Related papers: Contrastive Masked Autoencoders for Character-Leve…

Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical…

Aiming at exploiting the rich information in user behaviour sequences, sequential recommendation has been widely adopted in real-world recommender systems. However, current methods suffer from the following issues: 1) sparsity of user-item…

Unsupervised Time series anomaly detection plays a crucial role in applications across industries. However, existing methods face significant challenges due to data distributional shifts across different domains, which are exacerbated by…

Establishing correspondence between images or scenes is a significant challenge in computer vision, especially given occlusions, viewpoint changes, and varying object appearances. In this paper, we present Siamese Masked Autoencoders…

Airwriting Recognition is the problem of identifying letters written in free space with finger movement. It is essentially a specialized case of gesture recognition, wherein the vocabulary of gestures corresponds to letters as in a…

We present a variation of the Autoencoder (AE) that explicitly maximizes the mutual information between the input data and the hidden representation. The proposed model, the InfoMax Autoencoder (IMAE), by construction is able to learn a…

Writer identification (writer-id), an important field in biometrics, aims to identify a writer by their handwriting. Identification in existing writer-id studies requires a complete document or text, limiting the scalability and flexibility…

Learning rich data representations from unlabeled data is a key challenge towards applying deep learning algorithms in downstream tasks. Several variants of variational autoencoders (VAEs) have been proposed to learn compact data…

Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively…

While some powerful neural network architectures (e.g., Transformer, Graph Neural Networks) have achieved improved performance in sequential recommendation with high-order item dependency modeling, they may suffer from poor representation…

The cosmic microwave background power spectra are a primary window into the early universe. However, achieving interpretable, likelihood-compatible compression and fast inference under weak model assumptions remains challenging. We propose…

Context-aware methods have achieved remarkable advancements in supervised scene text recognition by leveraging semantic priors from words. Considering the heterogeneity of text and background in STR, we propose that such contextual priors…

3D captioning, which aims to describe the content of 3D scenes in natural language, remains highly challenging due to the inherent sparsity of point clouds and weak cross-modal alignment in existing methods. To address these challenges, we…

We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the…

It is challenging to detect curve texts due to their irregular shapes and varying sizes. In this paper, we first investigate the deficiency of the existing curve detection methods and then propose a novel Conditional Spatial Expansion (CSE)…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becoming increasingly…

Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of…

Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts. Most existing methods assume that events appear in sentences without overlaps, which are not applicable to the complicated…

Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining…