From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

We propose to use the visual denotations of linguistic expressions (i.e. the set of images they describe) to define novel denotational similarity metrics, which we show to be at least as beneficial as distributional similarities for two tasks that require semantic inference. To compute these denotational similarities, we construct a denotation graph, i.e. a subsumption hierarchy over constituents and their denotations, based on a large corpus of 30K images and 150K descriptive captions.

Last synced 2026-08-22 14:19 UTC

• Fusion-Enhanced Bidirectional Multimodal Entity Linking Model

  Engineering Applications of Artificial Intelligence 2026 · 0 citations

• A unified framework for early childhood image captioning via knowledge-grounded metrics and process-level reinforcement

  Engineering Applications of Artificial Intelligence 2026 · 0 citations

• ISAR-Mamba: A Dual-Stream Gated Mamba with Hierarchical Spatial Summaries for ISAR Image Captioning

  Sensors 2026 · 0 citations

• VQA-LLM Fusion Caption Generator: An integrated framework for informative vision-and-language generation

  Journal of Visual Communication and Image Representation 2026 · 0 citations

• Beyond pairwise alignment: Hypergraph-based semantic calibration for image-text matching

  Information Processing & Management 2026 · 0 citations

• VLGRA: Visual-Language Semantic Optimization and Graph Reasoning for cross-modal retrieval

  Information Processing & Management 2026 · 0 citations

• CLS-Guided Multimodal Fusion for Image Captioning with LSTM and T5 Decoders

  Applied Sciences 2026 · 0 citations