Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
Commercial greenhouse cucumber production is graded by fruit length, which drives harvest scheduling, labour allocation, and logistics. Manual measurement with thread or caliper is accurate but infeasible at commercial scale.
Accurate segmentation of subcortical regions is critical for neurosurgical planning and functional research. Most automated methods rely on template space coregistration, which may compromise patient-specific accuracy, particularly in small structures.
Enterprise Document Intelligence [Vol. 1 #5quinquies] - Same 1974 scanned PDF, two engines.
arXiv:2506. 01678v2 Announce Type: replace-cross Abstract: Scanning tunnelling microscopy (STM) is a powerful technique for imaging surfaces with atomic resolution, providing insight into physical and chemical processes at the level of single atoms and molecules.
arXiv:2606. 19824v1 Announce Type: cross Abstract: Accurate segmentation of thin, tortuous anatomical structures, such as retinal vessels, cerebral vasculature, and facial wrinkles, remains challenging due to low contrast, frequent discontinuities, and severe class imbalance.
arXiv:2603. 09420v3 Announce Type: replace-cross Abstract: Motion forecasting enables autonomous vehicles to anticipate scene evolution by predicting the future trajectories of dynamic agents.
arXiv:2603. 15106v2 Announce Type: replace Abstract: Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requires DNN architectures to be specialized for each device separately.
arXiv:2606. 19938v1 Announce Type: cross Abstract: We propose triangular consistency as a first-principled constraint for optical flow, which is agnostic to network architecture, supervision type, and dataset, and applies to both image-pair and multi-frame settings.
arXiv:2606. 19676v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation and editing.
arXiv:2606. 20189v1 Announce Type: cross Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD).
arXiv:2502. 03227v2 Announce Type: replace Abstract: Minimally redundant representations are typically learned by minimizing feature covariance.
arXiv:2604. 13240v2 Announce Type: replace-cross Abstract: Mapping the spatial distribution of species is essential for conservation policy and invasive species management.
arXiv:2606. 20264v1 Announce Type: new Abstract: Student-generated drawings are widely used in science education to assess learners' conceptual understanding in modeling-based tasks aligned with the Next Generation Science Standards (NGSS).
arXiv:2606. 20035v1 Announce Type: cross Abstract: Many dense prediction networks rely on additive feature transformations and model higher-order feature interactions only implicitly.
arXiv:2606. 20115v1 Announce Type: new Abstract: Conformal risk control (CRC) provides distribution-free guarantees on segmentation quality by calibrating a prediction-set threshold on held-out data.
arXiv:2606. 19451v1 Announce Type: new Abstract: We introduce 3D-DLP, a self-supervised object-centric representation learning model that decomposes scene-level RGB-D or voxel observations into a set of 3D latent particles.
arXiv:2606. 19733v1 Announce Type: cross Abstract: Efficiently retrieving specific 3D instances from large-scale scenes via natural language prompts remains a formidable challenge in multimedia analysis.
arXiv:2606. 19782v1 Announce Type: new Abstract: Financial chart question answering in regulated settings demands more than accuracy: practitioners must know which answers to trust before acting on them, and many institutions cannot send client data to external model providers.
arXiv:2606. 19934v1 Announce Type: cross Abstract: Current machine learning models commonly require large and well-annotated datasets.
arXiv:2606. 20559v1 Announce Type: cross Abstract: Egocentric video understanding is inherently limited by the narrow perspective of wearable cameras: a single viewpoint, a single modality, a single model cannot capture the full richness of human action.