Conferences · eligible papers
IJCAI
2021–2025 確定版
2025 · 1,014 papers
このEditionに反映済みのmain full research papersのみ掲載しています。著者リンクは日本の大学への著者別所属根拠がある場合に限ります。
- Subgraph Information Bottleneck with Causal Dependency for Stable Molecular Relational Learning
日本大学: 関与なし(対象大学)
- Suit the Node Pair to the Case: A Multi-Scale Node Pair Grouping Strategy for Graph-MLP Distillation
日本大学: 関与なし(対象大学)
- SyncAnimation: A Real-Time End-to-End Framework for Audio-Driven Human Pose and Talking Head Animation
日本大学: 関与なし(対象大学)
- SyncGaussian: Stable 3D Gaussian-Based Talking Head Generation with Enhanced Lip Sync via Discriminative Speech Features
日本大学: 関与なし(対象大学)
- Synthesis of Communication Policies for Multi-Agent Systems Robust to Communication Restrictions
日本大学: 関与なし(対象大学)
- Synthesising Minimum Cost Dynamic Norms
日本大学: 関与なし(対象大学)
- T-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction
日本大学: 関与なし(対象大学)
- T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models
日本大学: 関与なし(対象大学)
- TCDM: A Temporal Correlation-Empowered Diffusion Model for Time Series Forecasting
日本大学: 関与なし(対象大学)
- TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification
日本大学: 関与なし(対象大学)
- TESTN: A Triad-Enhanced Spatio-Temporal Network for Multi-Temporal POI Relationship Inference
日本大学: 関与なし(対象大学)
- TOTF: Missing-Aware Encoders for Clustering on Multi-View Incomplete Attributed Graphs
日本大学: 関与なし(対象大学)
- TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts
日本大学: 関与なし(対象大学)
- TSTAI: A Time-varying Brain Effective Connectivity Network Construction Method Combining with Brain Active Information
日本大学: 関与なし(対象大学)
- Tackling Long-Tailed Data Challenges in Spiking Neural Networks via Heterogeneous Knowledge Distillation
日本大学: 関与なし(対象大学)
- Template-based Uncertainty Multimodal Fusion Network for RGBT Tracking
日本大学: 関与なし(対象大学)
- Template3D-AD: Point Cloud Template Matching Method Based on Center Points for 3D Anomaly Detection
日本大学: 関与なし(対象大学)
- Temporal Consistency Constrained Transferable Adversarial Attacks with Background Mixup for Action Recognition
日本大学: 関与なし(対象大学)
- Tensorial Multi-view Clustering with Deep Anchor Graph Projection
日本大学: 関与なし(対象大学)
- Test-Time Adaptation on Recommender System with Data-Centric Graph Transformation
日本大学: 関与なし(対象大学)
- TextMEF: Text-guided Prompt Learning for Multi-exposure Image Fusion
日本大学: 関与なし(対象大学)
- The Core of Approval-Based Committee Elections with Few Seats
日本大学: 関与なし(対象大学)
- The Devil is in Fine-tuning and Long-tailed Problems: A New Benchmark for Scene Text Detection
日本大学: 関与なし(対象大学)
- The First Theoretical Approximation Guarantees for the Non-Dominated Sorting Genetic Algorithm III (NSGA-III)
日本大学: 関与なし(対象大学)
- The Proportional Veto Principle for Approval Ballots
日本大学: 関与なし(対象大学)
- The Role of Video Generation in Enhancing Data-Limited Action Understanding
日本大学: 関与なし(対象大学)
- Theoretical Analysis of Evolutionary Algorithms with Quality Diversity for a Classical Path Planning Problem
日本大学: 関与なし(対象大学)
- Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization
日本大学: 関与なし(対象大学)
- Think Twice Before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation
日本大学: 関与なし(対象大学)
- Tight Runtime Guarantees From Understanding the Population Dynamics of the GSEMO Multi-Objective Evolutionary Algorithm
日本大学: 関与なし(対象大学)
