Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2607. 06918v1 Announce Type: cross Abstract: Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for diverse downstream tasks.
arXiv:2607. 07083v1 Announce Type: cross Abstract: Subsampling significantly reduces the number of measurements, thereby streamlining data processing and transfer overhead, and shortening acquisition time across diverse real-world applications.
arXiv:2509. 21160v2 Announce Type: replace-cross Abstract: With the growing use of large language models, concerns over content authenticity have spurred a variety of watermarking schemes.
arXiv:2607. 06585v1 Announce Type: cross Abstract: Plant diseases, resulting from both biotic and abiotic stresses, cause an estimated 20-40% loss in global agricultural yield annually, resulting in economic damages exceeding USD 220 billion.
Unsupervised constituency parsing aims to accurately induce latent tree structures from raw text alone. Recent neural parameterizations of PCFGs achieve strong performance in both supervised and unsupervised parsing, yet rely on high-capacity black-box networks for rule scoring -- as exemplified by the Neural PCFG family -- leaving rule probabilities without an interpretable mathematical form.
We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarcity of faithfully annotated parsing corpora. Our contributions are threefold.
Automated crowd counting in Hajj video is difficult not because current models lack capacity, but because the footage violates the assumptions those models were built on: cameras observe the crowd from steep, near-vertical angles, individuals occlude one another extensively, and a single frame can contain well over a thousand people. Benchmarks that test crowd counting in such an environment are either private or not detailed per second.
Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage.
The precise pixel-level localization of 2D material flakes is crucial for high-throughput screening. However, traditional fully supervised methods rely on dense annotations, which are costly and time-consuming, severely limiting the practical deployment of segmentation models.
Medical image segmentation models can achieve strong benchmark performance while remaining sensitive to scanner, protocol, and institutional variation. These context shifts alter image appearance without changing the underlying lesion, allowing models to exploit nuisance cues that Dice and HD95 fail to expose.
Recent advances in semi-supervised medical image segmentation have achieved remarkable performance through prediction consistency, pseudo-label supervision, and hard-region supervision. However, these methods primarily improve supervision quality rather than explicitly enforcing semantic consistency in the learned representations of hard regions.
Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks. However, the prohibitive computational cost of CNNs hinders the deployment of CNNs onto resource-constrained embedded devices.
arXiv:2602. 10045v2 Announce Type: replace-cross Abstract: Current instance segmentation models achieve high performance on average predictions, but lack principled uncertainty quantification: their outputs are not calibrated, and there is no guarantee that a predicted mask is close to the ground truth.
arXiv:2312. 08230v2 Announce Type: replace-cross Abstract: Detecting partial extrinsic symmetry in 3D geometry is a fundamental yet persistent challenge in computer vision and graphics, critical for tasks ranging from shape completion to procedural generation.
arXiv:2601. 15275v3 Announce Type: replace-cross Abstract: We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant attention with multi-frequency similarity, and can adapt to the geometry of the underlying 3D scene.
arXiv:2607. 05908v1 Announce Type: new Abstract: Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine learning systems.
arXiv:2603. 04024v2 Announce Type: replace-cross Abstract: Ambiguous 3D medical image segmentation often involves boundaries where different expert delineations are non-identical yet clinically plausible.
arXiv:2607. 05691v1 Announce Type: cross Abstract: Every chemical language model reading SMILES begins with a tokenizer, yet the field has inherited byte-pair encoding (BPE) from natural language with little scrutiny.
arXiv:2607. 06309v1 Announce Type: cross Abstract: Accurate breast cancer classification from mammography requires effective integration of complementary information from craniocaudal (CC) and mediolateral oblique (MLO) views, which provide a more complete characterization of breast abnormalities.
arXiv:2607. 05798v1 Announce Type: cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception to interleaved visual-language reasoning, often referred to as ``thinking with images''.