The paper introduces a context‑aware neural grapheme‑to‑phoneme (G2P) system for unsegmented languages like Japanese, using a discriminative conditional random field over a word lattice built from dictionaries. It addresses data scarcity by generating over two million sentences with large language models. Experiments show the method surpasses traditional morphological analyzers and neural sequence models, achieving 99.62% target word reading accuracy and very low phoneme error rates on the Joyo‑Kanji‑Yomi benchmark.
By Rui Hu, Zhenpeng Zhan, Xiaolong Lin
BinoGen is an automated framework that generates large-scale, embodiment-aware egocentric binocular visual experiences in indoor environments. It models environmental and observer variation through generative scene synthesis, probabilistic object instantiation, appearance randomization, stochastic trajectory generation, and configurable binocular camera setups, producing synchronized videos with dense multimodal supervision such as depth maps, optical flow, surface normals, semantic maps, object coordinates, and camera poses. Using BinoGen, the authors created a dataset of over 20 million annotated images, demonstrating that incorporating this data improves real-world visual perception tasks like depth estimation, object detection, and video object tracking, and that embodiment-specific adaptation enhances performance while joint training enables a single model to perform competitively across different observer embodiments.
By Chunpeng Li, Ya-tang Li
WoundAIssist is an AI‑driven mobile application designed to support remote chronic wound care for elderly patients. It allows patients to capture wound images and complete questionnaires at home, while physicians monitor progress through remote video consultations and on‑device deep‑learning segmentation. A usability study involving patients and dermatologists found the app to be highly usable, of good quality, and positively received for its AI‑driven wound recognition.
By Vanessa Borst, Anna Riedmann, Tassilo Dege, Konstantin M\"uller, Astrid Schmieder, Birgit Lugrin, Samuel Kounev
The study benchmarks four commercial depth sensors—Intel RealSense D405, PMD Flexx2, Stereolabs ZED 2i, and Zivid 2M+ 60—on porcine bone, porcine belly, and a silicone kidney phantom. Using stylus-sampled references, the sensors were evaluated at ~50 cm distance across challenging surfaces such as homogeneous, specular, and subsurface scattering. The Zivid 2M+ 60 achieved the best overall performance, while the ZED 2i ranked second for real tissue but last for the phantom.
By Pit Henrich, Maximilian Weiherer, Franziska Hansen, Bernhard Egger, Franziska Mathis-Ullrich
The paper introduces SonoCorpus, an open dataset of 456,963 ultrasound images with 1,626,085 expert masks from 53 public sources across 24 clinical applications and 17 countries, and SonoBase, an interactive segmentation foundation model pretrained on this data. SonoBase outperforms existing models (SAM2, MedSAM2, MedSAM3) on fifteen diverse evaluation datasets, matching specialist models and achieving clinically relevant accuracy for metrics such as ejection fraction, fetal head circumference, and gestational age. The authors provide full reproducibility resources, including checkpoints, optimizer states, and starter code, to enable community adoption and further development.
By Chao Qin, Fahad Shahbaz Khan, Salman Khan, Sarim Ather, Siddiq Anwar, Rao Muhammad Anwer, Shadab Khan
PART is a transformer-based framework that performs 3D part retrieval and assembly by selecting appropriate parts from a library and predicting their 6‑DoF poses to reconstruct a target shape. It tackles the combinatorial search space, variable‑length outputs, and continuous pose estimation by formulating the task as set prediction and jointly training with a segmentation‑enhanced optimization module. The authors also introduce a large‑scale dataset of over 80,000 shapes and demonstrate that PART generalizes to scene layouts, image targets, and real‑world scans.
By Ruchao Bao, Wenzheng Wu, Chucheng Xiang, Zhongyuan Liu, Yuan Liu, Jinxin Dong, Ligang Liu, Ziqi Wang
LinePilot Digitizer is a tool for extracting numerical data from line plots, offering three calibration modes—standard, enhanced, and OCR—that combine continuous color-based curve recovery with flexible calibration. The authors introduce DigitizerBench, a benchmark that systematically evaluates digitizer performance across signal, rendering, and plot-structure factors, using a failure-penalized capped normalized root-mean-square error metric. Results show that LinePilot (OCR) and LinePilot (enhanced) achieve the lowest error rates and highest trusted usability on their respective benchmark subsets, demonstrating the effectiveness of the calibration modes and the benchmark’s factor analysis capabilities.
