Journal & Article

Artificial Intelligence

I/F
# Journal I/F

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE

LFSRM: Few-Shot Diagram-Sentence Matching via Local-Feedback Self-Regulating Memory Learning Physics-Informed Noise Models from Dark Frames for Low-Light Raw Image Denoising Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach Armor: Shielding Unlearnable Examples Against Data Augmentation Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration Detection of Model-Based Planted Pseudo-Cliques in Random Dot Product Graphs by the Adjacency Spectral Embedding and the Graph Encoder Embedding Toward Accurate Procedure Planning in Instructional Videos: Visual State Generation Helps Task-Selective Diffusion Unified Granularity Controller for Interactive Segmentation Hypergraph Foundation Model $\ell _{0}$ℓ0-Regularized Sparse Coding-Based Interpretable Network for Multi-Modal Image Fusion Temporal Stereo Matching From Event Cameras via Joint Learning With Stereoscopic Flow Reinforcement Learning-Based Sequential Parameter Tuning for Image Signal Processing Unveiling Fine-Grained Deceptive Patterns in Multimodal Fake News: An Explainable Neuro-Symbolic Framework With LVLMs A Theoretical Perspective on Streaming Noisy Data With Distribution Shift Breaking Barriers, Localizing Saliency: A Large-Scale Benchmark and Baseline for Condition-Constrained Salient Object Detection Recent Advances in Discrete Speech Tokens: A Review HGNN Shield: Defending Hypergraph Neural Networks Against High-Order Structure Attack Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation Augmenting Iterative Trajectory for Bilevel Optimization: Methodology, Analysis and Extensions Developing Evolving Adaptability in Biological Intelligence: A Novel Biologically-Inspired Continual Learning Model for Video Saliency Prediction A Unified Experience Replay Framework for Spiking Deep Reinforcement Learning Evolutionary Dimension-Specific Feature Selection for Multi-Dimensional Classification Toward Deeper Emotional Reflection: Crafting Affective Image Filters With Generative Priors VPT-NSP2++: Importance-Aware Visual Prompt Tuning in Null Space for Continual Learning Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers DSwinIR: Rethinking Window-Based Attention for Image Restoration Handwritten Text Recognition: A Survey RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation Condition-Guided Diffusion for Multi-Modal Pedestrian Trajectory Prediction Incorporating Intention and Interaction Priors Slack Federated Adversarial Training CompleMatch: Boosting Time-Series Semi-Supervised Classification With Temporal-Frequency Complementarity MESA: Effective Matching Redundancy Reduction by Semantic Area Segmentation MoEGAD: A Mixture-of-Experts Framework With Pseudo-Anomaly Generation for Graph-Level Anomaly Detection Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimation A Novel Approach to GNN Explainability: Distilling Knowledge With Inter-Layer Alignment Boosting Multi-Modal Large Language Model With Enhanced Visual Features Unsupervised Representation Learning From Sparse Transformation Analysis Data-Driven Bidirectional Spatial-Adaptive Network for Weakly Supervised Object Detection in Remote Sensing Images Bi-C2R: Bidirectional Continual Compatible Representation for Re-Indexing Free Lifelong Person Re-Identification Robust Semi-Supervised Feature Selection With Multi-Granularity Zentropy Modeling DirMixE: Harnessing Test Agnostic Long-Tail Recognition With Hierarchical Label Vartiations Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussians DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency Noisy Correspondence Rectification in Multimodal Clustering Space for Cross-Modal Matching HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving Breaking the Multi-Enhancement Bottleneck: Domain-Consistent Quality Enhancement for Compressed Images Jo-SNC: Combating Noisy Labels Through Fostering Self- and Neighbor-Consistency Proactive Bot Detection Based on Structural Information Principles Toward Understanding Generalization and Stability Gaps Between Centralized and Decentralized Federated Learning Spike Camera Optical Flow Estimation Based on Continuous Spike Streams