In the era of large-scale visual data, understanding collections of images is a challenging yet important task. To this end, we introduce ImageSet2Text, a novel method to automatically generate natural language descriptions of image sets. Based on large language models, visual-question answering chains, an external lexical graph, and CLIP-based verification, ImageSet2Text iteratively extracts key concepts from image subsets and organizes them into a structured concept graph. We conduct extensive experiments evaluating the quality of the generated descriptions in terms of accuracy, completeness, and user satisfaction. We also examine the method's behavior through ablation studies, scalability assessments, and failure analyses. Results demonstrate that ImageSet2Text combines data-driven AI and symbolic representations to reliably summarize large image collections for a wide range of applications.

Art and cultural heritage objects carry visual, textual, relational, and symbolic meaning that cannot be reduced to standard image understanding tasks. This tutorial presents computational methods for studying fine art and cultural artifacts, organized around three themes: relationality, meaning, and recognizability. We cover multimodal and graph-based representation learning for fine art analysis, knowledge-retrieval and agentic reasoning frameworks for artwork interpretation, and instance-level recognition in cultural heritage settings, as well as large-scale museum benchmarks and synthetic data generation strategies. Beyond these technical contributions, the tutorial foregrounds the cultural dimension of multimedia research, inviting discussion on current approaches for studying art and culture and directions for future research.

Gender bias in vision-language foundation models (VLMs) raises concerns about their safe deployment and is typically evaluated using benchmarks with gender annotations on real-world images. However, as these benchmarks often contain spurious correlations between gender and non-gender features, such as objects and backgrounds, we identify a critical oversight in gender bias evaluation: Do spurious features distort gender bias evaluation? To address this question, we systematically perturb non-gender features across four widely used benchmarks (COCO-gender, FACET, MIAP, and PHASE) and various VLMs to quantify their impact on bias evaluation. Our findings reveal that even minimal perturbations, such as masking just 10% of objects or weakly blurring backgrounds, can dramatically alter bias scores, shifting metrics by up to 175% in generative VLMs and 43% in CLIP variants. This suggests that current bias evaluations often reflect model responses to spurious features rather than gender bias, undermining their reliability. Since creating spurious feature-free benchmarks is fundamentally challenging, we recommend reporting bias metrics alongside feature-sensitivity measurements to enable a more reliable bias assessment.

Object detection in art is a valuable tool for the digital humanities, as it allows for faster identification of objects in artistic and historical images compared to humans. However, annotating such images poses significant challenges due to the need for specialized domain expertise. We present NADA (no annotations for detection in art), a pipeline that leverages diffusion models' art-related knowledge for object detection in paintings without the need for full bounding box supervision. Our method, which supports both weakly-supervised and zero-shot scenarios and does not require any fine-tuning of its pretrained components, consists of a class proposer based on large vision-language models and a class-conditioned detector based on Stable Diffusion. NADA is evaluated on two artwork datasets, ArtDL 2.0 and IconArt, outperforming prior work in weakly-supervised detection, while being the first work for zero-shot object detection in art. Code is available at https://github.com/patrick-john-ramos/nada

Abstract The use of AI systems for managing large-scale cultural heritage artifacts has become possible due to the rise of digitization. To classify such content, machine learning is typically used, where contextual information is important to structure the data. One way to capture context is through a knowledge graph. In this study, we propose a newd graph neural networks, we can improve artwork classification by utilizing the relationships between entities of the knowledge graph. Our experiments demonstrate that this approach achieves state-of-the-art results on multiple classification tasks across three datasets (SemArt paintings, Buddha statues, and Ukiyo-e woodblock prints). Moreover, our approach is effective in dealing with unbalanced data and we explore the use of both graph attention mechanisms and focal loss functions.

