Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation proposes FreNet, a framework that reconfigures images and features before and during encoding to improve lesion segmentation. It introduces an Implicit Prior Neural Network that uses a visual prior from SAM to suppress background responses, and a Dual-domain Feature Reconfiguration module that decouples features in frequency and spatial domains to better handle diverse lesion morphology. Experiments on nine benchmarks across three imaging modalities show FreNet outperforms state‑of‑the‑art methods, achieving a 5.0% Dice improvement over the best prior method on the ETIS dataset.
OCR-EDR is a rendering‑aware framework that diagnoses and repairs OCR errors by jointly evaluating an OCR prediction, its editable form, and the rendered image of the source document. It localizes genuine mistakes while preserving valid or rendering‑equivalent predictions, then applies executable edits and iteratively reassesses with updated renderings. On the newly constructed OCRErrBench, the DocEDR model achieves 94.78% diagnostic accuracy and repairs 86.23% of errors, boosting formula metrics by up to 30.99 percentage points and improving CDM scores on several OCR systems.
SAUF-Net is a semi‑supervised medical image segmentation framework that learns structure–appearance representations with uncertainty feedback. It decomposes bottleneck features into structural and appearance components, injects them into decoding, and uses auxiliary decoders and a dual‑head discriminator to estimate reliability and uncertainty. Experiments on ISIC‑2016 and Kvasir‑SEG show that SAUF‑Net surpasses state‑of‑the‑art methods, particularly when few labels are available.
By Qin Lu, Zheyang Jing, Yujie Yang, Jianwang Li, Chen Yi, Shaofeng Jiang
The paper introduces a multi‑camera computer vision system that computes Post‑Encroachment Time (PET) in real time to assess intersection safety. Using four synchronized cameras and YOLOv11 segmentation on NVIDIA Jetson AGX Xavier devices, vehicle detections are mapped to a unified bird’s‑eye view and processed with a pixel‑level PET algorithm to generate high‑resolution heatmaps. The system records PET data in an SQL database and demonstrates real‑time throughput (2.68 FPS) with 800 × 800 heatmaps, validating a scalable, decentralized approach for high‑resolution intersection safety evaluation.
By Shounak Ray Chaudhuri, Arash Jahangiri, Christopher Paolini
InsightSeg introduces an episodic memory system that captures successful correction episodes from multi-agent refinement processes and transforms them into reusable, visually grounded insights. These insights are distilled into natural-language directives and linked to specific image patches via visual concept vectors, allowing the segmentation agent to anticipate and avoid guideline-specific errors on new images. The approach improves both first-pass and final segmentation quality on Waymo and Cityscapes datasets while reducing the number of required refinement steps.
By Vanshika Vats, Ashwani Rathee, James Davis
The paper presents lightweight architectures for detecting GAN-generated synthetic faces, comparing a compact Swin Transformer, pre‑trained Swin‑Tiny and Swin‑Small models, and a hybrid EfficientNet‑B0 + Swin Transformer. Using the 140K Real and Fake Faces dataset, the hybrid model achieved 99% accuracy and 99.44% recall on 5,000 test images, outperforming both pure Swin variants and a CNN‑only baseline. The study demonstrates that combining hierarchical CNN features with shifted‑window self‑attention yields an efficient, computationally lightweight detection method.
By Sejuti Basu, Ashima Sood, Vijay Kumar, Sahil Sharma
InfraPatch is a white‑box, per‑instance framework that generates small grayscale patches to target infrared‑adapted vision‑language models (IR‑VLMs). The method optimizes a single‑channel patch within a 5% local‑area budget, using proxy‑guided placement and task‑adaptive objectives to induce desired behaviors in image classification, captioning, and binary visual question answering. Across ten IR‑VLM variants tested on synthetic infrared images, InfraPatch achieves targeted attack success rates ranging from 86% to 100%, revealing significant vulnerability differences among architectures and tasks.
