Image-Text Matching is one major task in cross-modal information processing. The main
challenge is to learn the unified visual and textual representations. Previous methods that …

Image and sentence matching is a critical task to bridge the visual and textual discrepancy
due to the heterogeneous modalities. Great progress has been made by exploring the …

This paper presents Universal Vision-Language Dense Retrieval (UniVL-DR), which builds
a unified model for multi-modal retrieval. UniVL-DR encodes queries and multi-modality …

Visual reasoning is a special kind of visual question answering, which is essentially multi-
step and compositional, and also requires intensive text-visual interaction. The most …

Transformer architectures have recently been introduced into the field of visual question
answering (VQA), due to their powerful capabilities of information extraction and fusion …

Multi-modal hashing learns compact binary hash codes by collaborating heterogeneous
multi-modal features at both the model training and online retrieval stages to support large …

Recently, image-text matching has been intensively explored to bridge vision and language.
Previous methods explore an inter-modality relationship between an image-text pair from …

Commonsense reasoning based on knowledge graphs (KGs) is a challenging task that
requires predicting complex questions over the described textual contexts and relevant …

A convergência entre a relação humana e máquina está associada ao conceito de
inteligência híbrida, que tem despertado crescente interesse no meio acadêmico. Objetivo …

Topic detection based on text reasoning has attracted widespread attention. Existing
methods focus on inference based on textual semantic cues. However, each video is …