相关论文: Cross-Lingual and Cross-Cultural Variation in Imag…

The use of explicit object detectors as an intermediate step to image captioning - which used to constitute an essential stage in early work - is often bypassed in the currently dominant end-to-end approaches, where the language model is…

Topic models aim to reveal latent structures within a corpus of text, typically through the use of term-frequency statistics over bag-of-words representations from documents. In recent years, conceptual entities -- interpretable,…

This paper discusses and demonstrates the outcomes from our experimentation on Image Captioning. Image captioning is a much more involved task than image recognition or classification, because of the additional challenge of recognizing the…

How does word frequency in pre-training data affect the behavior of similarity metrics in contextualized BERT embeddings? Are there systematic ways in which some word relationships are exaggerated or understated? In this work, we explore…

Vision-Language Models (VLMs) have demonstrated impressive capabilities across a range of tasks, yet concerns about their potential biases exist. This work investigates the extent to which prominent VLMs exhibit cultural biases by…

We study how persona prompting shapes language generated by multimodal large language models in an urban perception setting. Using 59,808 annotations from 1,200 persona-conditioned agents and two no-persona settings, we analyze captions,…

Emotion estimation in images is a challenging task, typically using computer vision methods to directly estimate people's emotions using face, body pose and contextual cues. In this paper, we explore whether Large Language Models (LLMs) can…

Language universals have long been attributed to an innate Universal Grammar. An alternative explanation states that linguistic universals emerged independently in every language in response to shared cognitive or perceptual biases. A…

In this paper, we pose the question: do people talk about women and men in different ways? We introduce two datasets and a novel integration of approaches for automatically inferring gender associations from language, discovering coherent…

State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model represents…

Latent semantic similarity (LSS) is a measure of the similarity of information exchanges in a conversation. Challenging the assumption that higher LSS bears more positive psychological meaning, we propose that this association might depend…

Multi-modal learning, particularly among imaging and linguistic modalities, has made amazing strides in many high-level fundamental visual understanding problems, ranging from language grounding to dense event captioning. However, much of…

Automatic recognition of emotion from facial expressions is an intense area of research, with a potentially long list of important application. Yet, the study of emotion requires knowing which facial expressions are used within and across…

The internet has been blurring the lines between local and global cultures, affecting in different ways the perception of people about themselves and others. In the global context of the internet, search engine platforms are a key mediator…

In this paper, we investigate a novel problem of telling the difference between image pairs in natural language. Compared to previous approaches for single image captioning, it is challenging to fetch linguistic representation from two…

Recent advances in vision-language models (VLMs) have improved image captioning for cultural heritage. However, inferring structured cultural metadata (e.g., creator, origin, period) from visual input remains underexplored. We introduce a…

The success of multilingual pre-trained models is underpinned by their ability to learn representations shared by multiple languages even in absence of any explicit supervision. However, it remains unclear how these models learn to…

When we experience a visual stimulus as beautiful, how much of that experience derives from perceptual computations we cannot describe versus conceptual knowledge we can readily translate into natural language? Disentangling perception from…

Product images (e.g., a phone) can be used to elicit a diverse set of consumer-reported features expressed through language, including surface-level perceptual attributes (e.g., "white") and more complex ones, like perceived utility (e.g.,…

Contextual influences on language often exhibit substantial cross-lingual regularities; for example, we are more verbose in situations that require finer distinctions. However, these regularities are sometimes obscured by semantic and…