Related papers: Deep Reversible Consistency Learning for Cross-mod…

Self-Supervised Learning (SSL) enables us to pre-train foundation models without costly labeled data. Among SSL methods, Contrastive Learning (CL) methods are better at obtaining accurate semantic representations in noise interference.…

While existing semi-supervised object detection (SSOD) methods perform well in general scenes, they encounter challenges in handling oriented objects in aerial images. We experimentally find three gaps between general and oriented object…

Multimodal recommendation systems integrate diverse multimodal information into the feature representations of both items and users, thereby enabling a more comprehensive modeling of user preferences. However, existing methods are hindered…

Indias linguistic diversity poses significant challenges for developing inclusive Automatic Speech Recognition (ASR) systems. Traditional multilingual models, which require simultaneous access to all language data, are impractical due to…

Cross-Modal Retrieval (CMR) is an important research topic across multimodal computing and information retrieval, which takes one type of data as the query to retrieve relevant data of another type. It has been widely used in many…

We propose a novel continual learning method called Residual Continual Learning (ResCL). Our method can prevent the catastrophic forgetting phenomenon in sequential learning of multiple tasks, without any source task information except the…

Cross-modal retrieval is the task of retrieving samples of a given modality by using queries of a different one. Due to the wide range of practical applications, the problem has been mainly focused on the vision and language case, e.g. text…

Current vision-language retrieval aims to perform cross-modal instance search, in which the core idea is to learn the consistent visionlanguage representations. Although the performance of cross-modal retrieval has greatly improved with the…

Self-supervised learning (SSL) has recently achieved great success in mining the user-item interactions for collaborative filtering. As a major paradigm, contrastive learning (CL) based SSL helps address data sparsity in Web platforms by…

Multimodal representation learning is a challenging task in which previous work mostly focus on either uni-modality pre-training or cross-modality fusion. In fact, we regard modeling multimodal representation as building a skyscraper, where…

Deep reinforcement learning (DRL) has been widely applied in autonomous exploration and mapping tasks, but often struggles with the challenges of sampling efficiency, poor adaptability to unknown map sizes, and slow simulation speed. To…

Multimodal learning aims to capture both shared and private information from multiple modalities. However, existing methods that project all modalities into a single latent space for fusion often overlook the asynchronous, multi-level…

Referring Expression Comprehension (REC) aims to localize an image region of a given object described by a natural-language expression. While promising performance has been demonstrated, existing REC algorithms make a strong assumption that…

Similarity analysis is one of the crucial steps in most fMRI studies. Representational Similarity Analysis (RSA) can measure similarities of neural signatures generated by different cognitive states. This paper develops Deep…

Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies have shown that popular benchmark datasets often contain…

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…

Sequential recommender systems (SRSs) aim to suggest next item for a user based on her historical interaction sequences. Recently, many research efforts have been devoted to attenuate the influence of noisy items in sequences by either…

Continual Learning (CL) involves fine-tuning pre-trained models with new data while maintaining the performance on the pre-trained data. This is particularly relevant for expanding multilingual ASR (MASR) capabilities. However, existing CL…

Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…

Compressive learning (CL) is an emerging framework that integrates signal acquisition via compressed sensing (CS) and machine learning for inference tasks directly on a small number of measurements. It can be a promising alternative to…