Related papers: ASMa: Asymmetric Spatio-temporal Masking for Skele…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks. Such approaches employ data…

Multimodal human action understanding is a significant problem in computer vision, with the central challenge being the effective utilization of the complementarity among diverse modalities while maintaining model efficiency. However, most…

Skeleton-based human action recognition has attracted increasing attention in recent years. However, most of the existing works focus on supervised learning which requiring a large number of annotated action sequences that are often…

A recent line of research on automated speaking assessment (ASA) has benefited from self-supervised learning (SSL) representations, which capture rich acoustic and linguistic patterns in non-native speech without underlying assumptions of…

Sequential recommender systems have demonstrated strong capabilities in modeling users' dynamic preferences and capturing item transition patterns. However, real-world user behaviors are often noisy due to factors such as human errors,…

Dexterous manipulation requires precise geometric reasoning, yet existing visuo-tactile learning methods struggle with sub-millimeter precision tasks that are routine for traditional model-based approaches. We identify a key limitation:…

We present Self-Organizing Visual Prototypes (SOP), a new training technique for unsupervised visual feature learning. Unlike existing prototypical self-supervised learning (SSL) methods that rely on a single prototype to encode all…

Contrastive learning has gained significant attention in skeleton-based action recognition for its ability to learn robust representations from unlabeled data. However, existing methods rely on a single skeleton convention, which limits…

Limited availability of labeled data for machine learning on multimodal time-series extensively hampers progress in the field. Self-supervised learning (SSL) is a promising approach to learning data representations without relying on…

Self-supervised landmark estimation is a challenging task that demands the formation of locally distinct feature representations to identify sparse facial landmarks in the absence of annotated data. To tackle this task, existing…

One-shot action recognition allows the recognition of human-performed actions with only a single training example. This can influence human-robot-interaction positively by enabling the robot to react to previously unseen behaviour. We…

Self-supervised learning (SSL) has delivered superior performance on a variety of downstream vision tasks. Two main-stream SSL frameworks have been proposed, i.e., Instance Discrimination (ID) and Masked Image Modeling (MIM). ID pulls…

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.…

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Skeleton-based Temporal Action Segmentation involves the dense action classification of variable-length skeleton sequences. Current approaches primarily apply graph-based networks to extract framewise, whole-body-level motion…

Inspired by the success of Self-supervised learning (SSL) in learning visual representations from unlabeled data, a few recent works have studied SSL in the context of continual learning (CL), where multiple tasks are learned sequentially,…

In past years model-agnostic meta-learning (MAML) has been one of the most promising approaches in meta-learning. It can be applied to different kinds of problems, e.g., reinforcement learning, but also shows good results on few-shot…

Self-supervised learning (SSL) techniques have recently produced outstanding results in learning visual representations from unlabeled videos. Despite the importance of motion in supervised learning techniques for action recognition, SSL…

With the great development of generative model techniques, face forgery detection draws more and more attention in the related field. Researchers find that existing face forgery models are still vulnerable to adversarial examples with…