| Poster 1 Chair: TBC |
10:00 - 11:45 | 15 | Sequential Amodal Segmentation via Cumulative Occlusion Learning |
|---|---|---|---|
| 16 | Region-based Entropy Separation for One-shot Test-Time Adaptation | ||
| 18 | MeTTA: Single-View to 3D Textured Mesh Reconstruction with Test-Time Adaptation | ||
| 19 | Few-shot Multispectral Segmentation with Representations Generated by Reinforcement Learning | ||
| 22 | HDRSplat: Gaussian Splatting for High Dynmaic Range 3D Scene Reconstruction from Raw Images | ||
| 25 | AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation | ||
| 26 | Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN | ||
| 33 | Self-Supervised Real-World Denoising by Jointly Learning Visible and Invisible Noise | ||
| 38 | Linear Calibration Approach to Knowledge-free Group Robust Classification | ||
| 41 | Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution | ||
| 43 | Learning to Segment Publicly Accessible Green Spaces with Visual and Semantic Data | ||
| 54 | InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning | ||
| 64 | Multi-Modal Information Bottleneck Attribution with Cross-Attention Guidance | ||
| 66 | Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models | ||
| 85 | Textual Attention RPN for Open-Vocabulary Object Detection | ||
| 101 | Interactive Image Segmentation with Temporal Information Augmented | ||
| 142 | Recovering Global Data Distribution Locally in Federated Learning | ||
| 150 | AISE: Adaptive Input Sampling for Explanation of Black-box Models | ||
| 152 | Retinex-Inspired Cooperative Game Through Multi-Level Feature Fusion for Robust, Universal Image Restoration | ||
| 164 | Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds | ||
| 165 | Learning Object Placement via Convolution Scoring Attention | ||
| 168 | Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation | ||
| 203 | S³-Match: Common-View Aligned Image Matching via Self-Supervised Keypoint Selection | ||
| 207 | Feature Splatting for Better Novel View Synthesis with Low Overlap | ||
| 210 | BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimation | ||
| 215 | AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains | ||
| 217 | GeoFormer: A Multi-Polygon Segmentation Transformer | ||
| 223 | AUPIMO: Redefining Anomaly Localization Benchmarks with High Speed and Low Tolerance | ||
| 227 | Cost-Sensitive Learning for Long-Tail Temporal Action Segmentation | ||
| 240 | SAM Helps SSL: Mask-guided Attention Bias for Self-supervised Learning | ||
| 249 | Transferable Learned Image Compression-Resistant Adversarial Perturbations | ||
| 250 | Deep Unfolding Network with Spatial-spectral Perception Enhanced for Pan-sharpening | ||
| 256 | IncreLM: Incremental 3D Line Mapping | ||
| 262 | Toward Highly Efficient Semantic-Guided Machine Vision for Low-Light Object Detection | ||
| 267 | Depth-Guided Privacy-Preserving Visual Localization Using 3D Sphere Clouds | ||
| 290 | Are Sparse Neural Networks Better Hard Sample Learners? | ||
| 295 | MxT: Mamba x Transformer for Image Inpainting | ||
| 297 | Generalizing Teacher Networks for Effective Knowledge Distillation Across Student Architectures | ||
| 12 | CLIP Adaptation by Intra-Modal Overlap Reduction | ||
| 77 | PT43D: A Probabilistic Transformer for Generating 3D Shapes from Single Highly-Ambiguous RGB Images | ||
| 304 | Interpretable Representation Learning from Videos using Nonlinear Priors | ||
| 557 | Hybrid-CSR: Coupling Explicit and Implicit Reconstruction of Cortical Surface | ||
| 763 | Horospherical Learning with Smart Prototypes | ||
| Oral 1 Chair: TBC |
11:45 | 12 | CLIP Adaptation by Intra-Modal Overlap Reduction |
| 12:00 | 77 | PT43D: A Probabilistic Transformer for Generating 3D Shapes from Single Highly-Ambiguous RGB Images | |
| 12:15 | 304 | Interpretable Representation Learning from Videos using Nonlinear Priors | |
| 12:30 | 557 | Hybrid-CSR: Coupling Explicit and Implicit Reconstruction of Cortical Surface | |
