Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
The inappropriate disposal of solid waste remains a significant public health and environmental concern worldwide, including in Ghana. Poor sanitation and improper waste management practices contribut...
Acquiring pixel-level annotations for medical image segmentation is a severe bottleneck. Traditional U-Net architectures, while effective, learn local texture patterns and lack awareness of global ana...
Human-robot interaction (HRI) requires robots to interpret human actions early in their execution in order to respond safely, efficiently, and naturally. However, many existing approaches to human act...
arXiv:2605.30972v2 Announce Type: replace Abstract: Accurate 3D medical image segmentation requires both fine spatial detail and long-range volumetric context. Although Mamba provides efficient long-...
CytoNet is a foundation model trained on 1 million unlabeled microscopic image patches from over 4,000 histological sections of nine postmortem brains, and evaluated on 2,000 sections from five additional brains. By using co‑localization in the cortical sheet for self‑supervision, it learns expressive, anatomically meaningful feature representations that enable downstream tasks such as area classification, laminar segmentation, microarchitectural quantification, and exploratory mapping of cortical subdivisions. Functional parcellation analyses demonstrate links between cytoarchitecture and macroscale functional organization, establishing CytoNet as a unified framework for scalable analysis of cortical microarchitecture and its relationship to structure‑function organization in the human cerebral cortex.
arXiv:2306.14300v2 Announce Type: replace-cross Abstract: Autism spectrum disorder (ASD) is a developmental condition that presents significant challenges in social interac- tion, communication, and...
The article addresses a specific data clustering problem: identifying groups of adjacent text segments of a suitable length that match a fuzzy pattern defined by a sequence of fuzzy properties. It proposes a heuristic algorithm that uses a prefix structure to efficiently map text segments to fuzzy properties, and proves that for the special case of unit-length segments (fuzzy string matching), the algorithm finds all matching segments. Additionally, it presents a dynamic programming approach to determine the best segmentation of an entire text based on a fuzzy pattern.
arXiv:2608.24384v1 Announce Type: cross Abstract: Resistance training can be a high risk activity, and safe form is essential to avoiding injury. Laboratory-based movement analysis provides quantitiv...
The paper proposes a modular training pipeline for zero‑shot cross‑city object detection that combines a multi‑dataset pre‑training strategy with class‑agnostic objectness distillation and a domain‑resilient augmentation stream featuring a Grayworld transformation. Applied to the RF‑DETR detector, the approach reduces cross‑city distribution gaps while using only 16 GB GPU memory, achieving a 24.29‑point mAP improvement and 1st place on the AI City Challenge Track 6 leaderboard. The authors provide code and data at the referenced GitHub repository.
The paper introduces Attnlocate, a runtime framework that localizes behavior‑guiding instructions within the attention matrix of large language model agents. By treating this localization as an object detection task, Attnlocate uses a multi‑head, multi‑layer attention aggregation scheme and a 1‑D U‑Net to identify spans that influence tool‑calling decisions. The system then adjudicates potential malicious invocations based on the authority of the source, achieving high detection metrics across diverse LLM families and demonstrating transferability to unseen models.
PhysMLLMs introduces physics-inspired spatial continuity priors into video multimodal large language models to address spatio‑temporal inconsistencies such as jitter, drift, and identity switches. The method, called Global Representation Prior Alignment (REPA‑Global), distills global visual representations from a frozen DINOv2 teacher during training, aligning student representations without affecting inference speed. Experiments on multiple video benchmarks show improved segmentation mask quality and cross‑frame consistency, especially for challenging scenarios involving small targets, fast motion, occlusion, and distractors, while maintaining comparable performance on single‑frame image segmentation and general VLM tasks.
The study audits the AION-1 foundation model, a 39‑modality transformer trained on over 200 million astronomical objects, and finds that its reliance on a survey detection channel—specifically the segmentation map—introduces a severe systematic bias. By keeping image tokens unchanged and editing only the segmentation map, all model outputs (flux, size, ellipticity, redshift) shift by factors of 110–4400 compared to a placebo, revealing that the model’s predictions are driven more by detection gating than by the actual light distribution. This bias propagates into cosmological analyses, shifting tomographic mean redshifts by a median 0.71 × the LSST DESC requirement and exceeding it in multiple assignments, while removing the detection channel eliminates the effect without measurable cost. whyItMatters":"The bias in the detection channel directly inflates errors in key astronomical measurements, potentially compromising the precision of cosmological studies that rely on accurate redshift estimates."
The paper introduces SAM‑H, a planar object tracker that estimates 8‑degree‑of‑freedom homographies directly from segmentation mask contours using a training‑free pipeline. When applied to masks from SAM 2, SAM‑H achieves a new state‑of‑the‑art performance on the PlanarTrack benchmark, improving the p@5 metric by 18.4 percentage points. The authors also demonstrate that combining segmentation‑based and correspondence‑based homography estimation yields WOFTSAM, which surpasses all previous methods on both PlanarTrack and POT‑210, and provide precise re‑annotations of PlanarTrack initial poses for more accurate benchmarking.
The paper introduces the Geometric Observability Index (GOI), a per-feature sensitivity metric for SE(3) pose estimation that quantifies the pose perturbation induced by a single measurement via the Gauss‑Newton curvature restricted to the observable subspace. GOI is shown to equal the norm of the M‑estimator influence function, to coincide with the Fisher information operator, and its smallest observable eigenvalue determines both worst‑case measurement amplification and a finite‑sample stability radius. Experiments on synthetic data and real RGB‑D/KITTI sequences validate that GOI accurately predicts leave‑one‑out pose shifts and explains the robustness of residual gating while highlighting the pitfalls of raw‑influence gating in weakly observable geometries.
ConsensusTAS is a self‑supervised, label‑free method for temporal action segmentation in long construction videos. It segments continuous video streams into distinct activity phases by leveraging internal consensus among candidate segmentations, and it has been evaluated on three public datasets, outperforming state‑of‑the‑art methods. In real‑world construction footage, the model successfully identified fine‑grained actions within bricklaying, and it can run on a CPU, making it suitable for mobile robotic platforms.
arXiv:2510.21536v5 Announce Type: replace-cross Abstract: Free-space segmentation is essential for autonomous robots to identify drivable regions and navigate safely across indoor, outdoor, and road-...
arXiv:2506.12006v4 Announce Type: replace-cross Abstract: The cross-Modality Domain Adaptation (crossMoDA) challenge series, initiated in 2021 in conjunction with the International Conference on Medi...
arXiv:2606.26706v2 Announce Type: replace Abstract: Intracranial aneurysms are often asymptomatic until rupture, which carries high mortality. Rupture risk assessment and treatment planning depend on...
arXiv:2604.19609v2 Announce Type: replace Abstract: Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong dom...
arXiv:2604.00313v3 Announce Type: replace Abstract: Underwater image classification is constrained by the cost of annotation and by the computational and methodological requirements of task-specific...