By Chengyin Hu, Dingyi Lu, Jiaju Han, Xiang Chen, Weiwen Shi, Jiahuan Long, Yiwei Wei, Jiujiang Guo
The paper introduces a new framework for estimating full-degree-of-freedom egomotion directly from asynchronous optical flow captured by event cameras. By decoupling the differential epipolar constraint into angular and linear components and applying a first-order approximation, the authors derive a polynomial formulation that yields the first algebraic minimal 5‑point solver for this problem. An accelerated solver that truncates high‑order angular velocity terms is also proposed, enabling real‑time performance in high‑speed scenarios, and extensive tests show superior accuracy and robustness compared to traditional synchronous methods.
By Shuo Pan, Banglei Guan, Bin Li, Zhenbao Yu, Zibin Liu, Zi Wang, Yang Shang, Qifeng Yu
AlphaRAD introduces a grounded zero‑shot classification framework for chest radiology that leverages structured medical concepts extracted from reports and a novel α‑Corrected Binary Cross‑Entropy loss to reduce in‑batch noise. It also presents FLaS, a lightweight cross‑modal fusion module that factorizes VLPM representations into independent subspaces, improving spatial grounding without adding parameters. The method achieves state‑of‑the‑art performance on 16 classification benchmarks and sets new records on several grounding, phrase‑grounding, and segmentation datasets.
By Jianzhong You, Yuan Gao, Chris McIntosh
The paper presents CycleGRPO, a reinforcement learning framework that unifies region understanding and localization for multimodal large language models (MLLMs). By treating the MLLM as both actor and critic, the method generates region captions and immediately grounds them back into spatial coordinates, using a token‑level cycle‑consistency reward that obviates the need for textual ground truths. Experiments on SAMTok demonstrate that CycleGRPO can bootstrap region captioning, VQA, grounded dialogue, and referring segmentation simultaneously, achieving consistent performance gains without task‑specific fine‑tuning.
By Xin Zhang, Haochen Wang, Yikang Zhou, Zhuochen Wang, Xiangtai Li, Robby T. Tan
The paper introduces a dual‑backbone architecture for glass segmentation that combines a frozen foundation model with a learned backbone trained on glass‑specific data. By fusing hierarchical multi‑scale features from both backbones, the method produces accurate segmentation masks and achieves state‑of‑the‑art performance on four benchmark datasets. Ablation studies confirm the benefits of the dual‑backbone design and its generalizability across different backbone choices, while also offering competitive inference speeds, especially with lighter backbones.
By Risto Ojala, Tristan Ellison, Mo Chen
The paper introduces DWFF‑Net, a Dynamic Weighted Feature Fusion Network designed to improve multi‑scale segmentation for agricultural habitat recognition. It employs a frozen DINOv3 encoder, a data‑level adaptive dynamic weighting strategy, and a decoder with a dynamic weight calculation network and hybrid loss. Experiments on an agricultural habitat dataset show significant gains in mIoU and mF1 over static fusion and several baseline models, especially for tiny features such as scattered trees.
By Kesong Zheng, Zhi Song, Peizhou Li, Shuyi Yao, Tong Li, Yonglin Shen, Zhenxing Bian
The paper introduces the Physics-Aware Radar Transformer (PART), a radar-only detector that predicts moving-object existence, surface points, and ground-plane velocity using Doppler-aware query initialization and physics-guided cross-attention. PART achieves high class-agnostic performance on the nuScenes dataset, excelling in rare categories and adverse conditions such as night, rain, and occlusion. The model is lightweight, with only 1.1 million parameters, and its code and pretrained weights will be released publicly.
By Yinghao Sun, Shuguang Li, Jinliang Shao, Tieshan Li
PointGauss is a 3D-native framework that performs semantic parsing and instance segmentation on 3D Gaussian splatting representations by treating Gaussian primitives as unstructured point sets and extracting scale‑invariant geometric features with Point Transformer V3. It introduces an adaptive region‑of‑interest cropping strategy and an instance‑aware distance‑constrained rasterization pipeline to enable scalable, view‑consistent pixel‑level projections. The authors also release SplatSeg‑360, a cross‑scale benchmark with 32 complex scenes and over 6,300 aligned 2D‑3D masks, and show that PointGauss achieves real‑time performance with state‑of‑the‑art 3D‑mIoU (~90%) and 2D‑mIoU (~80%) scores.