| 12:45 | 763 | Horospherical Learning with Smart Prototypes | |
| Poster 2 Chair: TBC |
14:00 - 15:45 | 37 | DRAFT: Direct Radiance Fields Editing with Composable Operations |
| 39 | HFGS: 4D Gaussian Splatting with Emphasis on Spatial and Temporal High-Frequency Components for Endoscopic Scene Reconstruction | ||
| 45 | D³Nav: Data-Driven Driving Agents for Autonomous Vehicles in Unstructured Traffic | ||
| 46 | FFR-UNet: Feature Filter-Refinement UNet for Medical Image Segmentation | ||
| 60 | Advancing Medical Image Segmentation: Morphology-Driven Learning with Diffusion Transformer | ||
| 100 | Painterly Image Harmonization via Bi-Transformation with Dynamic Kernels | ||
| 166 | Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection | ||
| 183 | Hierarchical Prompt Learning for Scene Graph Generation | ||
| 185 | Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion | ||
| 199 | A Revisit to the Decoder for Camouflaged Object Detection | ||
| 263 | Improving Object Detection via Local-global Image-translation | ||
| 319 | Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation | ||
| 342 | Unsupervised Domain Adaptation for Tubular Structure Segmentation Across Different Anatomical Sources | ||
| 365 | Cascade Masked Generative Distillation for Dense Prediction Tasks | ||
| 392 | Label Smoothing++: Enhanced Label Regularization for Training Neural Networks | ||
| 401 | Decoupling Forgery Semantics for Generalizable Deepfake Detection | ||
| 417 | Kernel Representation for Dynamic Networks | ||
| 424 | RETRO: Reusing teacher projection head for efficient embedding distillation on Lightweight Models via Self-supervised Learning | ||
| 472 | SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentation | ||
| 480 | Disparity Estimation Using a Quad-pixel Sensor | ||
| 500 | Future Does Matter: Boosting 3D Object Detection with Temporal Motion Estimation in Point Cloud Sequences | ||
| 533 | TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Training | ||
| 601 | Training-Free Zero-Shot Semantic Segmentation with LLM Refinement | ||
| 622 | The Attempt on Combining Three Talents by KD with Enhanced Boundary in Co-salient Object Detection | ||
| 630 | CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement | ||
| 637 | 3D Point Cloud Network Pruning: When Some Weights Do not Matter | ||
| 642 | Revitalizing Legacy Video Content: Deinterlacing with Bidirectional Information Propagation | ||
| 648 | 3D Blur Kernel on Gaussian Splatting | ||
| 667 | ICAF-4: An Integrated Framework of Category-level Articulated Object Perception and Manipulation for Embodied Intelligence | ||
| 685 | Boundary Contrastive Learning for Label-Efficient Medical Image Segmentation | ||
| 697 | Inverse Rendering of Outdoor Scenes with under Time-variant Illumination | ||
| 737 | Pseudo Labelling for Enhanced Masked Auto Encoders | ||
| 762 | Open-World Semi-Supervised Learning under Compound Distribution Shifts | ||
| 797 | Calibration of 2D LiDAR sensors using cylindrical target | ||
| 854 | CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection | ||
| 895 | Self-Evolving Depth-Supervised 3D Gaussian Splatting from Rendered Stereo Pairs | ||
| 897 | topK dice loss for medical image segmentation | ||
| 53 | NCA-Morph: Medical Image Registration with Neural Cellular Automata | ||
| 528 | SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries | ||
| 663 | Unsupervised Point Cloud Registration with Self-Distillation | ||
| 729 | Reconstructing Spheres by Fitting Planes | ||
| 779 | Outlier detection by ensembling uncertainty with negative objectness | ||
| Oral 2 Chair: TBC |
15:45 | 53 | NCA-Morph: Medical Image Registration with Neural Cellular Automata |
| 16:00 | 528 | SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries | |
| 16:15 | 663 | Unsupervised Point Cloud Registration with Self-Distillation | |
| 16:30 | 729 | Reconstructing Spheres by Fitting Planes | |
| 16:45 | 779 | Outlier detection by ensembling uncertainty with negative objectness |