- Time-Frequency Disentanglement Boosted Pre-Training: A Universal Spatio-Temporal Modeling Framework
日本大学: 関与なし(対象大学)
- Token-Level Accept or Reject: A Micro Alignment Approach for Large Language Models
日本大学: 関与なし(対象大学)
- Top-Down Guidance for Learning Object-Centric Representations
日本大学: 関与なし(対象大学)
- Top-I2P: Explore Open-Domain Image-to-Point Cloud Registration Using Topology Relationship
日本大学: 関与なし(対象大学)
- Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models
日本大学: 関与なし(対象大学)
- Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification
日本大学: 関与なし(対象大学)
- Towards Automatic Sampling of User Behaviors for Sequential Recommender Systems
日本大学: 関与なし(対象大学)
- Towards Debiased Generalized Category Discovery
日本大学: 関与なし(対象大学)
- Towards Equilibrium: An Instantaneous Probe-and-Rebalance Multimodal Learning Approach
日本大学: 関与なし(対象大学)
- Towards Fairness with Limited Demographics via Disentangled Learning
日本大学: 関与なし(対象大学)
- Towards Generalizable Neural Simulators: Addressing Distribution Shifts Induced by Environmental and Temporal Variations
日本大学: 関与なし(対象大学)
- Towards Improved Risk Bounds for Transductive Learning
日本大学: 関与なし(対象大学)
- Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach
日本大学: 関与なし(対象大学)
- Towards Recognizing Spatial-temporal Collaboration of EEG Phase Brain Networks for Emotion Understanding
日本大学: 関与なし(対象大学)
- Towards Region-Adaptive Feature Disentanglement and Enhancement for Small Object Detection
日本大学: 関与なし(対象大学)
- Towards Regularized Mixture of Predictions for Class-Imbalanced Semi-Supervised Facial Expression Recognition
日本大学: 関与なし(対象大学)
- Towards Robust Deterministic and Probabilistic Modeling for Predictive Learning
日本大学: 関与なし(対象大学)
- Towards Robust Incremental Learning Under Ambiguous Supervision
日本大学: 関与なし(対象大学)
- Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale Datasets for Responsible LLMs
日本大学: 関与なし(対象大学)
- Towards VLM-based Hybrid Explainable Prompt Enhancement for Zero-Shot Industrial Anomaly Detection
日本大学: 関与なし(対象大学)
- Towards a Unified View of Social Laws with Instantaneous Actions
日本大学: 関与なし(対象大学)
- Trace: Structural Riemannian Bridge Matching for Transferable Source Localization in Information Propagation
日本大学: 関与なし(対象大学)
- Training-free Fourier Phase Diffusion for Style Transfer
日本大学: 関与なし(対象大学)
- TrajCogn: Leveraging LLMs for Cognizing Movement Patterns and Travel Purposes from Trajectories
日本大学: 関与なし(対象大学)
- Trajectory-Dependent Generalization Bounds for Pairwise Learning with φ-mixing Samples
日本大学: 関与なし(対象大学)
- Transferable Relativistic Predictor: Mitigating Cross-Task Cold-Start Issue in NAS
日本大学: 関与なし(対象大学)
- Tree-of-AdEditor: Heuristic Tree Reasoning for Automated Video Advertisement Editing with Large Language Model
日本大学: 関与なし(対象大学)
- TreeKV: Smooth Key-Value Cache Compression with Tree Structures
日本大学: 関与なし(対象大学)
- TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning
日本大学: 関与なし(対象大学)
- Two-Stage Feature Generation with Transformer and Reinforcement Learning
日本大学: 関与なし(対象大学)
- Two-stage Risk Control with Application to Ranked Retrieval
日本大学: 関与なし(対象大学)
- UltraModel: A Modeling Paradigm for Industrial Objects
日本大学: 関与なし(対象大学)
- Uncertainty-guided Graph Contrastive Learning from a Unified Perspective
日本大学: 関与なし(対象大学)
- Underground Diagnosis in 3D GPR Data by Learning in CuCoRes Model Space
日本大学: 関与なし(対象大学)
