Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2607. 13468v1 Announce Type: cross Abstract: Recently, a line of works can generate impressive 3D objects from a single image, but they are limited by restricted representation resolution, making them unsuitable for 3D scene generation.
arXiv:2607. 13237v1 Announce Type: cross Abstract: Precise spatial-temporal annotation of laparoscopic videos is time-consuming and requires expert knowledge.
arXiv:2607. 13432v1 Announce Type: new Abstract: Plasticity -- a neural network's ability to adapt to new tasks -- is critical for continual and transfer learning.
arXiv:2607. 09776v2 Announce Type: replace-cross Abstract: When adapting Vision Language Action (VLA) models to downstream tasks, multiple rounds of post-training are often required to progressively address policy weaknesses.
arXiv:2607. 14041v1 Announce Type: cross Abstract: Historical Manchu OCR must accommodate various visually distinct writing styles, including regular script, running script, and the semi-cursive chancery hand used in palace memorials, despite limited labeled data.
Region-based loss functions, such as the Dice loss, have established themselves as the de facto standard for highly class- and region-imbalanced segmentation tasks. However, models trained using region-based loss functions are notoriously miscalibrated and typically yield over-confident predictions.
Multi-object detection and tracking from noisy point clouds remain challenging in many data-scarce radar applications. Current Bayesian trackers based on Poisson measurement models offer a training-free solution but struggle to achieve accuracy and efficiency under severe clutter, large object populations, and full-resolution Doppler point clouds.
In recent years, there has been growing interest in robust robotic systems for precise bin-picking applications. To achieve reliable performance, such systems must address errors arising from both the object pose estimation and the grasping process.
Active surveillance (AS) is the preferred strategy for favorable-risk prostate cancer, yet current protocols rely on scheduled repeat biopsies, most of which reveal no progression and are unnecessary. Existing risk-stratification tools operate on single time-point imaging or depend on explicit lesion segmentation, limiting their ability to capture longitudinal change and excluding patients without an MRI-visible lesion.
arXiv:2607. 12065v1 Announce Type: cross Abstract: While visual navigation has been extensively studied in agricultural robotics, most existing systems assume daytime conditions.
arXiv:2607. 11962v1 Announce Type: cross Abstract: Self-supervised learning offers a compelling approach for medical imaging, where labeled data are scarce and acquisition costs are high.
arXiv:2507. 15833v3 Announce Type: replace-cross Abstract: Human vision is a highly active process driven by gaze, which directs attention to task-relevant regions through foveation, dramatically reducing visual processing.
arXiv:2607. 12376v1 Announce Type: cross Abstract: Causal inference using front door intervention and multi-instance learning (MIL) has advanced the analysis of Whole Slide Images (WSI) in digital pathology.
arXiv:2603. 28583v2 Announce Type: replace-cross Abstract: Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations.
arXiv:2602. 16918v2 Announce Type: replace-cross Abstract: We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data.
arXiv:2602. 07008v3 Announce Type: replace-cross Abstract: Reliable models should not only predict correctly, but also justify decisions with acceptable evidence.
arXiv:2409. 16808v3 Announce Type: replace-cross Abstract: Modern applications such as autonomous vehicles, intelligent surveillance, and smart city systems increasingly require object detection on resource-constrained edge devices.
arXiv:2607. 12438v1 Announce Type: new Abstract: Deep networks trained with label noise often learn clean structure before memorizing corrupted labels.
arXiv:2607. 12833v1 Announce Type: cross Abstract: Circular data, representing angles or directions, are frequently encountered in computer vision, biology, geology, and meteorology.
arXiv:2607. 12175v1 Announce Type: cross Abstract: X-ray tomography enables nondestructive characterization of material microstructures, while advances in micro-CT imaging have accelerated volumetric data acquisition and reconstruction.