OOD detection  vision-language models  
Bi-Modality Individual-Aware Prompt Tuning for Visual-Language Model 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2025, 卷号: 47, 期号: 8, 页码: 6352-6368
作者:  Yao, Hantao;  Zhang, Rui;  Lyu, Huaihai;  Zhang, Yongdong;  Xu, Changsheng
收藏  |  浏览/下载：10/0  |  提交时间：2025/12/03
Tuning  Visualization  Training  Adaptation models  Hands  Feature extraction  Data models  Artificial intelligence  Transformers  Data mining  Prompt tuning  individual-aware prompt tuning  bi-modality prompt tuning  visual-language model  
A Visual-Cortex-Mimetic Tiny Neuromorphic Vision Processor Based on Reconfigurable Cortical Neuron Unit 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2025, 卷号: 72, 期号: 7, 页码: 943-947
作者:  Chen, Mingju;  He, Junxian;  Wang, Haibing;  Wang, Tengxiao;  Gao, Haoran;  Liu, Liyuan;  Wang, Ying;  Shi, Cong
收藏  |  浏览/下载：8/0  |  提交时间：2025/12/03
Neurons  Neuromorphics  Visualization  Feature extraction  Data models  Image edge detection  Brain modeling  Retina  Costs  Synapses  Neuromorphic processor  spiking neural network  visual cortex  on-chip learning  STDP  
Prompting Video-Language Foundation Models With Domain-Specific Fine-Grained Heuristics for Video Question Answering 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2025, 卷号: 35, 期号: 2, 页码: 1615-1630
作者:  Yu, Ting;  Fu, Kunhao;  Wang, Shuhui;  Huang, Qingming;  Yu, Jun
收藏  |  浏览/下载：42/0  |  提交时间：2025/06/25
Cognition  Computational modeling  Visualization  Context modeling  Data models  Adaptation models  Accuracy  Question answering (information retrieval)  Transformers  Feature extraction  Video question answering  discriminative unimodal comprehension  cross-modal interaction  domain-specific heuristics  video-language foundation models  entity-action relationships  context-aware reasoning  
Consistency Conditioned Memory Augmented Dynamic Diagnosis Model for Medical Visual Question Answering 期刊论文
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2025, 卷号: 29, 期号: 2, 页码: 1357-1370
作者:  Yu, Ting;  Ge, Binhui;  Wang, Shuhui;  Yang, Yan;  Huang, Qingming;  Yu, Jun
收藏  |  浏览/下载：43/0  |  提交时间：2025/06/25
Medical diagnostic imaging  Visualization  Question answering (information retrieval)  Feature extraction  Semantics  Engines  Cognition  Accuracy  Predictive models  Electronic mail  Clinical decisions  consistency  dynamic memory diagnosis  dynamic reasoning  medical assistance  medical visual question answering  
Screen Content-Aware Video Coding Through Non-Local Model Embedded With Intra-Inter In-Loop Filtering 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2025, 卷号: 35, 期号: 2, 页码: 1870-1883
作者:  Li, Mingxuan;  Ji, Wen
收藏  |  浏览/下载：28/0  |  提交时间：2025/06/25
Encoding  Feature extraction  Computational modeling  Adaptation models  Visualization  Nonlinear distortion  Information filters  Deep learning  Standards  Image color analysis  Video coding  in-loop filtering  screen content  deep learning  high-efficiency video coding (HEVC)  
LECLIP: Boosting Zero-Shot Anomaly Detection With Local Enhanced CLIP 期刊论文
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2025, 卷号: 74, 页码: 11
作者:  Liu, Yuyao;  Li, Qingyong;  Wang, Zhehong;  Kato, Jien;  Zhang, Jie;  Wang, Wen
收藏  |  浏览/下载：9/0  |  提交时间：2025/12/03
Visualization  Anomaly detection  Training  Accuracy  Image representation  Feature extraction  Biomedical imaging  Semantics  Attention mechanisms  Artificial intelligence  Echo-attention (EA)  local alignment (LA) module  local enhanced CLIP (LECLIP)  zero-shot anomaly detection (ZSAD)  
A Joint Visual Compression and Perception Framework for Neuromorphic Spiking Camera 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2025, 卷号: 34, 页码: 4343-4356
作者:  Feng, Kexiang;  Jia, Chuanmin;  Ma, Siwei;  Gao, Wen
收藏  |  浏览/下载：8/0  |  提交时间：2025/12/03
Image coding  Cameras  Feature extraction  Encoding  Visualization  Distortion  Decoding  Binary sequences  Video compression  Vectors  Spike compression  visual intelligence  end-to-end spike coding  
Dual-Alignment CLIP: Task-Specific Alignment of Text and Visual Features for Few-Shot Remote Sensing Scene Classification 期刊论文
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2025, 卷号: 18, 页码: 19260-19272
作者:  Deng, Dongmei;  Yao, Ping
收藏  |  浏览/下载：10/0  |  提交时间：2025/12/03
Remote sensing  Scene classification  Visualization  Training  Manuals  Few shot learning  Feature extraction  Adaptation models  Training data  Streaming media  Contrastive vision-language pretraining (CLIP)  few-shot learning (FSL)  image classification  remote sensing  
Boost Tracking by Natural Language With Prompt-Guided Grounding 期刊论文
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 页码: 13
作者:  Li, Hengyou;  Liu, Xinyan;  Li, Guorong;  Wang, Shuhui;  Qing, Laiyun;  Huang, Qingming
收藏  |  浏览/下载：22/0  |  提交时间：2025/06/25
Target tracking  Grounding  Switches  Visualization  Feature extraction  Computational modeling  Adaptation models  Location awareness  Linguistics  Memory management  Vision-language tracking  prompt learning  inverse tracking