Several studies have raised awareness about social biases in image generative models, demonstrating their predisposition towards stereotypes and imbalances. This paper contributes to this growing body of research by introducing an evaluation protocol that analyzes the impact of gender indicators at every step of the generation process on Stable Diffusion images. Leveraging insights from prior work, we explore how gender indicators not only affect gender presentation but also the representation of objects and layouts within the generated images. Our findings include the existence of differences in the depiction of objects, such as instruments tailored for specific genders, and shifts in overall layouts. We also reveal that neutral prompts tend to produce images more aligned with masculine prompts than their feminine counterparts. We further explore where bias originates through representational disparities and how it manifests in the images via prompt-image dependencies, and provide recommendations for developers and users to mitigate potential bias in image generation.

Multiple-choice questions (MCQs) are widely used in the evaluation of large language models (LLMs) due to their simplicity and efficiency. However, there are concerns about whether MCQs can truly measure LLM’s capabilities, particularly in knowledge-intensive scenarios where long-form generation (LFG) answers are required. The misalignment between the task and the evaluation method demands a thoughtful analysis of MCQ’s efficacy, which we undertake in this paper by evaluating nine LLMs on four question-answering (QA) datasets in two languages: Chinese and English. We identify a significant issue: LLMs exhibit an order sensitivity in bilingual MCQs, favoring answers located at specific positions, i.e., the first position. We further quantify the gap between MCQs and long-form generation questions (LFGQs) by comparing their direct outputs, token logits, and embeddings. Our results reveal a relatively low correlation between answers from MCQs and LFGQs for identical questions. Additionally, we propose two methods to quantify the consistency and confidence of LLMs’ output, which can be generalized to other QA evaluation benchmarks. Notably, our analysis challenges the idea that the higher the consistency, the greater the accuracy. We also find MCQs to be less reliable than LFGQs in terms of expected calibration error. Finally, the misalignment between MCQs and LFGQs is not only reflected in the evaluation performance but also in the embedding space. Our code and models can be accessed at https://github.com/Meetyou-AI-Lab/Can-MC-Evaluate-LLMs.

We investigate the impact of deep generative models on potential social biases in upcoming computer vision mod-els. As the internet witnesses an increasing influx of AI-generated images, concerns arise regarding inherent biases that may accompany them, potentially leading to the dis-semination of harmful content. This paper explores whether a detrimental feedback loop, resulting in bias amplification, would occur if generated images were used as the training data for future models. We conduct simulations by progressively substituting original images in COCO and CC3M datasets with images generated through Stable Dif-fusion. The modified datasets are used to train OpenCLIP and image captioning models, which we evaluate in terms of quality and bias. Contrary to expectations, our findings indicate that introducing generated images during training does not uniformly amplify bias. Instead, instances of bias mitigation across specific tasks are observed. We further explore the factors that may influence these phenomena, such as artifacts in image generation (e.g., blurry faces) or pre-existing biases in the original datasets.

Multimodal human understanding and analysis are emerging research areas that cut through several disciplines like Computer Vision (CV), Natural Language Processing (NLP), Speech Processing, Human-Computer Interaction (HCI), and Multimedia. Several multimodal learning techniques have recently shown the benefit of combining multiple modalities in image-text, audio-visual and video representation learning and various downstream multimodal tasks. At the core, these methods focus on modelling the modalities and their complex interactions by using large amounts of data, different loss functions and deep neural network architectures. However, for many Web and Social media applications, there is the need to model the human, including the understanding of human behaviour and perception. For this, it becomes important to consider interdisciplinary approaches, including social sciences and psychology. The core is understanding various cross-modal relations, quantifying bias such as social biases, and the applicability of models to real-world problems. Interdisciplinary theories such as semiotics or gestalt psychology can provide additional insights on perceptual understanding through signs and symbols across multiple modalities. In general, these theories provide a compelling view of multimodality and perception that can further expand computational research and multimedia applications on the Web and Social media.

