Related papers: Smart Multi-Modal Search: Contextual Sparse and De…

Information retrieval systems have traditionally relied on exact term match methods such as BM25 for first-stage retrieval. However, recent advancements in neural network-based techniques have introduced a new method called dense retrieval.…

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…

Cross-modal retrieval relies on accurate models to retrieve relevant results for queries across modalities such as image, text, and video. In this paper, we build upon previous work by tackling the difficulty of evaluating models both…

Text-image cross-modal retrieval is a challenging task in the field of language and vision. Most previous approaches independently embed images and sentences into a joint embedding space and compare their similarities. However, previous…

We present Deep-n-Cheap -- an open-source AutoML framework to search for deep learning models. This search includes both architecture and training hyperparameters, and supports convolutional neural networks and multi-layer perceptrons. Our…

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible…

With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most…

Advancements in cross-modal feature extraction and integration have significantly enhanced performance in few-shot learning tasks. However, current multi-modal object detection (MM-OD) methods often experience notable performance…

Most real world applications of image retrieval such as Adobe Stock, which is a marketplace for stock photography and illustrations, need a way for users to find images which are both visually (i.e. aesthetically) and conceptually (i.e.…

This paper presents a comprehensive comparison of BM25, SPLADE, and Expanded-SPLADE models in the context of large-scale web document retrieval. We evaluate the effectiveness and efficiency of these models on datasets spanning from tens of…

Developing artificial intelligence (AI) and machine learning (ML) models for medical imaging typically involves extensive training and testing on large datasets, consuming significant computational time, energy, and resources. There is a…

Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across…

This paper presents Universal Vision-Language Dense Retrieval (UniVL-DR), which builds a unified model for multi-modal retrieval. UniVL-DR encodes queries and multi-modality resources in an embedding space for searching candidates from…

We present principled approaches to train and deploy dyadic neural embedding models at the billion scale, focusing our investigation on the application of semantic product search. When training a dyadic model, one seeks to embed two…

The digital realm has witnessed the rise of various search modalities, among which the Image-Based Conversational Search System stands out. This research delves into the design, implementation, and evaluation of this specific system,…

Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…

Constituting highly informative network embeddings is an important tool for network analysis. It encodes network topology, along with other useful side information, into low-dimensional node-based feature representations that can be…

Query-by-example search often uses dynamic time warping (DTW) for comparing queries and proposed matching segments. Recent work has shown that comparing speech segments by representing them as fixed-dimensional vectors --- acoustic word…

Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine…

Lifelong user interest modeling is crucial for industrial recommender systems, yet existing approaches rely predominantly on ID-based features, suffering from poor generalization on long-tail items and limited semantic expressiveness. While…