paper-with-me

Papers

Cross-modal Retrieval for Knowledge-based Visual Question Answering

2024-01-11 · Paul Lerner, Olivier Ferret, Camille Guinaudeau

Knowledge-based Visual Question Answering about Named Entities is a challenging task that requires retrieving information from a multimodal Knowledge Base. Named entities have diverse visual representations and are therefore difficult to recognize. We argue that cross-modal retrieval may help bridge the semantic gap between an entity and its depictions, and is foremost complementary with mono-modal retrieval. We provide empirical evidence through experiments with a multimodal dual encoder, namely CLIP, on the recent ViQuAE, InfoSeek, and Encyclopedic-VQA datasets. Additionally, we study three different strategies to fine-tune such a model: mono-modal, cross-modal, or joint training. Our method, which combines mono-and cross-modal retrieval, is competitive with billion-parameter models on the three datasets, while being conceptually simpler and computationally cheaper.

📄 PDF Abstract BibTeX arXiv:2401.05736

Code (1)

paullerner/viquae 공식 구현 pytorch

Tasks

Cross-Modal RetrievalQuestion AnsweringRetrievalVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Multi-Modal Retrieval Augmentation for Open-Ended and Knowledge-Intensive Video Question Answering

2025-02-17 · Md Zarif Ul Alam, Hamed Zamani

While current video question answering systems perform well on some tasks requiring only direct visual understanding, they struggle with questions demanding knowledge beyond what is immediately observable in the video co…

Multiple-choiceQuestion AnsweringRetrievalRetrieval-augmented Generation+2

Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering

2026-07-28 · Noor Islam S. Mohammad, Uluğ Bayazıt arxiv

Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense retrieval over large external corpora, and full cross-modal fusion. E…

Question Answering

Visualized Text-to-Image Retrieval

2025-05-26 · Di wu, Yixin Wan, Kai-Wei Chang

We propose Visualize-then-Retrieve (VisRet), a new paradigm for Text-to-Image (T2I) retrieval that mitigates the limitations of cross-modal similarity alignment of existing multi-modal embeddings. VisRet first projects t…

Image RetrievalQuestion AnsweringRetrievalRetrieval-augmented Generation+1

Enhancing Visual Question Answering with Multimodal LLMs via Chain-of-Question Guided Retrieval-Augmented Generation

2026-05-05 · Quanxing Xu, Ling Zhou, Xian Zhong, Xiaohua Huang 외 arxiv

With advances in multimodal research and deep learning, Multimodal Large Language Models (MLLMs) have emerged as a powerful paradigm for a wide range of multimodal tasks. As a core problem in vision-language research, Vi…

Visual Question Answering

Passage Retrieval for Outside-Knowledge Visual Question Answering

2021-05-09 · Chen Qu, Hamed Zamani, Liu Yang, W. Bruce Croft 외

In this work, we address multi-modal information needs that contain text questions and images by focusing on passage retrieval for outside-knowledge visual question answering. This task requires access to outside knowled…

Image CaptioningObjectPassage RetrievalQuestion Answering+3