Image recognition, detection, and visual AI
![[2602.09678] Administrative Law's Fourth Settlement: AI and the Capability-Accountability Trap](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2602.09678: Administrative Law's Fourth Settlement: AI and the Capability-Accountability Trap
Abstract page for arXiv paper 2601.13622: CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language...
Abstract page for arXiv paper 2603.26551: Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones
The paper presents MiSCHiEF, a benchmark for evaluating fine-grained image-caption alignment, focusing on safety and cultural contexts, h...
The paper presents Video-TwG, a curriculum reinforced framework for improving long video understanding through selective video grounding ...
This article evaluates how data anonymization affects the performance of Content-Based Image Retrieval (CBIR) systems, highlighting the b...
The paper presents DM4CT, a benchmark for evaluating diffusion models in computed tomography (CT) reconstruction, addressing practical ch...
The paper explores the effectiveness of single versus multiple object annotation for flower recognition using various YOLO models, presen...
This paper presents a variational framework for optimizing anisotropic diffusion schedules in machine learning, enhancing performance acr...
Rodent-Bench introduces a benchmark for evaluating Multimodal Large Language Models (MLLMs) in annotating rodent behavior videos, reveali...
The paper presents VLANeXt, a framework for building effective Vision-Language-Action (VLA) models, addressing inconsistencies in trainin...
The paper presents JAEGER, a framework for joint 3D audio-visual grounding and reasoning, addressing limitations of existing 2D models by...
The paper presents Sketch2Feedback, a framework that enhances feedback on student-drawn STEM diagrams by integrating grammar rules to red...
This paper presents a computer vision framework for detecting and tracking players and the ball in soccer broadcast footage using a singl...
This article presents a framework for mapping 2D drawing annotations to 3D CAD features using context-aware reasoning, enhancing manufact...
The paper presents NI-Tex, a method for generating non-isometric garment textures using a new dataset and advanced techniques for cross-p...
This paper explores iterative feedback loops in image generative models, introducing the concept of neural resonance and its implications...
The paper introduces DEFNet, a multitask-based deep evidential fusion network designed to enhance blind image quality assessment (BIQA) b...
This article presents a novel approach to inverse lithography using generative reinforcement learning, significantly improving mask quali...
The paper introduces PCA-VAE, a novel approach to vector-quantized autoencoders that replaces traditional quantization methods with a dif...
This paper presents a computational framework that aligns human linguistic descriptions with visual perceptual data, enhancing understand...
The paper explores the Bayesian Lottery Ticket Hypothesis, demonstrating that sparse subnetworks in Bayesian neural networks can achieve ...
This paper investigates the alignment of representations from time series, vision, and language modalities, revealing insights into their...
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime