Image-text retrieval is a fundamental task to bridge the semantic gap between natural language and vision. Recent works primarily focus on aligning textual meanings with visual appearance. However, they often overlook the semantic discrepancy caused by syntactic structure in natural language expressions and relationships among visual entities. This oversight would lead to sub-optimal alignment and degraded retrieval performance, since the underlying semantic dependencies and object interactions remain inadequately encoded in both textual and visual embeddings. In this paper, we propose a novel Visual-Linguistic Dependency Encoding (VL-DE) framework, which explicitly models the dependency information among textual words and interaction patterns between image regions, improving the discriminative power of cross-modal representations for more accurate image-text retrieval. Specifically, VL-DE enhances textual representations by considering syntactic relationships and dependency types, and visual representations by attending to its spatially neighboring regions. Cross-attention mechanism is then introduced to aggregate aligned region-word pairs into image-text similarities. Analysis on Winoground, a dataset specially designed to measure vision-linguistic compositional structure reasoning, shows that VL-DE outperforms existing methods, demonstrating its effectiveness at this task. Comprehensive experiments on two benchmarks, Flickr30K and MS-COCO, further validates the competitiveness of our approach.

Although co-design between teacher and researcher as a means could effectively promote teachers’ professional development, little is known about the process of developing a simulation-based math classroom for compulsory education by a co-design team between teachers and researchers. From a dual theoretical perspective involving activity theory and boundary crossing, we investigate the contradictions that emerged between teaching and research activity systems, and the way to deal with the contradictions. The results showed three main contradictions: (1) theoretical ideas versus practical knowledge, (2) simulation-based versus traditional teaching design, and (3) generative interactions versus structured classroom culture. The contradictions were resolved to varying degrees through the efforts of participants who acted as brokers, mainly in terms of the process of perspective making and taking. These findings not only guide how to maximize learning opportunities for teachers in the co-design process with researchers but also enrich teacher education and activity theory.