Tag: Computer Vision

Researchers have developed DELTA, an unsupervised domain adaptation model that combines a grouped divergence attention module with self-paced deep clustering ...

A fine-tuned three-billion-parameter vision-language model learned to halt all traffic at simulated intersections when pedestrians were in danger, cutting their ...

Researchers have developed a transformer-based framework with local-global attention that identifies writers from scanned handwriting without reading the text, achieving ...

Researchers in India have developed CAT-Net, a hybrid deep learning model combining convolutional networks, coordinate attention, and Transformer encoders to ...

Researchers combined YOLOv8s and Pix2Pix with ant colony and particle swarm optimization to stabilize wrinkle detection and realistic cosmetic skin ...

Researchers in China have developed an unsupervised tensor decomposition algorithm that detects subtle, low-contrast fabric defects while keeping false alarms ...

Researchers have developed a multiobject tracking framework combining a nonlinear adaptive Kalman filter, multi-scale appearance enhancement, and trajectory stitching that ...

Researchers have introduced Light-wDEF, a resource-efficient and fully reproducible framework that enabled a fair comparison of ten visual deepfake detectors ...

Researchers have built a modular AI pipeline that indexes hours of video and retrieves specific people from text, image, or ...

Researchers in China have developed HA-DETR, a transformer-based detector that adaptively enhances features at different semantic levels to overcome blur, ...

Researchers have developed DPAS-Net, a deep learning framework that maintains remarkably accurate multi-view clustering even when up to 90 percent ...

Researchers have developed a memory-augmented CNN-vision transformer autoencoder that uses Farneback optical flow to detect anomalies in surveillance video with ...

Researchers have developed FUS-DETR, a transformer-based AI detector that achieves state-of-the-art accuracy in spotting small drones against cluttered backgrounds in ...

A new prediction-based neural network called RMTA-Net combines recurrent temporal processing, learnable memory banks, and adaptive attention to detect video ...

Researchers compared seven convolutional neural network architectures for detecting diseases and pests in star fruit and found that the classic ...

Researchers have developed LMANet, a lightweight multiscale attention network that achieves high-accuracy skin-lesion segmentation with only 5.6 million parameters by ...

Researchers in Chongqing have developed a wavelet-guided deep learning framework that coordinates frequency-domain and spatial cues to sharply localize changes ...

Researchers at Hohai University have developed ShuffleNet-MSAA, a lightweight AI system that uses adaptive attention and sonar imaging to detect ...

Researchers have built a drone perception framework that pairs an enhanced YOLOv7 detector with graph attention network reasoning and spatial ...

Researchers have developed AttentiveGaze, a real-time multimodal AI framework that fuses face, eye, and head pose cues with attention mechanisms ...