By Wentao Sun, Yiping Chen, John S. Zelek, Jonathan Li
The paper introduces Epipolar Distillation (EpiDistill), a method that transfers scale‑aware geometric priors from multi‑view models to monocular depth foundation models using Rectified Stereo Tokens. By preserving epipolar attention patterns, the single‑view model maintains geometric consistency without needing multi‑view inputs during inference. Experiments show significant improvements in zero‑shot metric depth estimation on challenging datasets such as ETH3D and DIODE, and the approach consistently boosts performance of state‑of‑the‑art ViT‑based models like UniDepthV2 and DepthPro.
By Jung-Hee Kim, Xiaoming Liu
MMTryon is a multi‑modal, multi‑reference virtual try‑on framework that generates high‑quality compositional try‑on results using text instructions and multiple garment images. It addresses three overlooked problems: supporting multiple try‑on items, allowing dressing style specification via text, and eliminating reliance on segmentation models by using a parsing‑free garment encoder and a scalable data generation pipeline. Experiments on high‑resolution benchmarks and in‑the‑wild test sets show MMTryon outperforms state‑of‑the‑art methods qualitatively and quantitatively.
By Xujie Zhang, Ente Lin, Michael Kampffmeyer, Zhenyu Xie, Jiang Li, Ting Liu, Xiaochao Qu, Luoqi Liu, Xiaodan Liang
The paper introduces a new task called video object segmentation‑aware audio generation, which conditions sound synthesis on object‑level segmentation maps. It presents SAGANet, a multimodal generative model that uses visual segmentation masks, video, and textual cues to produce controllable audio for musical instruments, offering fine‑grained, visually localized control. The authors also release the Segmented Music Solos dataset of instrument performance videos with segmentation information to support this task and demonstrate that SAGANet outperforms current state‑of‑the‑art methods in controllable, high‑fidelity Foley synthesis.
By Ilpo Viertola, Vladimir Iashin, Esa Rahtu
PlantC2USeg is a deep transfer‑learning framework that uses cross‑scale consistency learning and an information‑restricted decoder to improve plant point cloud segmentation. It achieves state‑of‑the‑art performance on Soybean3D and ShapeNet Part, and demonstrates strong few‑shot generalization across species and sensing conditions. The method reduces the need for large annotated datasets and lowers adaptation overhead for new plant species.
By Yu Tian, Xintong Jiang, Jan Franklin Adamowski, Shiv O. Prasher, Shangpeng Sun
The paper investigates how much clinical text influences pixel‑level predictions in multimodal medical image segmentation. It shows that segmentation performance is largely insensitive to the choice of fusion module, but that the impact of text varies across datasets: removing text severely degrades performance on BUSI and BTMRI, while it has only a marginal effect on ISIC and Kvasir‑SEG. Using an Evidence Decoupling Decoder, the authors reveal that text mainly modulates global semantic context rather than spatial localization, and that the specific semantic components driving sensitivity differ by dataset.
By Ziquan Liu, Zhewei Zhu, Xuyang Shi
RouteGraph-Mona introduces a confusion‑aware routing fine‑tuning approach for mineral image classification, building on the Mona visual adapter. It replaces Mona’s static multi‑scale aggregation with sample‑adaptive routing, creating a compact routing space that reflects each image’s scale preferences. The method regularizes routing signatures using class‑wise route anchors and confusion‑weighted margins, encouraging consistent routing patterns and greater separation between visually similar mineral categories. Experiments on three public mineral image datasets with two visual backbones show that RouteGraph‑Mona consistently outperforms Mona and remains competitive with other fine‑tuning methods and classification baselines.
By Jierui Li, Zhiyuan Qi, Hao Zhu, Yufan Liu, Jixian Liu, Shaojie Jiang, Jianda Wang, Yaqi Liu, Xiaotong Li, Wei Wang