Related papers: WSFE: Wasserstein Sub-graph Feature Encoder for Ef…

Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. This is exacerbated in some structured prediction tasks, such as semantic…

Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS…

Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS)…

Semantic segmentation is a core computer vision problem, but the high costs of data annotation have hindered its wide application. Weakly-Supervised Semantic Segmentation (WSSS) offers a cost-efficient workaround to extensive labeling in…

Learning user sequence behaviour embedding is very sophisticated and challenging due to the complicated feature interactions over time and high dimensions of user features. Recent emerging foundation models, e.g., BERT and its variants,…

Recently, matrix factorization-based recommendation methods have been criticized for the problem raised by the triangle inequality violation. Although several metric learning-based approaches have been proposed to overcome this issue,…

Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions. Existing CF-based methods commonly adopt negative sampling to discriminate different items. Training with…

In general, recommendation can be viewed as a matching problem, i.e., match proper items for proper users. However, due to the huge semantic gap between users and items, it's almost impossible to directly match users and items in their…

Many unsupervised representation learning methods belong to the class of similarity learning models. While various modality-specific approaches exist for different types of data, a core property of many methods is that representations of…

As the core algorithm in recommendation systems, collaborative filtering (CF) algorithms inevitably face the problem of data sparsity. Since CF captures similar users and items for recommendations, it is effective to augment the lacking…

Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects. To…

Collaborative data consist of ratings relating two distinct sets of objects: users and items. Much of the work with such data focuses on filtering: predicting unknown ratings for pairs of users and items. In this paper we focus on the…

We propose a novel approach for comparing distributions whose supports do not necessarily lie on the same metric space. Unlike Gromov-Wasserstein (GW) distance which compares pairwise distances of elements from each distribution, we…

Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework. However, only a…

In this paper, a new feature selection algorithm, called SFE (Simple, Fast, and Efficient), is proposed for high-dimensional datasets. The SFE algorithm performs its search process using a search agent and two operators: non-selection and…

We introduce a new convolutional AutoEncoder architecture for user modelling and recommendation tasks with several improvements over the state of the art. Firstly, our model has the flexibility to learn a set of associations and…

Recommender systems play an increasingly important role in online applications to help users find what they need or prefer. Collaborative filtering algorithms that generate predictions by analyzing the user-item rating matrix perform poorly…

Nowadays designing a real recommendation system has been a critical problem for both academic and industry. However, due to the huge number of users and items, the diversity and dynamic property of the user interest, how to design a…

Recent recommender systems increasingly leverage embeddings from large pre-trained language models (PLMs). However, such embeddings exhibit two key limitations: (1) PLMs are not explicitly optimized to produce structured and discriminative…

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…