Related papers: Multimodal Learned Sparse Retrieval for Image Sugg…

Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional…

The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and…

State of the art Symbolic Regression (SR) methods currently build specialized models, while the application of Large Language Models (LLMs) remains largely unexplored. In this work, we introduce the first comprehensive framework that…

We consider the problem of high-dimensional light field reconstruction and develop a learning-based framework for spatial and angular super-resolution. Many current approaches either require disparity clues or restore the spatial and…

Unsupervised cross-lingual speech representation learning (XLSR) has recently shown promising results in speech recognition by leveraging vast amounts of unlabeled data across multiple languages. However, standard XLSR model suffers from…

Sequential Recommender Systems (SRS) aim to predict users' next interaction based on their historical behaviors, while still facing the challenge of data sparsity. With the rapid advancement of Multimodal Large Language Models (MLLMs),…

Multitask learning (MTL) can utilize the relatedness between multiple tasks for performance improvement. The advent of multimodal data allows tasks to be referenced by multiple indices. High-order tensors are capable of providing efficient…

Query suggestion, a technique widely adopted in information retrieval, enhances system interactivity and the browsing experience of document collections. In cross-modal retrieval, many works have focused on retrieving relevant items from…

For image super-resolution (SR), bridging the gap between the performance on synthetic datasets and real-world degradation scenarios remains a challenge. This work introduces a novel "Low-Res Leads the Way" (LWay) training framework,…

Supervised deep learning approaches can artificially increase the resolution of microscopy images by learning a mapping between two image resolutions or modalities. However, such methods often require a large set of hard-to-get…

Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adopt the late-fusion strategy to combine visual and language…

Text-to-Image Retrieval (T2IR) is a highly valuable task that aims to match a given textual query to images in a gallery. Existing benchmarks primarily focus on textual queries describing overall image semantics or foreground salient…

Unsupervised methods have proven effective for discriminative tasks in a single-modality scenario. In this paper, we present a multimodal framework for learning sparse representations that can capture semantic correlation between…

This paper proposes a novel algorithm for image phase retrieval, i.e., for recovering complex-valued images from the amplitudes of noisy linear combinations (often the Fourier transform) of the sought complex images. The algorithm is…

Semantic sparsity is a common challenge in structured visual classification problems; when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the training set. This paper studies semantic…

The compressive sensing (CS) scheme exploits much fewer measurements than suggested by the Nyquist-Shannon sampling theorem to accurately reconstruct images, which has attracted considerable attention in the computational imaging community.…

Since the first success of Dong et al., the deep-learning-based approach has become dominant in the field of single-image super-resolution. This replaces all the handcrafted image processing steps of traditional sparse-coding-based methods…

Spatial Pyramid Matching (SPM) and its variants have achieved a lot of success in image classification. The main difference among them is their encoding schemes. For example, ScSPM incorporates Sparse Code (SC) instead of Vector…

State-of-the-art learned reconstruction methods often rely on black-box modules that, despite their strong performance, raise questions about their interpretability and robustness. Here, we build on a recently proposed image reconstruction…

Among the representation learning, the low-rank representation (LRR) is one of the hot research topics in many fields, especially in image processing and pattern recognition. Although LRR can capture the global structure, the ability of…