Related papers: Bridging the Gap Between Semantic and User Prefere…

Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even…

Hierarchical classification is a crucial task in many applications, where objects are organized into multiple levels of categories. However, conventional classification approaches often neglect inherent inter-class relationships at…

Emotion Recognition in Conversation (ERC) plays an important role in driving the development of human-machine interaction. Emotions can exist in multiple modalities, and multimodal ERC mainly faces two problems: (1) the noise problem in the…

Sequential recommendation addresses the issue of preference drift by predicting the next item based on the user's previous behaviors. Recently, a promising approach using contrastive learning has emerged, demonstrating its effectiveness in…

In musical compositions that include vocals, lyrics significantly contribute to artistic expression. Consequently, previous studies have introduced the concept of a recommendation system that suggests lyrics similar to a user's favorites or…

The self-supervised ultrasound (US) video model pretraining can use a small amount of labeled data to achieve one of the most promising results on US diagnosis. However, it does not take full advantage of multi-level knowledge for learning…

State-of-the-art model for zero-shot cross-lingual spoken language understanding performs cross-lingual unsupervised contrastive learning to achieve the label-agnostic semantic alignment between each utterance and its code-switched data.…

We present a new Self-Supervised Learning (SSL) approach to pre-train encoders on unlabeled audio data that reduces the need for large amounts of labeled data for audio and speech classification. Our primary aim is to learn audio…

Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have been driven mainly by generative reconstruction objectives, contrastive approaches remain…

Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coarser-grained semantics. Capturing such structures with image…

Personalized recommender systems play a crucial role in capturing users' evolving preferences over time to provide accurate and effective recommendations on various online platforms. However, many recommendation models rely on a single type…

Learning symbolic music representations, especially disentangled representations with probabilistic interpretations, has been shown to benefit both music understanding and generation. However, most models are only applicable to short-term…

Contrastive Learning (CL) performances as a rising approach to address the challenge of sparse and noisy recommendation data. Although having achieved promising results, most existing CL methods only perform either hand-crafted data or…

Multi-modal semantic understanding requires integrating information from different modalities to extract users' real intention behind words. Most previous work applies a dual-encoder structure to separately encode image and text, but fails…

Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…

Contrastive learning has shown effectiveness in improving sequential recommendation models. However, existing methods still face challenges in generating high-quality contrastive pairs: they either rely on random perturbations that corrupt…

Heterogeneous graphs can well describe the complex entity relationships in the real world. For example, online shopping networks contain multiple physical types of consumers and products, as well as multiple relationship types such as…

Session-based recommendation aims to predict intents of anonymous users based on limited behaviors. With the ability in alleviating data sparsity, contrastive learning is prevailing in the task. However, we spot that existing contrastive…

Video highlight detection is a crucial yet challenging problem that aims to identify the interesting moments in untrimmed videos. The key to this task lies in effective video representations that jointly pursue two goals, \textit{i.e.},…

Hierarchical Text Classification (HTC) has recently gained traction given the ability to handle complex label hierarchy. This has found applications in domains like E- commerce, customer care and medicine industry among other real-world…