Computer Vision news and analysis on Web Pulse: 3345 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers propose PhysFlood, a physics-aware masked diffusion-based simulation system that generates realistic flood images from a single fisheye lens photo, addressing the shortage of flood data for urban disaster det…
A new method called Object-Part Hierarchical Reflective Grounding (OP-HRG) improves part-level visual grounding in multimodal large language models by introducing a coarse-to-fine reasoning pipeline that first localizes …
A new study comparing handcrafted feature descriptors and convolutional neural networks (CNNs) for facial expression recognition finds that CNNs achieve the best overall performance across three datasets (FER-2013, CK+, …
Researchers introduced DrawingVQA, the first benchmark for evaluating multimodal large language models (MLLMs) on real-world construction drawings, featuring 33 'Issued for Construction' drawings and 92 expert-curated qu…
A new study from arXiv finds that test-time adaptation (TTA) can improve zero-shot 3D CT vision-language models only under specific conditions, and introduces CARVE (Cardinality-Aware Retained-View Entropy) as the first …
A pre-training Partial Information Decomposition framework that ranks multi-contrast 3D MRI input pairs by their redundant, unique, and synergistic information about regional tumor burden selected T1c+T2-FLAIR as the opt…
Researchers introduce SLAPBench, the first benchmark for evaluating multimodal large language models (MLLMs) on four-finger SLAP fingerprint verification, built from NIST SD302b with 7,832 pairs. Under similarity-scoring…
A study comparing deep learning architectures for sleep apnea detection from EEG signals achieved a best test AUC of 0.750 using a Vision Transformer trained on topological data analysis features, tested on 575 pediatric…
A new framework called Epipolar Distillation (EpiDistill) transfers scale-aware geometric priors from multi-view models into monocular depth foundation models, significantly improving zero-shot metric depth estimation on…
A new study from arXiv reveals that video pretrained backbones underperform on AI-generated video detection due to excessive spatiotemporal aggregation in their readout layers, which suppresses local temporal dynamics. T…
A new closed-loop AutoML framework using GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers achieves mean test accuracies above 93% and a best accuracy of 98.1% for cross-lingual handwritten O…
Researchers have adapted LIME, a popular perturbation-based XAI method, to use generative inpainting for creating photorealistic perturbed image samples, improving explanation quality by avoiding unrealistic out-of-distr…
A new benchmark from researchers at arXiv shows that token reduction can cut computational cost by up to 29% and boost throughput by 44% in visual place recognition (VPR) models based on vision transformers, with less th…
Researchers introduced MAR-12, a framework using Vision Language Models (VLMs) to detect and explain harmful humor in memes, achieving up to 80.3% accuracy for humor detection and 75.9% for hate detection on the PrideMM …
A lifetime family license to VideoProc Converter AI for Windows, normally $119.90, is available for $29.97 through midnight tonight, according to Boing Boing. The AI-powered tool can transform old, blurry videos in just …
Birdfy's midyear sale takes up to 40 percent off its smart bird feeders, with the Birdfy Feeder AI-Powered Smart Bird Feeder with Camera dropping to $149.99 at Birdfy, its second-best price to date. The bundle includes a…
A new benchmark called RadLE 2.0 reveals that many AI models in radiology deliver incorrect findings with full confidence, while human radiologists still outperform them. The benchmark tests whether AI can recognize when…
Developer of the iOS app PictureFramer added AI-powered reflection removal for museum photos, enforcing a hard invariant that every pixel outside the user's mask remains bit-identical to the original. The feature support…
A new open-source project demonstrates how multimodal vector search works under the hood, using OpenAI CLIP (ViT-B/32) to embed text and images into a 512-dimensional vector space and Qdrant (HNSW indexing) for similarit…
Visual prompting is the deliberate design of visual context to steer a model's attention, constrain its hypothesis space, improve grounding, and shape downstream reasoning, representing a change in the interaction paradi…