Related papers: Multimodal Search on Iconclass using Vision-Langua…
Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a sequence of interpretable queries about the data in order of information gain, updating its posterior at each step based on observed query-answer pairs.…
Despite the prevalence and historical importance of maps in digital collections, current methods of navigating and exploring map collections are largely restricted to catalog records and structured metadata. In this paper, we explore the…
CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…
Multi-stage ranking pipelines have been a practical solution in modern search systems, where the first-stage retrieval is to return a subset of candidate documents, and latter stages attempt to re-rank those candidates. Unlike re-ranking…
Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which…
Training models to apply linguistic knowledge and visual concepts from 2D images to 3D world understanding is a promising direction that researchers have only recently started to explore. In this work, we design a novel 3D pre-training…
Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal reasoning tasks, but they often struggle to disentangle fine-grained visual attributes and reason about underlying causal relationships.…
Composed Image Retrieval (CIR) allows users to search for images by combining a reference image with a text prompt that describes desired modifications. While vision-language models like CLIP have popularized this task by embedding multiple…
Methods based on Contrastive Language-Image Pre-training (CLIP) are nowadays extensively used in support of vision-and-language tasks involving remote sensing data, such as cross-modal retrieval. The adaptation of CLIP to this specific…
Image-text retrieval (ITR) is a task to retrieve the relevant images/texts, given the query from another modality. The conventional dense retrieval paradigm relies on encoding images and texts into dense representations using dual-stream…
Image cropping has progressed tremendously under the data-driven paradigm. However, current approaches do not account for the intentions of the user, which is an issue especially when the composition of the input image is complex. Moreover,…
Multilingual (or cross-lingual) embeddings represent several languages in a unique vector space. Using a common embedding space enables for a shared semantic between words from different languages. In this paper, we propose to embed images…
While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, due to issues like training objective…
Acquiring the desired font for various design tasks can be challenging and requires professional typographic knowledge. While previous font retrieval or generation works have alleviated some of these difficulties, they often lack support…
Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps from the frozen visual encoder to compute the pixel-wise…
The analysis of vision-based deep neural networks (DNNs) is highly desirable but it is very challenging due to the difficulty of expressing formal specifications for vision tasks and the lack of efficient verification procedures. In this…
Tagging-based systems enable users to categorize web resources by means of tags (freely chosen keywords), in order to refinding these resources later. Tagging is implicitly also a social indexing process, since users share their tags and…
This paper explores the usage of multimodal image-to-text models to enhance text-based item retrieval. We propose utilizing pre-trained image captioning and tagging models, such as instructBLIP and CLIP, to generate text-based product…
Vision-language pretrained models have seen remarkable success, but their application to safety-critical settings is limited by their lack of interpretability. To improve the interpretability of vision-language models such as CLIP, we…
TIReID aims to retrieve the image corresponding to the given text query from a pool of candidate images. Existing methods employ prior knowledge from single-modality pre-training to facilitate learning, but lack multi-modal correspondences.…