Related papers: Exploiting ID-Text Complementarity via Ensembling …

Image-text matching is a key multimodal task that aims to model the semantic association between images and text as a matching relationship. With the advent of the multimedia information age, image, and text data show explosive growth, and…

In this paper, we explore the usage of Word Embedding semantic resources for Information Retrieval (IR) task. This embedding, produced by a shallow neural network, have been shown to catch semantic similarities between words (Mikolov et…

Multi-modal recommendation systems aim to enhance performance by integrating an item's content features across various modalities with user behavior data. Effective utilization of features from different modalities requires addressing two…

This paper explores the use of Large Language Models (LLMs) for sequential recommendation, which predicts users' future interactions based on their past behavior. We introduce a new concept, "Integrating Recommendation Systems as a New…

Word embeddings have gained significant attention as learnable representations of semantic relations between words, and have been shown to improve upon the results of traditional word representations. However, little effort has been devoted…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

Text-Pedestrian Image Retrieval aims to use the text describing pedestrian appearance to retrieve the corresponding pedestrian image. This task involves not only modality discrepancy, but also the challenge of the textual diversity of…

Due to the modality gap between visible and infrared images with high visual ambiguity, learning \textbf{diverse} modality-shared semantic concepts for visible-infrared person re-identification (VI-ReID) remains a challenging problem. Body…

Embedding-based methods have attracted increasing attention in recent entity alignment (EA) studies. Although great promise they can offer, there are still several limitations. The most notable is that they identify the aligned entities…

Semantic ID (SID)-based recommendation is a promising paradigm for scaling sequential recommender systems, but existing methods largely follow a semantic-centric pipeline: item embeddings are learned from foundation models and discretized…

Multimodal recommendation has attracted extensive attention by leveraging heterogeneous modality information to alleviate data sparsity and improve recommendation accuracy. Existing methods have attempted to replace ID embeddings with…

Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiting scalability and generalization. Semantic IDs, derived…

Recommender systems have seen significant advancements with the influence of deep learning and graph neural networks, particularly in capturing complex user-item relationships. However, these graph-based recommenders heavily depend on…

Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to its various applications in public security and video…

Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image. However,…

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…

In this paper, we explore the unsupervised learning of a semantic embedding space for co-occurring sensory inputs. Specifically, we focus on the task of learning a semantic vector space for both spoken and handwritten digits using the…

Although multi-interest recommenders have achieved significant progress in the matching stage, our research reveals that existing models tend to exhibit an under-clustered item embedding space, which leads to a low discernibility between…

The exponential growth of online content has posed significant challenges to ID-based models in industrial recommendation systems, ranging from extremely high cardinality and dynamically growing ID space, to highly skewed engagement…

Integrating visual features has been proved useful for natural language understanding tasks. Nevertheless, in most existing multimodal language models, the alignment of visual and textual data is expensive. In this paper, we propose a novel…