We introduce an emotional stimuli retrieval task that targets extracting emotional regions that evoke people's emotions (i.e., emotional stimuli) in artworks. This task offers new challenges to the community because of the diversity of artwork styles and the subjectivity of emotions, which can be a suitable testbed for benchmarking the capability of the current neural networks to deal with human emotion. For this task, we construct a dataset called APOLO for quantifying emotional stimuli retrieval performance in artworks by crowd-sourcing pixel-level annotation of emotional stimuli. APOLO contains 6,781 emotional stimuli in 4,718 artworks for validation and testing. We also evaluate eight baseline methods, including a dedicated one, to show the difficulties of the task and the limitations of the current techniques through qualitative and quantitative experiments. Our data and methods are available in https://github.com/Tianwei3989/apolo.

In this companion paper, we provide the artifacts of the GOYA model for disentangling content and style in art paintings, as presented at ICMR2023. The scripts are written in Python.

Multimodal human understanding and analysis is an emerging research area that cuts through several disciplines like Computer Vision, Natural Language Processing (NLP), Speech Processing, Human-Computer Interaction, and Multimedia. Several multimodal learning techniques have recently shown the benefit of combining multiple modalities in image-text, audio-visual and video representation learning and various downstream multimodal tasks. At the core, these methods focus on modelling the modalities and their complex interactions by using large amounts of data, different loss functions and deep neural network architectures. However, for many Web and Social media applications, there is the need to model the human, including the understanding of human behaviour and perception. For this, it becomes important to consider interdisciplinary approaches, including social sciences, semiotics and psychology. The core is understanding various cross-modal relations, quantifying bias such as social biases, and the applicability of models to real-world problems. Interdisciplinary theories such as semiotics or gestalt psychology can provide additional insights and analysis on perceptual understanding through signs and symbols via multiple modalities. In general, these theories provide a compelling view of multimodality and perception that can further expand computational research and multimedia applications on the Web and Social media.

The increasing tendency to collect large and uncurated datasets to train vision-and-language models has raised concerns about fair representations. It is known that even small but manually annotated datasets, such as MSCOCO, are affected by societal bias. This problem, far from being solved, may be getting worse with data crawled from the Internet without much control. In addition, the lack of tools to analyze societal bias in big collections of images makes addressing the problem extremely challenging. Our first contribution is to annotate part of the Google Conceptual Captions dataset, widely used for training vision-and-language models, with four demographic and two contextual attributes. Our second contribution is to conduct a comprehensive analysis of the annotations, focusing on how different demographic groups are represented. Our last contribution lies in evaluating three prevailing vision-and-language tasks: image captioning, text-image CLIP embeddings, and text-to-image generation, showing that societal bias is a persistent problem in all of them. https://github.com/noagarcia/phase

Image captioning models are known to perpetuate and amplify harmful societal bias in the training set. In this work, we aim to mitigate such gender bias in image captioning models. While prior work has addressed this problem by forcing models to focus on people to reduce gender mis-classification, it conversely generates gender-stereotypical words at the expense of predicting the correct gender. From this observation, we hypothesize that there are two types of gender bias affecting image captioning models: 1) bias that exploits context to predict gender, and 2) bias in the probability of generating certain (often stereotypical) words because of gender. To mitigate both types of gender biases, we propose a framework, called LIBRA, that learns from synthetically biased samples to decrease both types of biases, correcting gender misclassification and changing gender-stereotypical words to more neutral ones.

The duality of content and style is inherent to the nature of art. For humans, these two elements are clearly different: content refers to the objects and concepts in the piece of art, and style to the way it is expressed. This duality poses an important challenge for computer vision. The visual appearance of objects and concepts is modulated by the style that may reflect the author’s emotions, social trends, artistic movement, etc., and their deep comprehension undoubtfully requires to handle both. A promising step towards a general paradigm for art analysis is to disentangle content and style, whereas relying on human annotations to cull a single aspect of artworks has limitations in learning semantic concepts and the visual appearance of paintings. We thus present GOYA, a method that distills the artistic knowledge captured in a recent generative model to disentangle content and style. Experiments show that synthetically generated images sufficiently serve as a proxy of the real distribution of artworks, allowing GOYA to separately represent the two elements of art while keeping more information than existing methods.

