{"total":30,"rows":[{"id":"2507.01634","title":"Depth Anything at Any Condition","created":"2025-07-02","cited_by_count":12,"area":null},{"id":"2508.08811","title":"Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment","created":"2025-08-12","cited_by_count":5,"area":null},{"id":"2509.15096","title":"OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation","created":"2025-09-18","cited_by_count":5,"area":null},{"id":"2508.13601","title":"Unleashing Semantic and Geometric Priors for 3D Scene Completion","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2509.10005","title":"TUNI: Unifying Pre-training and Fine-tuning with Modality-Aware Mutual Learning and Rectification for RGB-T Semantic Segmentation","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2511.13047","title":"DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2601.01192","title":"Crowded Video Individual Counting Informed by Social Grouping and Spatial-Temporal Displacement Priors","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2609.12622","title":"RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation","created":"2026-09-11","cited_by_count":2,"area":null},{"id":"2507.09294","title":"Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2604.11585","title":"GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.12319","title":"RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.15856","title":"Robust Multispectral Semantic Segmentation under Missing or Full Modalities via Structured Latent Projection","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.19591","title":"Structure-Semantic Decoupled Modulation of Global Geospatial Embeddings for High-Resolution Remote Sensing Mapping","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.10706","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2607.10278","title":"Geometry-aware Gaussian Prior and Axial Attention for Cervical Cytology Image Classification","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2601.02831","title":"DGA-Net: Enhancing SAM with Depth Prompting and Graph-Anchor Guidance for Camouflaged Object Detection","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2602.11804","title":"Efficient Segment Anything with Depth-Aware Fusion and Limited Training Data","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.13588","title":"Two-Stream Interactive Joint Learning of Scene Parsing and Geometric Vision Tasks","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.07691","title":"RoboPCA: Pose-centered Affordance Learning from Human Demonstrations for Robot Manipulation","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.28414","title":"Unified Restoration-Perception Learning: Maritime Infrared-Visible Image Fusion and Segmentation","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.26893","title":"Graph-based Semantic Calibration Network for Unaligned UAV RGBT Image Semantic Segmentation and A Large-scale Benchmark","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.24893","title":"BED-SAM2: Boundary-Enhanced-Depth SAM2 via Monocular Geometric Priors","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.02551","title":"AFUN: Towards an Affordance Foundation Model for Functionality Understanding","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.09143","title":"Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.03559","title":"Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.05671","title":"URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.27226","title":"DINOcular: Self-Supervised Visuospatial Representations","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.28360","title":"Privacy-Preserving Semantic Segmentation from High-Resolution Depth and Ultra-Low-Resolution RGB","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.29028","title":"RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.07014","title":"DTFormer: Text-Guided Semantic Alignment for RGB-D Segmentation","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}