Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2606. 04364v1 Announce Type: cross Abstract: Concept bottleneck models (CBMs) predict a layer of human-named attributes before predicting a class, which makes their decisions auditable.
arXiv:2606. 04409v1 Announce Type: cross Abstract: Modern deep neural networks usually have large parameter scales and nonlinear hierarchical structures, and they have achieved strong performance in computer vision.
arXiv:2602. 07253v3 Announce Type: replace Abstract: Detecting hallucinations in large language models is a critical open problem with significant implications for safety and reliability.
arXiv:2606. 03564v2 Announce Type: replace-cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning.
arXiv:2606. 04684v1 Announce Type: cross Abstract: The real-time hardships of video processing seriously limit the usage of Automatic License Plate Recognition (ALPR) with application in dynamic traffic monitoring settings.
arXiv:2606. 05116v1 Announce Type: new Abstract: We introduce the Graph Set Transformer (GST), a neural network architecture for learning on sets of graphs, designed for tasks in which per-element predictions depend on set-wide context as well as local structure.
arXiv:2606. 05115v1 Announce Type: cross Abstract: Children learn the meanings of words from a continuous, temporally structured stream of egocentric experience.
arXiv:2606. 04772v1 Announce Type: cross Abstract: Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience.
arXiv:2606. 04705v1 Announce Type: cross Abstract: Semantic segmentation in medical imaging is a critical yet challenging task due to data scarcity and high variability across modalities.
arXiv:2606. 04365v1 Announce Type: cross Abstract: Radiology reports describe kidney lesions by type, size, enhancement, and attenuation, yet existing 3D methods predict only at the patient or organ level.
arXiv:2606. 04345v1 Announce Type: cross Abstract: This paper presents HYolo, an intelligent IoT-based object detection framework that integrates hypergraph learning into the YOLO architecture.
arXiv:2605. 13672v1 Announce Type: cross Abstract: Few-shot classification (FSC) is widely used for learning from limited labeled data, yet most evaluations implicitly assume that target concepts are independent of contextual cues.
arXiv:2606. 05149v1 Announce Type: cross Abstract: Vehicle body type is a significant determinant of cyclist injury severity in overtaking crashes, yet automated tools for classifying vehicles into injury-risk-relevant categories from naturalistic roadway video do not exist in the open literature.
arXiv:2604. 25649v2 Announce Type: replace Abstract: Deep learning models are used in critical applications, in which mistakes can have serious consequences.
arXiv:2510. 03511v3 Announce Type: replace-cross Abstract: While widespread, Transformers lack inductive biases for geometric symmetries common in science and computer vision.
arXiv:2602. 06883v3 Announce Type: replace Abstract: The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness.
arXiv:2606. 04820v1 Announce Type: cross Abstract: CutMix has become the de facto standard mixing augmentation, yet its label assignment rests on a flawed assumption: The area of the pasted patch faithfully reflects its semantic contribution to the mixed image.
arXiv:2606. 04266v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are used in a variety of real-world applications including, for example, image classification and speech recognition.
arXiv:2511. 18454v3 Announce Type: replace-cross Abstract: Embryo fragmentation is a morphological indicator critical for evaluating developmental potential in In Vitro Fertilization (IVF).
arXiv:2606. 04656v1 Announce Type: cross Abstract: Object detection is a safety-critical component of autonomous driving.