相关论文: Winoground: Probing Vision and Language Models for…

Despite recent progress towards scaling up multimodal vision-language models, these models are still known to struggle on compositional generalization benchmarks such as Winoground. We find that a critical component lacking from current…

Image captioning models tend to describe images in an object-centric way, emphasising visible objects. But image descriptions can also abstract away from objects and describe the type of scene depicted. In this paper, we explore the…

Vision-Language Models (VLMs) have shown remarkable capabilities in a large number of downstream tasks. Nonetheless, compositional image understanding remains a rather difficult task due to the object bias present in training data. In this…

We study the composition style in deep image matting, a notion that characterizes a data generation flow on how to exploit limited foregrounds and random backgrounds to form a training dataset. Prior art executes this flow in a completely…

Systems that can find correspondences between multiple modalities, such as between speech and images, have great potential to solve different recognition and data analysis tasks in an unsupervised manner. This work studies multimodal…

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal understanding, enabling more sophisticated and accurate integration of visual and textual information across various tasks, including image and video…

In this paper, we explore the potential of visual in-context learning to enable a single model to handle multiple tasks and adapt to new tasks during test time without re-training. Unlike previous approaches, our focus is on training…

Large Multimodal Models have achieved remarkable progress in integrating vision and language, enabling strong performance across perception, reasoning, and domain-specific tasks. However, their capacity to reason over multiple, visually…

Image captioning is a research area of immense importance, aiming to generate natural language descriptions for visual content in the form of still images. The advent of deep learning and more recently vision-language pre-training…

We introduce a new multi-modal task for computer systems, posed as a combined vision-language comprehension challenge: identifying the most suitable text describing a scene, given several similar options. Accomplishing the task entails…

This paper introduces a large-scale multimodal and multilingual dataset that aims to facilitate research on grounding words to images in their contextual usage in language. The dataset consists of images selected to unambiguously illustrate…

Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…

Existing vision-language understanding benchmarks largely consist of images of objects in their usual contexts. As a consequence, recent multimodal large language models can perform well with only a shallow visual understanding by relying…

News Image Captioning aims to create captions from news articles and images, emphasizing the connection between textual context and visual elements. Recognizing the significance of human faces in news images and the face-name co-occurrence…

We introduce SeeingSounds, a lightweight and modular framework for audio-to-image generation that leverages the interplay between audio, language, and vision-without requiring any paired audio-visual data or training on visual generative…

There has been growing sentiment recently that modern large multimodal models (LMMs) have addressed most of the key challenges related to short video comprehension. As a result, both academia and industry are gradually shifting their…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Humans perceive and comprehend different visual properties of an object based on specific contexts. For instance, we know that a banana turns brown ``when it becomes rotten,'' whereas it appears green ``when it is unripe.'' Previous studies…

This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to…

Understanding language goes hand in hand with the ability to integrate complex contextual information obtained via perception. In this work, we present a novel task for grounded language understanding: disambiguating a sentence given a…