Related papers: A Symmetric Dual Encoding Dense Retrieval Framewor…
In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is adopted to learn dense representations of questions and…
We describe our two-stage system for the Multilingual Information Access (MIA) 2022 Shared Task on Cross-Lingual Open-Retrieval Question Answering. The first stage consists of multilingual passage retrieval with a hybrid dense and sparse…
Composed image retrieval (CIR) aims to retrieve the target image based on a multimodal query, i.e., a reference image paired with corresponding modification text. Recent CIR studies leverage vision-language pre-trained (VLP) methods as the…
Medical Visual Question Answering (VQA) systems play a supporting role to understand clinic-relevant information carried by medical images. The questions to a medical image include two categories: close-end (such as Yes/No question) and…
Dual encoders have been used for question-answering (QA) and information retrieval (IR) tasks with good results. Previous research focuses on two major types of dual encoders, Siamese Dual Encoder (SDE), with parameters shared across two…
In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection includes documents in multiple languages. We demonstrate that applying state-of-the-art approaches developed for cross-lingual information…
We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…
Visual Question Answering (VQA) is a challenging task that requires systems to provide accurate answers to questions based on image content. Current VQA models struggle with complex questions due to limitations in capturing and integrating…
Recent progress has been made in region-aware vision-language modeling, particularly with the emergence of the Describe Anything Model (DAM). DAM is capable of generating detailed descriptions of any specific image areas or objects without…
Knowledge-based Visual Question Answering (KVQA) requires external knowledge beyond the visible content to answer questions about an image. This ability is challenging but indispensable to achieve general VQA. One limitation of existing…
Open-Domain Question Answering (ODQA) systems necessitate a reader model capable of generating answers by simultaneously referring to multiple passages. Although representative models like Fusion-in-Decoder (FiD) have been proposed to…
Quantization-Aware Training (QAT), combined with Knowledge Distillation (KD), holds immense promise for compressing models for edge deployment. However, joint optimization for precision-sensitive image restoration (IR) to recover visual…
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…
Existing debiasing approaches in Visual Question Answering (VQA) primarily focus on enhancing visual learning, integrating auxiliary models, or employing data augmentation strategies. However, these methods exhibit two major drawbacks.…
We study the Knowledge-Based visual question-answering problem, for which given a question, the models need to ground it into the visual modality to find the answer. Although many recent works use question-dependent captioners to verbalize…
Outside-knowledge visual question answering (OK-VQA) requires the agent to comprehend the image, make use of relevant knowledge from the entire web, and digest all the information to answer the question. Most previous works address the…
Visual Question Answering (VQA) presents a unique challenge as it requires the ability to understand and encode the multi-modal inputs - in terms of image processing and natural language processing. The algorithm further needs to learn how…
In computer vision and image processing tasks, image fusion has evolved into an attractive research field. However, recent existing image fusion methods are mostly built on pixel-level operations, which may produce unacceptable artifacts…
Knowledge-intensive visual question answering (VQA) requires external knowledge beyond image content, demanding precise visual grounding and coherent integration of visual and textual information. Although multimodal retrieval-augmented…
Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both visual content of images and textual content of questions. To support the VQA task, we need to find good solutions for the following…