Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2609.16785v1 Announce Type: new Abstract: Zero-shot anomaly detection aims to localize anomalies without target-domain samples. Existing CLIP-based methods suffer from coarse anomaly maps and l...
arXiv:2609.13677v1 Announce Type: cross Abstract: Modern real application problems involve matrix-valued parameters, yet conventional optimizers treat them as vectors, thereby motivating matrix-aware...
arXiv:2609.16909v1 Announce Type: new Abstract: With the increasing deployment of deep neural networks in critical systems, such as medical diagnostics and autonomous vehicles, ensuring their interpr...
arXiv:2609.17509v1 Announce Type: cross Abstract: Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing comput...
NeuroSymbEAD is a large‑scale neuro‑symbolic caption dataset that builds an ego‑centric knowledge graph of static and dynamic objects on the KITTI‑360 dataset, annotating classes, categories, heading directions, orientations, and distances from the ego‑vehicle. The dataset generates multilevel textual captions that serve as a lightweight representation of an ego‑centric scene map, enabling outdoor scene‑map reconstruction, visual recognition, and object grounding. Baselines for driving common sense and traffic/scene understanding are established, and the dataset is benchmarked using pre‑trained grounding and learned auto‑regressive captioning networks to support vision‑language and foundation models for traffic‑scene explanation, 3D reasoning, and interpretable autonomous‑driving perception.
The paper introduces a method for extracting and matching vessel graphs from longitudinal angiographic images that improves temporal consistency. By performing an early matching step before refining the graphs—removing spurious bulges and merging junctions using joint information—the approach yields a higher matched area and reduces graph fragmentation compared to traditional separate or no refinement strategies. Experiments on complex retinal vessel graphs confirm these benefits.
arXiv:2609.16207v1 Announce Type: new Abstract: Spatial Transcriptomics (ST) has transformed biomedical research by enabling the spatial mapping of gene expression across tissue sections. However, hi...
arXiv:2609.17458v1 Announce Type: cross Abstract: Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering...
arXiv:2609.16365v1 Announce Type: cross Abstract: Real-world datasets often exhibit long-tailed class distributions, where a few head classes contain a large number of training samples while a large...
The paper presents a formal framework for majority‑minority learning tasks, demonstrating that standard gradient‑descent training can amplify bias by favoring majority groups and producing stereotypical predictors that ignore minority‑specific features. It identifies three key theoretical findings: the close proximity between full‑data and stereotypical predictors, the dominance of a region where training the entire model mainly captures majority traits, and a lower bound on the extra training needed to mitigate this effect. Experiments on deep learning for tabular and image classification illustrate these results.
arXiv:2608.06205v2 Announce Type: replace Abstract: Multispectral object detection combines visible and thermal imagery to improve perception under challenging illumination and environmental conditio...
arXiv:2609.09012v2 Announce Type: replace Abstract: Spherical observations provide global visual context for 3D scene understanding. However, visual information is encoded in an angular domain, where...
arXiv:2609.16448v1 Announce Type: cross Abstract: Breast histopathology analysis increasingly relies on distributed learning because direct data pooling across institutions is often restricted by pri...
The paper introduces FastFlowGS, a streaming 4D Gaussian Splatting method that reconstructs fast-moving subjects from a sparse set of external cameras, and Monaco4D, a photorealistic Unreal Engine 5 benchmark featuring Formula 1 sequences with dense ground truth. FastFlowGS combines sparse matches, semi-dense tracks, and dense optical flow using a Kalman-style temporal update, achieving significant performance gains over existing baselines on both CMU-Panoptic and Monaco4D datasets. The benchmark provides varied illumination and viewpoints from trackside, onboard, and drone cameras, enabling evaluation of high-speed outdoor reconstruction.
The paper evaluates optical‑flow based wingbeat counting on simulated Crazyflie vehicles using MuJoCo. Three temporal models—causal temporal convolution, leaky integrate‑and‑fire spiking, and causal self‑attention—were combined with a shared convolutional encoder and tested on 1,440 clips at 1.5 m and 3.0 m distances. Exact‑count accuracies ranged from 92.22 % to 96.67 %, with no significant differences between models, and the study highlights the need to report both total counts and event‑level timing.
arXiv:2505.15147v3 Announce Type: replace Abstract: Remote sensing images (RSIs) capture both natural and human-induced changes on the Earth's surface. Semantic segmentation (SS) of RSIs enables the...
arXiv:2609.16775v1 Announce Type: new Abstract: Annotating large radiology datasets is bottlenecked by the manual effort of delineating structures slice-by-slice in 3D volumes. Interactive methods re...
The study evaluates the use of frozen geospatial foundation embeddings (AlphaEarth) for mapping cultivated versus non‑cultivated land in Maine. Using 192 spatially separated patches and USDA Cropland Data Layer labels, a lightweight classifier achieved 93.7% overall accuracy without fine‑tuning, and a nearest‑class‑centroid rule reached 90.2%. A balanced sample of 60,000 labeled pixels was nearly as effective as the full 8.6 million‑pixel pool, and classifiers trained in one year remained accurate across 2018‑2023. In a blind human validation of 385 points, the AlphaEarth‑plus‑random‑forest map matched 95.3% of the consensus, outperforming the CDL reference (91.7%).
Reference labels used to train medical image classification models are not always as certain as they may appear, and this uncertainty has implications on performance metrics. In this study, we propose...
Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing computational costs. Dynamic frame rate codecs mitigate t...