By Fengbo Ma, Rayan Akhtar, Aakash H. Joshi, Xiaoting Li, Haijian Sun, Zhen Xiang, Xianyan Chen, Yiping Zhao
The paper presents a method for dense univariate time‑series segmentation by treating each time point as a node in a graph and applying a Graph Attention Network (GAT). Using visibility‑based graph constructions, particularly WDPVG, the approach achieves competitive performance on a 59‑dataset benchmark, matching or surpassing traditional point‑wise classifiers while requiring far fewer parameters and less memory. The method’s advantage stems from long‑range edges that provide contextual information beyond local windows.
By Ivana Kesi\'c, Carolina Fortuna, Mihael Mohor\v{c}i\v{c}, Bla\v{z} Bertalani\v{c}
PerSeM is a training‑free framework that builds a persistent semantic memory for long‑horizon UAV mapping by associating frame‑wise segmentation results with world‑space voxels and refining them through spatial refinement, trust‑aware replay, and context‑guided verification. Experiments on Forest and UAVScenes benchmarks show that this persistent 3D memory improves semantic correctness and temporal stability compared to frame‑wise predictions, especially in semantically difficult and temporally unstable regions. The method achieves these gains without retraining or additional neural‑network inference.
By Saurbh Singh Jamwal, Ganesh Ramakrishnan
The paper introduces G2G, a method that leverages known intra-group geometry to estimate the relative 6-DoF pose between two image groups, a key problem in cross-sequence relocalization and multi-camera rig odometry. G2G keeps a frozen foundation model and adds three lightweight trainable modules—a perceiver resampler, a cross-group bridge with merged self-attention, and a multi-frame pose head—totaling about 32 M parameters, less than 6% of the full model. Evaluated on four diverse datasets covering indoor/outdoor simulation, real-world cross-season capture, and zero-shot sim-to-real transfer, G2G achieves state‑of‑the‑art accuracy on both pose estimation tasks while only requiring supervision from relative poses.
By Yufei Wei, Shuhao Ye, Chenxiao Hu, Yiyuan Pan, Dongyu Feng, Rong Xiong, Yue Wang, Yanmei Jiao
LapaTrack-3D is a real‑time 6 DoF tracking algorithm designed for monocular laparoscopic surgery, aligning intra‑operative video with pre‑operative CT data. It modifies the ORB‑SLAM2 framework with four key changes: fast initialization using a primitive 3D shape, a pseudo‑segmentation strategy to isolate the target organ, incorporation of the 3D shape as a geometric prior in pose graph optimization, and enhanced imaging via a modified Multi‑Scale Retinex with Chromaticity Preservation algorithm. Experiments on in‑vivo and ex‑vivo data show robust tracking under challenging conditions such as poor illumination, fast motion, and partial visibility, achieving 13 Hz on 1280×720 video.
By Jingwei Song, Javid Hussain Jakir, Ray Zhang, Wenwei Zhang, Hao Zhou, Xiaomeng Xian, Maani Ghaffari
This study presents a domain-aware deep learning framework based on nnU-Net for segmenting ischemic stroke lesions on non‑contrast CT scans and quantifying net water uptake (NWU). Trained on data from Hamburg and the Acute Ischemic Stroke Dataset, the model was fine‑tuned on small target‑domain subsets from Boston and ISLES, achieving median Dice scores of 0.68 and 0.56 for lesions ≥30 mL, and an NWU mean absolute error of 1.37 percentage points on the Boston cohort. The results demonstrate that target‑domain adaptation can enable accurate NCCT‑only infarct segmentation and low‑error NWU estimation across heterogeneous multicenter datasets.
By Linus Britt, Maximilian Nielsen, Susan Klapproth, Andre Kemmling, Michael H. Lev, Gabriel Broocks, Rene Werner, Thilo Sentker
The paper introduces DynaWeightPnP, a real‑time algorithm for correspondence‑free Perspective‑n‑Point (PnP) problems that aligns 3D and 2D shapes without needing point correspondences. It uses a Reproducing Kernel Hilbert Space formulation solved via iterative reweighted least squares, and addresses a numerical ambiguity between rotation and translation with a dynamic weighting sub‑problem and alternative search strategy. Experiments on 3D‑2D vascular centerline registration in endovascular image‑guided interventions show processing rates of 60 Hz (without refinement) and 31 Hz (with refinement) on a single‑core CPU, achieving accuracy comparable to existing methods.
By Jingwei Song, Maani Ghaffari
The paper introduces a privacy‑preserving approach to open‑vocabulary 3D semantic segmentation that operates solely on depth data, eliminating the use of RGB images to avoid disclosing scene‑specific visual information. It proposes a stricter depth‑only evaluation protocol and presents UTTO, a model‑agnostic uncertainty‑guided test‑time optimization framework that refines predictions from frozen open‑vocabulary 3D backbones using structured predictive uncertainty. Experiments on ScanNet and Matterport3D show consistent improvements, and additional analyses demonstrate the method’s relevance for privacy‑constrained robotic applications.