The recent advances in natural language processing (NLP), have led to a new trend of applying large language models (LLMs) to real-world scenarios. While the latest LLMs are astonishingly fluent when interacting with humans, they suffer from the misinformation problem by unintentionally generating factually false statements. This can lead to harmful consequences, especially when produced within sensitive contexts, such as healthcare. Yet few previous works have focused on evaluating misinformation in the long-form (LF) generation of LLMs, especially for knowledge-intensive topics. Moreover, although LLMs have been shown to perform well in different languages, misinformation evaluation has been mostly conducted in English. To this end, we present a benchmark, CARE-MI, for evaluating LLM misinformation in: 1) a sensitive topic, specifically the maternity and infant care domain; and 2) a language other than English, namely Chinese. Most importantly, we provide an innovative paradigm for building LF generation evaluation benchmarks that can be transferred to other knowledge-intensive domains and low-resourced languages. Our proposed benchmark fills the gap between the extensive usage of LLMs and the lack of datasets for assessing the misinformation generated by these models. It contains 1,612 expert-checked questions, accompanied with human-selected references. Using our benchmark, we conduct extensive experiments and found that current Chinese LLMs are far from perfect in the topic of maternity and infant care. In an effort to minimize the reliance on human resources for performance evaluation, we offer off-the-shelf judgment models for automatically assessing the LF output of LLMs given benchmark questions. Moreover, we compare potential solutions for LF generation evaluation and provide insights for building better automated metrics.

We study societal bias amplification in image captioning. Image captioning models have been shown to perpetuate gender and racial biases, however, metrics to measure, quantify, and evaluate the societal bias in captions are not yet standardized. We provide a comprehensive study on the strengths and limitations of each metric, and propose LIC, a metric to study captioning bias amplification. We argue that, for image captioning, it is not enough to focus on the correct prediction of the protected attribute, and the whole context should be taken into account. We conduct extensive evaluation on traditional and state-of-the-art image captioning models, and surprisingly find that, by only focusing on the protected attribute prediction, bias mitigation models are unexpectedly amplifying bias.

Visually grounded paraphrases (VGPs) are different phrasal expressions describing the same visual concept in an image. Previous studies treat VGP identification as a binary classification task, which ignores various phenomena behind VGPs (i.e., different linguistic interpretation of the same visual concept) such as linguistic paraphrases and VGPs from different aspects. In this paper, we propose semantic typology for VGPs, aiming to elucidate the VGP phenomena and deepen the understanding about how human beings interpret vision with language. We construct a large VGP dataset that annotates the class to which each VGP pair belongs according to our typology. In addition, we present a classification model that fuses language and visual features for VGP classification on our dataset. Experiments indicate that joint language and vision representation learning is important for VGP classification. We further demonstrate that our VGP typology can boost the performance of visually grounded textual entailment.

Have you ever looked at a painting and wondered what is the story behind it? This work presents a framework to bring art closer to people by generating comprehensive descriptions of fine-art paintings. Generating informative descriptions for artworks, however, is extremely challenging, as it requires to 1) describe multiple aspects of the image such as its style, content, or composition, and 2) provide background and contextual knowledge about the artist, their influences, or the historical period. To address these challenges, we introduce a multi-topic and knowledgeable art description framework, which modules the generated sentences according to three artistic topics and, additionally, enhances each description with external knowledge. The framework is validated through an exhaustive analysis, both quantitative and qualitative, as well as a comparative human evaluation, demonstrating outstanding results in terms of both topic diversity and information veracity.

