Vision 固定订阅页

《PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving》〔评测 / 方法〕：This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segme…

1. PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving · Score 106
   title matched "multimodal"；title matched "segmentation"；has PDF
   原始来源
2. Diff-SBSR: Learning Multimodal Feature-Enhanced Diffusion Models for Zero-Shot Sketch-Based 3D Shape Retrieval · Score 100
   title matched "diffusion"；title matched "multimodal"；has PDF
   原始来源
3. ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis · Score 90
   title matched "video generation"；summary matched "diffusion"；has PDF
   原始来源
4. MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation · Score 89
   title matched "video generation"；summary matched "diffusion"；has PDF
   原始来源
5. MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention · Score 89
   title matched "segmentation"；summary matched "diffusion"；has PDF
   原始来源

《AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation》〔应用 / 方法〕：Video diffusion transformers (DiTs) suffer from prohibitive inference latency due to quadratic attention complexity. Existing…

1. AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation · Score 87
   title matched "video generation"；summary matched "diffusion"；has PDF
   原始来源
2. DiffuSAM: Diffusion Guided Zero-Shot Object Grounding for Remote Sensing Imagery · Score 85
   title matched "diffusion"；summary matched "segmentation"；has PDF
   原始来源
3. Weakly-Supervised Referring Video Object Segmentation through Text Supervision · Score 76
   title matched "segmentation"；summary matched "multimodal"；has PDF
   原始来源
4. AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation · Score 72
   title matched "segmentation"；has PDF；has rich summary
   原始来源
5. UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models · Score 71
   title matched "diffusion"；has PDF；has rich summary
   原始来源

《SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation》〔应用 / 方法〕：Reliable uncertainty estimation is critical for medical image segmentation, where automated contours…

1. SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation · Score 72
   title matched "segmentation"；has PDF；has rich summary
   原始来源
2. Unsupervised Skeleton-Based Action Segmentation via Hierarchical Spatiotemporal Vector Quantization · Score 70
   title matched "segmentation"；has PDF；has rich summary
   原始来源
3. Boundary-Centric Active Learning for Temporal Action Segmentation · Score 70
   title matched "segmentation"；has PDF；has rich summary
   原始来源
4. An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for Image Generation · Score 70
   title matched "diffusion"；has PDF；has rich summary
   原始来源
5. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework · Score 68
   summary matched "diffusion"；summary matched "multimodal"；has PDF
   原始来源

《ROSE: Retrieval-Oriented Segmentation Enhancement》〔评测 / 方法〕：Existing segmentation models based on multimodal large language models (MLLMs), such as LISA, often struggle with novel or emerging entities due to their inab…

1. ROSE: Retrieval-Oriented Segmentation Enhancement · Score 90
   title matched "segmentation"；summary matched "multimodal"；has PDF
   原始来源
2. Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models · Score 88
   title matched "multimodal"；summary matched "segmentation"；has PDF
   原始来源
3. Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding · Score 78
   title matched "multimodal"；summary matched "diffusion"；has PDF
   原始来源
4. DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer · Score 78
   title matched "diffusion"；summary matched "video generation"；has PDF
   原始来源
5. Seedance 2.0: Advancing Video Generation for World Complexity · Score 72
   title matched "video generation"；has PDF；has rich summary
   原始来源

《RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation》〔评测 / 方法〕：Multimodal semantic segmentation has emerged as a powerful paradigm for enhancing scene understanding by leveragin…

1. RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation · Score 100
   title matched "multimodal"；title matched "segmentation"；has PDF
   原始来源
2. All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding · Score 78
   title matched "multimodal"；summary matched "segmentation"；has PDF
   原始来源
3. Probabilistic Feature Imputation and Uncertainty-Aware Multimodal Federated Aggregation · Score 71
   title matched "multimodal"；has PDF；has rich summary
   原始来源
4. AbdomenGen: Sequential Volume-Conditioned Diffusion Framework for Abdominal Anatomy Generation · Score 71
   title matched "diffusion"；has PDF；has rich summary
   原始来源
5. Radar-Camera BEV Multi-Task Learning with Cross-Task Attention Bridge for Joint 3D Detection and Segmentation · Score 70
   title matched "segmentation"；has PDF；has rich summary
   原始来源

《OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation》〔评测 / 数据 / 应用 / 方法〕：In this work, we study Human-Object Interaction Video Generation (HOIVG), which aims to synthesize high-quality…

1. OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation · Score 112
   title matched "video generation"；title matched "multimodal"；has PDF
   原始来源
2. LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation · Score 90
   title matched "segmentation"；summary matched "multimodal"；has PDF
   原始来源
3. GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth · Score 87
   title matched "segmentation"；summary matched "multimodal"；has PDF
   原始来源
4. Anthropogenic Regional Adaptation in Multimodal Vision-Language Model · Score 86
   title matched "multimodal"；summary matched "diffusion"；has PDF
   原始来源
5. GazeVaLM: A Multi-Observer Eye-Tracking Benchmark for Evaluating Clinical Realism in AI-Generated X-Rays · Score 78
   summary matched "diffusion"；summary matched "multimodal"；has DOI
   原始来源

收录 10 篇，重点包括《Action Images: End-to-End Policy Learning via Multiview Video Generation》、《DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models》。

1. Action Images: End-to-End Policy Learning via Multiview Video Generation
   原始来源
2. DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
   原始来源
3. MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control
   原始来源
4. Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery
   原始来源
5. SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation
   原始来源