By Xuying Huang, Sicong Pan, Maren Bennewitz
The paper introduces BADA, a Boundary-Aware Data Augmentation technique for offline reinforcement learning. By interpolating neighboring states to create synthetic data that respects the original distribution, BADA improves in-distribution generalization and robustness. Experiments on limited offline datasets show that BADA achieves state-of-the-art performance across diverse benchmarks.
By Gong Gao, Weidong Zhao, Xianhui Liu
HunyuanOCR-1.5 is a lightweight, end‑to‑end OCR‑specialized vision‑language model that unifies document parsing, text spotting, information extraction, text‑image translation, and multi‑image document understanding. It builds on the HunyuanOCR‑1.0 architecture, improving efficiency with DFlash‑based OCR decoding for faster inference (6.37× Transformer speedup, 2.14× under vLLM) and enhancing capability through an Agentic Data Flow system that autonomously constructs high‑quality training data for long‑tail OCR tasks. The model achieves top‑tier performance on OmniDocBench v1.6 and sets new milestones in ancient‑script OCR, chart/table parsing, multilingual parsing, and hallucination evaluation, while remaining lightweight for deployment.
By Gengluo Li, Xingyu Wan, Shangpin Peng, Weinong Wang, Hao Feng, Yongkun Du, Binghong Wu, Zheng Ruan, Zhiqiong Lu, Liang Wu, Pengyuan Lyu, Huawen Shen, Zibin Lin, Shijing Hu, Jieneng Yang, Hongbing Wen, Guanghua Yu, Hong Liu, Bochao Wang, Can Ma, Han Hu, Chengquan Zhang, Yu Zhou
The paper introduces the "segmentation ceiling," a quantitative criterion that determines when explicit left‑ventricular (LV) segmentation can improve ejection fraction (EF) regression. By deriving how per‑frame segmentation area error propagates into EF error, the authors find that a break‑even error of about 10% per frame is required, whereas typical segmenters exceed this threshold (~14%). Consequently, several strategies that incorporate segmentation or area information fail to outperform a raw‑video baseline, while techniques such as weight averaging with strong augmentation and a heteroscedastic beta‑NLL loss yield competitive EF predictions and well‑calibrated uncertainty estimates.
By Farshid Farhadi Khouzani, Paul La Plante, Bryar Mustafa Shareef, Laxmi Gewali
G^2RA‑Net is a medical image segmentation framework that models cross‑slice relations using a graph-based approach and refines segmentation with a cross‑slice attention gate. It represents each image slice as a graph node, propagates semantic context through graph message passing, and then selects relevant neighboring context to emphasize target anatomical regions. Experiments on brain MRI and abdominal CT datasets show that G^2RA‑Net improves segmentation accuracy and boundary quality compared to representative methods, with ablation studies confirming the effectiveness of its design.
By Shengye Wang, Zonglin Wu, Liang Fan, Yule Xue, Haozhe Zhao
FreqDINO++ is a frequency‑guided multi‑task routing vision foundation model designed for universal ultrasound analysis. It introduces a Multi‑task Routing Adapter for efficient task‑common and task‑specific integration, a Frequency‑aware Feature Enhancer to capture multi‑scale frequency characteristics, and a Task‑aligned Collaborative Decoder that promotes collaboration between dense and global prediction tasks. Experiments on large‑scale multi‑task and external single‑task ultrasound benchmarks show that FreqDINO++ outperforms strong baselines and recent foundation models across 27 diverse clinical task scenarios, with promising generalization to unseen data.
By Qing Xu, Yixuan Zhang, Yue Li, Xiangjian He, Qian Zhang, Mainul Haque, Rong Qu, Wenting Duan, Jieyun Bai, Zhen Chen
The Public Discourse Corpus (PDC) is the first dataset of public‑figure interview speech annotated for affective valence and epistemic modality. It contains 998 videos from 100 speakers across seven professional domains, yielding 186,642 sentences (3.1 million words). A key methodological contribution is Target Speaker Participation (TSP), a five‑category annotation taxonomy with documented inter‑annotator reliability (κ = 0.616), and an audio‑first diarization pipeline that separates target‑speaker turns from interviewer and third‑party speech. The corpus, annotation tools, validation sample, and processing pipeline are released as open source.
By Bo Chen