52+ min ago   (394+ words) Unmanned aerial vehicle (UAV) inspection of transmission towers requires joint analysis of corridor geometry, tower components, and localized defects, whereas available datasets provide incompatible annotations at different scales. Tower-HMT is a hierarchical multitask network that shares a ConvNeXt-Tiny encoder and…...

1+ day, 19+ min ago   (445+ words) Automated essay scoring models trained on imbalanced examination data often compress predictions toward the score mean, disproportionately harming low-proficiency responses. We investigate whether synthetic tail data can mitigate this failure in Chinese second-language writing assessment. Using 10,067 HSK writing samples, we…...

1+ day, 5+ hour ago   (319+ words) Existing scientific text representation methods based on contrastive learning typically adopt a binary classification paradigm of positive and negative samples, which struggles to capture the complex, hierarchical semantic similarity relationships inherent in scientific texts. To address this, we propose SciRep,…...

1+ day, 5+ hour ago   (449+ words) Scalable classroom process evidence can support teacher reflection and expert review, but manual observation is labor-intensive and direct eye tracking is often too intrusive for routine classroom use. This paper presents a single-camera classroom video analytics system that converts ordinary…...

3+ day, 3+ hour ago   (486+ words) Federated learning relies on aggregation schemes that assume all participants train models with identical architectures and a common parameter initialization. While this enables parameter-averaging strategies such as Federated Averaging, it also imposes a strong inductive bias by constraining local models…...

3+ day, 3+ hour ago   (370+ words) With the rapid development of intelligent teaching technologies, automatic classroom behavior detection can provide objective visual evidence for classroom participation analysis and teaching feedback. However, real classroom scenes commonly involve dense student distributions, large scale variations between front and rear…...

3+ day, 4+ hour ago   (447+ words) Interest changes complicate sequential recommendation when interaction histories are combined with item content. We evaluate MM-DRLSR on four public Amazon and Yelp benchmarks. The model integrates category-overlap drift supervision, history-derived drift representations, lightweight identifier–image–text fusion, candidate-conditioned scoring, and…...

3+ day, 5+ hour ago   (425+ words) Point cloud semantic segmentation is fundamental for 3D scene understanding and has been widely used in autonomous driving and infrastructure inspection applications. However, its performance is often limited by insufficient representation of local geometric structures and the high cost of point-wise…...

4+ day, 1+ hour ago   (428+ words) Artificial intelligence (AI) has become a key driver of transformation in educational contexts, influencing both teaching and learning processes as well as the digital competencies required by teachers and students. In this context, understanding how AI is perceived, used, and…...

4+ day, 6+ hour ago   (373+ words) Vocabulary integration is an effective approach for improving named entity recognition performance. However, existing methods exhibit insufficient decoupling capability in modeling the position and content between characters and words, and under static matching mechanisms, models tend to memorize fixed character…...