Search

Monitoring the process is crucial for ensuring high quality in wood-based panel production. Interest in the distribution of resin in fibers and particles has increased during the last couple of decades. This study considered the potential to determine urea formaldehyde (UF) resin content in fiber mat using near-infrared (NIR) spectroscopy. Fiber mats with various resin contents were investigated with NIR combined with the partial least squares (PLS) regression and root mean square error of calibration and validation (RMSECV). The external factors, such as the distance between the fiber optic probe and the sample surface and light sources, were also evaluated. The results showed that this technique can sufficiently determine the resin content in the resinous fiber mat with accuracy of up to 95%. The light sources and the distances from the probe to the surface did not significantly influence the discrimination and prediction of resin content. Fundamental Research Funds for Central Public Welfare Research Institutes [CAFYBB2021ZJ001]; China National Natural Science Fund [31770766]; Program for Leading Talents of Science and Technology of Yunnan Province [2017HA013] Published version The authors acknowledge the financial support of the Fundamental Research Funds for Central Public Welfare Research Institutes (Grant No. CAFYBB2021ZJ001), the China National Natural Science Fund (Grant No. 31770766) and the Program for Leading Talents of Science and Technology of Yunnan Province (Grant No. 2017HA013).

We introduce VisoGender, a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related gender biases, inspired by Winograd and Winogender schemas, where each image is associated with a caption containing a pronoun relationship of subjects and objects in the scene. VisoGender is balanced by gender representation in professional roles, supporting bias evaluation in two ways: i) resolution bias, where we evaluate the difference between gender resolution accuracies for men and women and ii) retrieval bias, where we compare ratios of male and female professionals retrieved for a gender-neutral search query. We benchmark several state-of-the-art vision-language models and find that they lack the reasoning abilities to correctly resolve gender in complex scenes. While the direction and magnitude of gender bias depends on the task and the model being evaluated, captioning models generally are more accurate and less biased than CLIP-like models. Dataset and code are available at https://github.com/oxai/visogender, Comment: Data and code available at https://github.com/oxai/visogender