Related papers: A Contextual-Aware Position Encoding for Sequentia…

Modeling users' dynamic and evolving preferences from their historical behaviors is challenging and crucial for recommendation systems. Previous methods employ sequential neural networks (e.g., Recurrent Neural Network) to encode users'…

Repurchase behavior is a primary signal in large-scale retail recommendation, particularly in categories with frequent replenishment: many items in a user's next basket were previously purchased, and their timing follows stable,…

Recent research explores incorporating knowledge graphs (KG) into e-commerce recommender systems, not only to achieve better recommendation performance, but more importantly to generate explanations of why particular decisions are made.…

Recurrent Neural Networks (RNN) received a vast amount of attention last decade. Recently, the architectures of Recurrent AutoEncoders (RAE) found many applications in practice. RAE can extract the semantically valuable information, called…

We conducted empirical experiments to assess the transferability of a light curve transformer to datasets with different cadences and magnitude distributions using various positional encodings (PEs). We proposed a new approach to…

Category-Agnostic Pose Estimation (CAPE) aims to localize keypoints on an object of any category given few exemplars in an in-context manner. Prior arts involve sophisticated designs, e.g., sundry modules for similarity calculation and a…

Scene Coordinate Regression (SCR) is a visual localization technique that utilizes deep neural networks (DNN) to directly regress 2D-3D correspondences for camera pose estimation. However, current SCR methods often face challenges in…

Sequential location recommendation plays a huge role in modern life, which can enhance user experience, bring more profit to businesses and assist in government administration. Although methods for location recommendation have evolved…

Sequential recommendation leverages interaction sequences to predict forthcoming user behaviors, crucial for crafting personalized recommendations. However, the true preferences of a user are inherently complex and high-dimensional, while…

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Accounting for the fact that users have different sequential patterns, the main drawback of state-of-the-art recommendation strategies is that a fixed sequence length of user-item interactions is required as input to train the models. This…

Recommendation models are typically trained on observational user interaction data, but the interactions between latent factors in users' decision-making processes lead to complex and entangled data. Disentangling these latent factors to…

Recently, self-attention based models have achieved state-of-the-art performance in sequential recommendation task. Following the custom from language processing, most of these models rely on a simple positional embedding to exploit the…

Sequence labeling is a fundamental task in natural language processing and has been widely studied. Recently, RNN-based sequence labeling models have increasingly gained attentions. Despite superior performance achieved by learning the long…

Positional Encodings (PEs) are used to inject word-order information into transformer-based language models. While they can significantly enhance the quality of sentence representations, their specific contribution to language models is not…

Encoding a sequence of observations is an essential task with many applications. The encoding can become highly efficient when the observations are generated by a dynamical system. A dynamical system imposes regularities on the observations…

Transformer architectures have established strong baselines in time series forecasting, yet they typically rely on positional encodings that assume uniform, index-based temporal progression. However, real-world systems, from shifting…

Calibrated recommendation, which aims to maintain personalized proportions of categories within recommendations, is crucial in practical scenarios since it enhances user satisfaction by reflecting diverse interests. However, achieving…

3D hand pose estimation (HPE) is the process of locating the joints of the hand in 3D from any visual input. HPE has recently received an increased amount of attention due to its key role in a variety of human-computer interaction…

Positional encodings are essential to transformer-based generative models, yet their behavior in multimodal and attention-sharing settings is not fully understood. In this work, we present a principled analysis of Rotary Positional…