Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2606. 29484v1 Announce Type: cross Abstract: Modern deepfake detectors are rarely consumed as bare classifiers.
arXiv:2606. 30374v1 Announce Type: cross Abstract: Multimodal MRI is essential for accurate brain tumor segmentation.
arXiv:2606. 28724v1 Announce Type: cross Abstract: Understanding and localizing subtle changes between paired images is critical for tasks such as surveillance and image editing.
arXiv:2508. 02425v2 Announce Type: replace-cross Abstract: In physical human-robot collaboration (pHRC) settings, humans and robots collaborate directly in shared environments.
arXiv:2606. 29112v1 Announce Type: new Abstract: Deep learning, which in general relies on voluminous amounts of training data, is vulnerable to data poisoning attacks, including error-generic attacks and backdoors (Trojans).
arXiv:2603. 17863v2 Announce Type: replace-cross Abstract: Automating the development of machine learning algorithms has the potential to unlock new breakthroughs.
arXiv:2606. 29136v1 Announce Type: cross Abstract: Event cameras capture sparse brightness changes with high temporal resolution and high dynamic range, compensating for the deficiencies of the conventional RGB frames.
arXiv:2606. 28419v1 Announce Type: cross Abstract: Limited data availability, class imbalance, and domain variability remain major barriers to reliable medical image classification.
arXiv:2606. 28439v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are widely applied in Network-based Intrusion Detection System (NIDS) due to their high accuracy.
arXiv:2606. 29161v1 Announce Type: new Abstract: Predicting tandem mass spectra (MS/MS) from molecular structures represents a central task in analytical chemistry with direct relevance to clinical metabolomics, systems biology, and adjacent disciplines.
arXiv:2606. 29102v1 Announce Type: cross Abstract: Jointly learning to segment and classify medical images demands cross-task synergy, yet encoder-sharing architectures limit decoder reconstruction to task-private representations, permanently discarding the boundary cues and semantic priors each branch could supply to the other.
arXiv:2606. 28656v1 Announce Type: cross Abstract: Deformable 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for rendering dynamic scenes in a wide range of 3D applications.
arXiv:2606. 29723v1 Announce Type: new Abstract: Continuous physical fields represent a large fraction of data under scientific investigation.
arXiv:2606. 29085v1 Announce Type: cross Abstract: The carbonized papyri from Herculaneum preserve the only large-scale library to survive from classical antiquity, but many unopened rolls remain unread because physical opening risks irreversible damage.
arXiv:2606. 30049v1 Announce Type: cross Abstract: Visibility distance is critical to maritime navigational safety because it determines the effective observation range of shipborne and shore-based monitoring systems.
3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view settings due to insufficient geometric constraints. While recent methods introduce monocular depth priors to mitigate this, they inherently struggle with scale ambiguity and cross-view inconsistency, leading to defective geometry.
As real-world prediction systems often face missing modalities at inference, incomplete multimodal learning (IML) remains a practical challenge. While prior methods aim to learn representations robust to missing inputs, representations from incomplete modalities inevitably deviate from their full-modality counterparts due to missing evidence.
RECIST diameter measurements are widely used for tumor response assessment, but they provide only a limited 2D description of lesion extent. We present LETT-NeXt, a lightweight RECIST-guided model that predicts 3D lesion masks from CT volumes and RECIST markers for the CVPR 2026 Foundation Models for Pan-cancer Segmentation in CT Images competition.
Metric feed-forward 3D reconstruction for panoramic data remains under-explored due to the lack of large-scale panoramic RGB-D training data. We present Realsee3D, a hybrid dataset of 10K indoor scenes (1K real, 9K synthetic) with 299K panoramic viewpoints and precise metric annotations, and Argus, a feed-forward network trained on it for metric panoramic 3D reconstruction.
Continual learning (CL), where a model is trained on a sequence of data tasks, is increasingly being adopted across key fields such as large language models and image recognition, yet it remains highly vulnerable to data poisoning that triggers learning divergence or severe excess risk. Despite these threats, a principled theoretical foundation in CL for understanding attack and defense remains lacking.