Related papers: CaLa: Complementary Association Learning for Augme…

Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual embeddings obtained from template prompts, e.g.,…

Non-local attention module has been proven to be crucial for image restoration. Conventional non-local attention processes features of each layer separately, so it risks missing correlation between features among different layers. To…

Existing in-context learning (ICL) methods for relation extraction (RE) often prioritize language similarity over structural similarity, which can lead to overlooking entity relationships. To address this, we propose an AMR-enhanced…

Aggregated search aims to construct search result pages (SERPs) from blue-links and heterogeneous modules (such as news, images, and videos). Existing studies have largely ignored the correlations between blue-links and heterogeneous…

Composed Image Retrieval (CIR) aims to retrieve target images that closely resemble a reference image while integrating user-specified textual modifications, thereby capturing user intent more precisely. Existing training-free zero-shot CIR…

Retrieval-Augmented Generation (RAG) has emerged as a promising technique to enhance the quality and relevance of responses generated by large language models. While recent advancements have mainly focused on improving RAG for text-based…

Learning recipe and food image representation in common embedding space is non-trivial but crucial for cross-modal recipe retrieval. In this paper, we propose a new perspective for this problem by utilizing foundation models for data…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by pulling in external material, document, code, manuals, from vast and ever-growing corpora, to effectively answer user queries. The effectiveness of RAG depends…

Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. While analytic learning enables rapid, recursive closed-form updates, its efficacy is often…

The evaluation of machine-generated image captions poses an interesting yet persistent challenge. Effective evaluation measures must consider numerous dimensions of similarity, including semantic relevance, visual structure, object…

Despite remarkable advancements in text-to-image person re-identification (TIReID) facilitated by the breakthrough of cross-modal embedding models, existing methods often struggle to distinguish challenging candidate images due to intrinsic…

This paper proposes a Japanese/English cross-language information retrieval (CLIR) system targeting technical documents. Our system first translates a given query containing technical terms into the target language, and then retrieves…

In-Context Learning (ICL) emerges as a key feature for Large Language Models (LLMs), allowing them to adapt to new tasks by leveraging task-specific examples without updating model parameters. However, ICL faces challenges with increasing…

This paper addresses the task of interactive, conversational text-to-image retrieval. Our DIR-TIR framework progressively refines the target image search through two specialized modules: the Dialog Refiner Module and the Image Refiner…

Composed Image Retrieval (CIR) aims to retrieve target images by integrating a reference image with a corresponding modification text. CIR requires jointly considering the explicit semantics specified in the query and the implicit semantics…

Retrieval-Augmented Generation (RAG) mitigates hallucination in large language models (LLMs) by incorporating external knowledge during generation. However, the effectiveness of RAG depends not only on the design of the retriever and the…

A cross-modal retrieval process is to use a query in one modality to obtain relevant data in another modality. The challenging issue of cross-modal retrieval lies in bridging the heterogeneous gap for similarity computation, which has been…

We study the problem of deep recall model in industrial web search, which is, given a user query, retrieve hundreds of most relevance documents from billions of candidates. The common framework is to train two encoding models based on…

Controllable Image Captioning (CIC) aims at generating natural language descriptions for an image, conditioned on information provided by end users, e.g., regions, entities or events of interest. However, available image-language datasets…

We address the problem of cross-domain image retrieval, considering the following practical application: given a user photo depicting a clothing image, our goal is to retrieve the same or attribute-similar clothing items from online…