- Understanding Matters: Semantic-Structural Determined Visual Relocalization for Large Scenes
日本大学: 関与なし(対象大学)
- Understanding Visual Detail Hallucinations of Large Vision-Language Models
日本大学: 関与なし(対象大学)
- UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block
日本大学: 関与なし(対象大学)
- Universal Backdoor Defense via Label Consistency in Vertical Federated Learning
日本大学: 関与なし(対象大学)
- Universal Graph Self-Contrastive Learning
日本大学: 関与なし(対象大学)
- Unleashing the Potential of Transformer Flow for Photorealistic Face Restoration
日本大学: 関与なし(対象大学)
- Unleashing the Semantic Adaptability of Controlled Diffusion Model for Image Colorization
日本大学: 関与なし(対象大学)
- Unlocking Dark Vision Potential for Medical Image Segmentation
日本大学: 関与なし(対象大学)
- Unlocking the Potential of Lightweight Quantized Models for Deepfake Detection
日本大学: 関与なし(対象大学)
- Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming
日本大学: 関与なし(対象大学)
- Unveiling Maternity and Infant Care Conversations: A Chinese Dialogue Dataset for Enhanced Parenting Support
日本大学: 関与なし(対象大学)
- Unveiling the Power of Noise Priors: Enhancing Diffusion Models for Mobile Traffic Prediction
日本大学: 関与なし(対象大学)
- VQCounter: Designing Visual Prompt Queue for Accurate Open-World Counting
日本大学: 関与なし(対象大学)
- Variational Graph Auto-Encoder Driven Graph Enhancement for Sequential Recommendation
日本大学: 関西大学
- Variational Multi-Modal Hypergraph Attention Network for Multi-Modal Relation Extraction
日本大学: 関与なし(対象大学)
- Variational Offline Multi-agent Skill Discovery
日本大学: 関与なし(対象大学)
- Variety-Seeking Jump Games on Graphs
日本大学: 関与なし(対象大学)
- VeRecycle: Reclaiming Guarantees from Probabilistic Certificates for Stochastic Dynamical Systems after Change
日本大学: 関与なし(対象大学)
- Verified Certificates via SAT and Computer Algebra Systems for the Ramsey R(3,8) and R(3,9) Problems
日本大学: 関与なし(対象大学)
- Verifying Quantized Graph Neural Networks is PSPACE-complete
日本大学: 関与なし(対象大学)
- VidEvo: Evolving Video Editing through Exhaustive Temporal Modeling
日本大学: 関与なし(対象大学)
- VideoHumanMIB: Unlocking Appearance Decoupling for Video Human Motion In-betweening
日本大学: 関与なし(対象大学)
- View-Association-Guided Dynamic Multi-View Classification
日本大学: 関与なし(対象大学)
- VimGeo: Efficient Cross-View Geo-Localization with Vision Mamba Architecture
日本大学: 関与なし(対象大学)
- Viral Marketing and Convergence Properties in Generalised Voter Model
日本大学: 関与なし(対象大学)
- Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models
日本大学: 関与なし(対象大学)
- Volumetric Axial Disentanglement Enabling Advancing in Medical Image Segmentation
日本大学: 関与なし(対象大学)
- WDMIR: Wavelet-Driven Multimodal Intent Recognition
日本大学: 関与なし(対象大学)
- Wave-driven Graph Neural Networks with Energy Dynamics for Over-smoothing Mitigation
日本大学: 関与なし(対象大学)
- Wave-wise Discriminative Tracking by Phase-Amplitude Separation, Augmentation and Mixture
日本大学: 関与なし(対象大学)
- Wavelet Multi-scale Region-Enhanced Network for Medical Image Segmentation
日本大学: 関与なし(対象大学)
- Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network
日本大学: 関与なし(対象大学)
- WenyanGPT: A Large Language Model for Classical Chinese Tasks
日本大学: 関与なし(対象大学)
- What Can We Learn From MIMO Graph Convolutions?
日本大学: 関与なし(対象大学)
- What Makes You Special? Contrastive Heuristics Based on Qualified Dominance
日本大学: 関与なし(対象大学)
- Where Does This Data Come From? Enhanced Source Inference Attacks in Federated Learning
日本大学: 関西大学