The rise of digitization of cultural documents offers large-scale contents, opening the road for development of AI systems in order to preserve, search, and deliver cultural heritage. To organize such cultural content also means to classify them, a task that is very familiar to modern computer science. Contextual information is often the key to structure such real world data, and we propose to use it in form of a knowledge graph. Such a knowledge graph, combined with content analysis, enhances the notion of proximity between artworks so it improves the performances in classification tasks. In this paper, we propose a novel use of a knowledge graph, that is constructed on annotated data and pseudo-labeled data. With label propagation, we boost artwork classification by training a model using a graph convolutional network, relying on the relationships between entities of the knowledge graph. Following a transductive learning framework, our experiments show that relying on a knowledge graph modeling the relations between labeled data and unlabeled data allows to achieve state-of-the-art results on multiple classification tasks on a dataset of paintings, and on a dataset of Buddha statues. Additionally, we show state-of-the-art results for the difficult case of dealing with unbalanced data, with the limitation of disregarding classes with extremely low degrees in the knowledge graph.

Humor is a very important communication tool; yet, it is an open problem for machines to understand humor. In this paper, we build a new multimodal dataset for humor prediction that includes subtitles and video frames, as well as humor labels associated with video's timestamps. On top of it, we present a model to predict whether a subtitle causes laughter. Our model uses the visual modality through facial expression and character name recognition, together with the verbal modality, to explore how the visual modality helps. In addition, we use an attention mechanism to adjust the weight for each modality to facilitate humor prediction. Interestingly, our experimental results show that the performance boost by combinations of different modalities, and the attention mechanism and the model mostly relies on the verbal modality.

We propose a novel video understanding task by fusing knowledge-based and video question answering. First, we introduce KnowIT VQA, a video dataset with 24,282 human-generated question-answer pairs about a popular sitcom. The dataset combines visual, textual and temporal coherence reasoning together with knowledge-based questions, which need of the experience obtained from the viewing of the series to be answered. Second, we propose a video understanding model by combining the visual and textual video content with specific knowledge about the show. Our main findings are: (i) the incorporation of knowledge produces outstanding improvements for VQA in video, and (ii) the performance on KnowIT VQA still lags well behind human accuracy, indicating its usefulness for studying current video modelling limitations.

Visual question answering (VQA) aims at answering questions about the visual content of an image or a video. Currently, most work on VQA is focused on image-based question answering, and less attention has been paid into answering questions about videos. However, VQA in video presents some unique challenges that are worth studying: it not only requires to model a sequence of visual features over time, but often it also needs to reason about associated subtitles. In this work, we propose to use BERT, a sequential modelling technique based on Transformers, to encode the complex semantics from video clips. Our proposed model jointly captures the visual and language information of a video scene by encoding not only the subtitles but also a sequence of visual concepts with a pretrained language-based Transformer. In our experiments, we exhaustively study the performance of our model by taking different input arrangements, showing outstanding improvements when compared against previous work on two well-known video VQA datasets: TVQA and Pororo.

Automatic art analysis aims to classify and retrieve artistic representations from a collection of images by using computer vision and machine learning techniques. In this work, we propose to enhance visual representations from neural networks with contextual artistic information. Whereas visual representations are able to capture information about the content and the style of an artwork, our proposed context-aware embeddings additionally encode relationships between different artistic attributes, such as author, school, or historical period. We design two different approaches for using context in automatic art analysis. In the first one, contextual data is obtained through a multi-task learning model, in which several attributes are trained together to find visual relationships between elements. In the second approach, context is obtained through an art-specific knowledge graph, which encodes relationships between artistic attributes. An exhaustive evaluation of both of our models in several art analysis problems, such as author identification, type classification, or cross-modal retrieval, show that performance is improved by up to 7.3% in art classification and 37.24% in retrieval when context-aware embeddings are used.

In this research we study the specific task of image-to-video retrieval, in which static pictures are used to find a specific timestamp or frame within a collection of videos. The inner temporal structure of video data consists of a sequence of highly correlated images or frames, commonly reproduced at rates of 24 to 30 frames per second. To perform large-scale retrieval, it is necessary to reduce the amount of data to be processed by exploiting the redundancy between these highly correlated images. In this work, we explore several techniques to aggregate visual temporal information from video data based on both standard local features and deep learning representations with the focus on the image-to-video retrieval task.