Image and Vision Computing
Publisher: Elsevier · ISSN 0262-8856 · 49 articles
- AFAC: An adaptive frequency-aware context fusion network for visible-infrared object detection
- Disentangling the link between image statistics and human perception
- DBMamba: A dual-branch spectral–spatial state space network for accurate hyperspectral image classification
- Restoration of low-resolution seated buttock pressure images with mechanism-matched processing
- Box2Pix-Det: From 3D bounding boxes to pixel-level semantics for indoor 3D object detection
- Editorial Board
- Dual-adaptive cost aggregation for robust stereo matching
- Trustworthy heuristic graph learning for image-text matching
- CME-DETR: Context-aware and multi-scale enhanced DETR for UAV small object detection
- Dual-prior Graph Neural Network: Illuminating and sharpening multispectral object detection
- IPUEC-IAD: A framework for industrial anomaly detection with improved performance under efficiency constraints
- Caps-ViT: A synthetic-free capsule vision Transformer for reconstruction based anomaly detection and localization
- IVCP: Instruction-Guided Video Context Prompting for video action recognition
- Weakly-supervised camouflaged object detection with enhanced boundary perception
- ZID-net: Zero-inference diffusion prior decoupling network for single image dehazing
- FusePrompt: A prompt fusion framework for vision–language adaptation
- A style-preserving cross-lingual scene text translation system with tri-conditional diffusion
- A cross-guided and dynamic adaptive convolutional network for ancient city wall defect detection
- An infrared polarization image fusion method based on the fusion structure of convolutional neural network and transformer
- Deepfake image detection via edge and spatial refined attentive features with adaptive fuzzy interaction fusion
- MESF-DETR: Mamba-enhanced spatial-frequency fusion for small object detection in UAV imagery
- FSTA-Gait: Factorized Spatio-Temporal Attention Network for robust gait recognition
- Uncertainty-guided semantic feature adaptation for non-exemplar online class-incremental learning on long-tailed data
- Heterogeneity Alleviation and Detail Enhancement Network for RGB-D Video Salient Object Detection
- YOLO-LGA: Enhance YOLO with local to global attention for multi-class insect pest detection
- Point-cloud-aware 3D Gaussian Splatting initialization for novel view synthesis
- STM-WVideoClip: Mamba and vision-language learning for traffic anomaly detection
- Online global HD map updating and construction based on road geometry
- ViBERT-X: Bias-resilient dual-path cross-attentional framework for robust hateful meme detection
- Exploring the risks of generative AI misuse via ambiguous prompts: Bypassing safety filters in Text-to-Image/Video models