English
Related papers

Related papers: MetaEmbed: Scaling Multimodal Retrieval at Test-Ti…

200 papers

Despite the success of text retrieval in many NLP tasks, code retrieval remains a largely underexplored area. Most text retrieval systems are tailored for natural language queries, often neglecting the specific challenges of retrieving…

Software Engineering · Computer Science 2025-08-11 Ye Liu , Rui Meng , Shafiq Joty , Silvio Savarese , Caiming Xiong , Yingbo Zhou , Semih Yavuz

Most multi-modal tasks can be formulated into problems of either generation or embedding. Existing models usually tackle these two types of problems by decoupling language modules into a text decoder for generation, and a text encoder for…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Feipeng Ma , Hongwei Xue , Guangting Wang , Yizhou Zhou , Fengyun Rao , Shilin Yan , Yueyi Zhang , Siying Wu , Mike Zheng Shou , Xiaoyan Sun

Our objective is to build an embedding model that captures the nuanced relationship between a search query and candidate videos. We cover three aspects of nuanced retrieval: (i) temporal, (ii) negation, and (iii) multimodal. For temporal…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Piyush Bagad , Andrew Zisserman

There is a growing interest in Universal Multimodal Embeddings (UME), where models are required to generate task-specific representations. While recent studies show that Multimodal Large Language Models (MLLMs) perform well on such tasks,…

Visual embedding models excel at zero-shot tasks like visual retrieval and classification. However, these models cannot be used for tasks that contain ambiguity or require user instruction. These tasks necessitate an embedding model which…

Computer Vision and Pattern Recognition · Computer Science 2025-08-22 Benjamin Schneider , Florian Kerschbaum , Wenhu Chen

Recent advances in large language models have demonstrated remarkable effectiveness in information retrieval (IR) tasks. While many neural IR systems encode queries and documents into single-vector representations, multi-vector models…

Information Retrieval · Computer Science 2023-12-12 Susav Shrestha , Narasimha Reddy , Zongwang Li

Multi-vector visual retrievers (e.g., ColPali-style late interaction models) deliver strong accuracy, but scale poorly because each page yields thousands of vectors, making indexing and search increasingly expensive. We present Visual RAG…

Information Retrieval · Computer Science 2026-02-16 Ara Yeroyan

Video moment retrieval aims to search the moment most relevant to a given language query. However, most existing methods in this community often require temporal boundary annotations which are expensive and time-consuming to label. Hence…

Computer Vision and Pattern Recognition · Computer Science 2021-11-05 Ding Li , Rui Wu , Yongqiang Tang , Zhizhong Zhang , Wensheng Zhang

Embedding based retrieval (EBR) is a fundamental building block in many web applications. However, EBR in sponsored search is distinguished from other generic scenarios and technically challenging due to the need of serving multiple…

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…

Computer Vision and Pattern Recognition · Computer Science 2019-05-15 Maxime Portaz , Hicham Randrianarivo , Adrien Nivaggioli , Estelle Maudet , Christophe Servan , Sylvain Peyronnet

Multimodal data has become a crucial element in the realm of big data analytics, driving advancements in data exploration, data mining, and empowering artificial intelligence applications. To support high-quality retrieval for these…

Databases · Computer Science 2025-02-11 Ming Sheng , Shuliang Wang , Yong Zhang , Kaige Wang , Jingyi Wang , Yi Luo , Rui Hao

Text embeddings are typically evaluated on a limited set of tasks, which are constrained by language, domain, and task diversity. To address these limitations and provide a more comprehensive evaluation, we introduce the Massive…

The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable…

Multimedia · Computer Science 2024-02-19 Yongqi Li , Wenjie Wang , Leigang Qu , Liqiang Nie , Wenjie Li , Tat-Seng Chua

The ever-increasing size of language models curtails their widespread availability to the community, thereby galvanizing many companies into offering access to large language models through APIs. One particular type, suitable for dense…

Information Retrieval · Computer Science 2023-07-10 Ehsan Kamalloo , Xinyu Zhang , Odunayo Ogundepo , Nandan Thakur , David Alfonso-Hermelo , Mehdi Rezagholizadeh , Jimmy Lin

Multimodal models excel in English, supported by abundant image-text and audio-text data, but performance drops sharply for other languages due to limited multilingual multimodal resources. Existing solutions rely on machine translation,…

Machine Learning · Computer Science 2026-01-22 Piyush Singh Pasi

Multimodal Large Language Models (MLLMs) have demonstrated strong cross-modal reasoning capabilities, yet their potential for vision-only tasks remains underexplored. We investigate MLLMs as training-free similarity estimators for…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Bahey Tharwat , Giorgos Kordopatis-Zilos , Pavel Suma , Ian Reid , Giorgos Tolias

Current video retrieval systems, especially those used in competitions, primarily focus on querying individual keyframes or images rather than encoding an entire clip or video segment. However, queries often describe an action or event over…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Quoc-Bao Nguyen-Le , Thanh-Huy Le-Nguyen

Fixed-dimensional speaker embeddings have become the dominant approach in speaker modeling, typically spanning hundreds to thousands of dimensions. These dimensions are hyperparameters that are not specifically picked, nor are they…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Shuai Wang , Pengcheng Zhu , Haizhou Li

Textbook question answering (TQA) is a complex task, requiring the interpretation of complex multimodal context. Although recent advances have improved overall performance, they often encounter difficulties in educational settings where…

Information Retrieval · Computer Science 2025-05-21 Hessa Alawwad , Usman Naseem , Areej Alhothali , Ali Alkhathlan , Amani Jamal

Multimodal vector search offers a new paradigm for information retrieval by exposing numerous pieces of functionality which are not possible in traditional lexical search engines. While multimodal vector search can be treated as a drop in…

Information Retrieval · Computer Science 2024-09-19 Owen Pendrigh Elliott , Tom Hamer , Jesse Clark