1300 papers
The paper introduces VocSegMRI, a multimodal framework that leverages cross-attention fusion and contrastive learning to integrate video, audio, and phonological signals, achieving state-of-the-art vocal tract segmentation in real-time MRI with a Dice score of 0.95 and robust performance even when audio is unavailable.
CoRe-GS is a coarse-to-refine Gaussian Splatting framework that accelerates 3D reconstruction for robotic applications by selectively optimizing only task-relevant points of interest, thereby significantly reducing training time and mitigating artifacts while maintaining high-quality semantic segmentation.
YOPO is a minimalist, single-stage transformer framework that unifies 2D object detection and category-level 9-DoF pose estimation from monocular RGB images without requiring pseudo-depth or CAD models, achieving state-of-the-art performance on multiple benchmarks.
This paper introduces FieldLVLM, a novel framework that enhances Large Vision-Language Models' ability to interpret complex scientific field data by combining a specialized pipeline for extracting physical features into structured text with a data-compressed tuning strategy, resulting in superior performance on scientific benchmarks.
This paper proposes SpikeSMOKE, a low-power monocular 3D object detection framework based on Spiking Neural Networks that introduces a Cross-Scale Gating Coding mechanism and a lightweight residual block to overcome information loss and computational inefficiency, achieving superior performance on KITTI and other datasets while significantly reducing energy consumption and model complexity compared to traditional ANN-based approaches.
This paper introduces EasyText, a controllable Diffusion Transformer framework that leverages character positioning encoding and position interpolation to achieve high-quality, precise multilingual text rendering, supported by a newly constructed large-scale synthetic dataset for pretraining and fine-tuning.
This paper proposes MARRS, a novel framework that generates coordinated and fine-grained human reaction motions by combining a Unit-distinguished Motion VAE, Action-Conditioned Fusion with token masking, and Adaptive Unit Modulation to overcome the limitations of vector quantization and enhance inter-unit interaction.
This paper introduces M4-SAR, a large-scale, multi-resolution, multi-polarization, and multi-source dataset with nearly one million labeled instances, alongside a unified benchmarking toolkit and a novel end-to-end fusion framework (E2E-OSDet) that collectively advance optical-SAR object detection by demonstrating significant performance gains over single-source methods in complex environments.
This paper introduces BR-Gen, a large-scale dataset of 150,000 locally forged images with diverse scene-aware annotations, and proposes NFA-ViT, a noise-guided Vision Transformer that amplifies subtle forgery traces to significantly improve the detection and generalization of localized AI-generated image forgeries.
This paper proposes a novel semi-supervised teacher-student framework for biomedical image segmentation that leverages denoising diffusion probabilistic models to generate and iteratively refine pseudo-labels, demonstrating superior performance over state-of-the-art methods in scenarios with limited annotated data.
This paper introduces RS-STE, a novel unified framework that synergistically integrates text recognition and editing via a multi-modal parallel decoder and cyclic self-supervised fine-tuning to achieve state-of-the-art scene text editing performance on both synthetic and real-world benchmarks.
This survey provides a comprehensive review of over 200 papers on Wi-Fi sensing generalizability, offering a structured taxonomy of techniques to address domain shifts, summarizing key datasets, and outlining future research directions and community resources.
This paper introduces iMarkers, a novel class of invisible fiducial markers detectable only by robots and AR devices, which overcome the visual aesthetic limitations of traditional markers while offering customizable production, robust detection algorithms, and proven effectiveness across diverse robotics scenarios.
This paper introduces ARSGaussian, a novel view synthesis method for aerial remote sensing that integrates LiDAR constraints, distortion-aware coordinate transformations, and geometric consistency losses to mitigate floaters and overgrowth while achieving high-precision geo-alignment, supported by the newly released AIR-LONGYAN dataset.
This paper proposes a budget-efficient active prompt learning framework for vision-language models that utilizes class-guided clustering and adaptive class-wise thresholding to achieve higher accuracy with fewer labeled samples compared to existing baselines.
TIMotion is an efficient framework for human-human motion generation that improves upon existing methods by introducing Causal Interactive Injection, Role-Evolving Scanning, and Localized Pattern Amplification to better model temporal dynamics and interactive roles, thereby achieving superior performance on benchmark datasets.
ReCoSplat is an autoregressive feed-forward Gaussian Splatting model that overcomes the training-inference pose mismatch dilemma through a novel Render-and-Compare module and achieves state-of-the-art online novel view synthesis with efficient long-sequence handling via hybrid KV cache compression.
This paper introduces the concept of Whole Slide Difficulty (WSD), derived from diagnostic disagreements between expert and non-expert pathologists, and demonstrates that leveraging this metric through multi-task learning or weighted loss functions significantly improves the accuracy of prostate cancer Gleason grading in Multiple Instance Learning models, particularly for higher-grade cases.
This paper proposes a novel unsupervised domain adaptation framework based on a reformulated Margin Disparity Discrepancy to bridge the modality gap between annotated CT and unannotated interventional CBCT scans, achieving state-of-the-art performance in liver segmentation for both unsupervised and few-shot settings.
This paper proposes an interpretable text-motion retrieval framework that represents 3D human motion as joint-angle pseudo-images processed by Vision Transformers and aligns them with text via a token-wise late interaction mechanism, thereby overcoming the limitations of global-embedding methods by capturing fine-grained correspondences and improving retrieval accuracy.