YOLO11X
PulseAugur coverage of YOLO11X — every cluster mentioning YOLO11X across labs, papers, and developer communities, ranked by signal.
-
New pipeline detects traffic accidents using vision-language models
Researchers have developed a novel pipeline for detecting traffic accidents in video footage without requiring labeled training data. This system, named ACCIDENT @ CVPR, utilizes a coarse-to-fine approach that combines …
-
Geometry-first 3D tracking outperforms depth estimation in Sim2Real challenges
A new research paper proposes a geometry-first approach for multi-camera 3D tracking in large indoor warehouses, outperforming methods that rely on estimated depth. The study, submitted to arXiv, found that a pipeline u…
-
Smaller AI models outperform larger ones in data-scarce scenarios, study finds
A new paper challenges the prevailing assumption that larger AI models are always superior, particularly in data-scarce environments like Earth observation. The research found that smaller models, such as YOLO11N, can a…