self-supervised learning

Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery WACV 2026 Reading Your Actions: Learning Generalizable Action Representations via Pre-training AEMG CVPR 2026 Reasoning via Implicit Self-supervised Emergence for Instruction Segmentation AAAI 2026 Region-Aware Instance Consistency Learning for Micro-Expression Recognition CVPR 2026 Reimagining Anomalies: What If Anomalies Were Normal? AAAI 2026 Reliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding AAAI 2026 RelightAnyone: A Generalized Relightable 3D Gaussian Head Model CVPR 2026 Render-to-Adapt: Unsupervised Personal Adaptation for Gaze Estimation CVPR 2026 Residual Connections Harm Generative Representation Learning CVPR 2026 Rethinking Box Supervision: Bias-Free Weakly Supervised Medical Segmentation CVPR 2026 Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction AAAI 2026 RiskProp: Collision-Anchored Self-Supervised Risk Propagation For Early Accident Anticipation CVPR 2026 RiverScope: High-Resolution River Masking Dataset AAAI 2026 RoSAMDepth: Robust Self-supervised Depth Estimation Leveraging Segment Anything Model CVPR 2026 RTMol: Rethinking Molecule-text Alignment in a Round-trip View AAAI 2026 S2-Boost: Synergistic Semantic Boosting for Coarse-to-Fine Ensemble Learning AAAI 2026 S²HyRec: Self-Supervised Hypergraph Sequential Recommendation AAAI 2026 S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything Without Supervision AAAI 2026 SAIL: Self-supervised Learning of Lighting-Invariant Representations from Real Images with Latent Diffusion WACV 2026 SARMAE: Masked Autoencoder for SAR Representation Learning CVPR 2026 SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance WACV 2026 Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction CVPR 2026 Scaling Up AI Alignment AAAI 2026 SCAN: Self-Calibrated AutoregressioN for High-Quality Visual Generation AAAI 2026 SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation CVPR 2026