Related papers: OneDB: A Distributed Multi-Metric Data Similarity …
In this study, we introduce LoopDB, which is a challenging loop closure dataset comprising over 1000 images captured across diverse environments, including parks, indoor scenes, parking spaces, as well as centered around individual objects.…
Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. It is a challenging yet crucial area with numerous real-world applications in multimedia, affective computing, robotics,…
There has been increased interest in data search as a means to find relevant datasets or data points in data lakes and repositories. Although approaches have been proposed to support spatial dataset search and data point search, they…
Organizations are collecting increasingly large amounts of data for data driven decision making. These data are often dumped into a centralized repository, e.g., a data lake, consisting of thousands of structured and unstructured datasets.…
The explosive growth of multimodal data - spanning text, image, video, spatial, and relational modalities, coupled with the need for real-time semantic search and retrieval over these data - has outpaced the capabilities of existing…
Dense retrieval, which encodes queries and documents into a single dense vector, has become the dominant neural retrieval approach due to its simplicity and compatibility with fast approximate nearest neighbor algorithms. As the tasks dense…
We demonstrate NeedleDB, an open-source, deployment-ready database system for answering complex natural language queries over image data. Unlike existing approaches that rely on contrastive-learning embeddings (e.g., CLIP), which degrade on…
This paper introduces SLIM-VDB, a new lightweight semantic mapping system with probabilistic semantic fusion for closed-set or open-set dictionaries. Advances in data structures from the computer graphics community, such as OpenVDB, have…
The scarcity of high-quality data remains a primary bottleneck in adapting multimodal generative models for medical image editing. Existing medical image editing datasets often suffer from limited diversity, neglect of medical image…
Similarity searching finds application in a wide variety of domains including multilingual databases, computational biology, pattern recognition and text retrieval. Similarity is measured in terms of a distance function, edit distance, in…
Measuring inter-dataset similarity is an important task in machine learning and data mining with various use cases and applications. Existing methods for measuring inter-dataset similarity are computationally expensive, limited, or…
Unimodality constitutes a key property indicating grouping behavior of the data around a single mode of its density. We propose a method that partitions univariate data into unimodal subsets through recursive splitting around valley points…
Large-scale deep learning models contribute to significant performance improvements on varieties of downstream tasks. Current data and model parallelism approaches utilize model replication and partition techniques to support the…
Developing a universal model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration. Our daily choices, especially in domains like fashion and…
At Pinterest, we utilize image embeddings throughout our search and recommendation systems to help our users navigate through visual content by powering experiences like browsing of related content and searching for exact products for…
We describe a novel metric-based learning approach that introduces a multimodal framework and uses deep audio and geophone encoders in siamese configuration to design an adaptable and lightweight supervised model. This framework eliminates…
In healthcare applications, there is a growing need to develop machine learning models that use data from a single source, such as that from a wrist wearable device, to monitor physical activities, assess health risks, and provide immediate…
Lossless compression is essential for efficient data storage and transmission. Although learning-based lossless compressors achieve strong results, most of them are designed for a single modality, leading to redundant compressor deployments…
Purpose High dimensional, multimodal data can nowadays be analyzed by huge deep neural networks with little effort. Several fusion methods for bringing together different modalities have been developed. Given the prevalence of…
With the development of web technology, multi-modal or multi-view data has surged as a major stream for big data, where each modal/view encodes individual property of data objects. Often, different modalities are complementary to each…