Related papers: 3D Human Action Representation Learning via Cross-…
Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable…
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…
Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation. Contrastive learning makes use of unlabeled data for the…
Human action recognition from skeletal data is a hot research topic and important in many open domain applications of computer vision, thanks to recently introduced 3D sensors. In the literature, naive methods simply transfer off-the-shelf…
One central question for video action recognition is how to model motion. In this paper, we present hierarchical contrastive motion learning, a new self-supervised learning framework to extract effective motion representations from raw…
Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents…
We consider the problem of semi-supervised 3D action recognition which has been rarely explored before. Its major challenge lies in how to effectively learn motion representations from unlabeled data. Self-supervised learning (SSL) has been…
Disease diagnosis from medical images via supervised learning is usually dependent on tedious, error-prone, and costly image labeling by medical experts. Alternatively, semi-supervised learning and self-supervised learning offer…
Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…
Concept-oriented deep learning (CODL) is a general approach to meet the future challenges for deep learning: (1) learning with little or no external supervision, (2) coping with test examples that come from a different distribution than the…
Pose-estimation methods enable extracting human motion from common videos in the structured form of 3D skeleton sequences. Despite great application opportunities, effective content-based access to such spatio-temporal motion data is a…
Skeleton-based action recognition has garnered significant attention due to the utilization of concise and resilient skeletons. Nevertheless, the absence of detailed body information in skeletons restricts performance, while other…
Although machine learning on hypergraphs has attracted considerable attention, most of the works have focused on (semi-)supervised learning, which may cause heavy labeling costs and poor generalization. Recently, contrastive learning has…
Deep learning is ubiquitous across many areas areas of computer vision. It often requires large scale datasets for training before being fine-tuned on small-to-medium scale problems. Activity, or, in other words, action recognition, is one…
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.…
Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…
Generalist Vision-Language-Action models are currently hindered by the scarcity of robotic data compared to the abundance of human video demonstrations. Existing Latent Action Models attempt to leverage video data but often suffer from…
Instance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning. They are not suitable for exploiting the rich…
Self-supervised learning has demonstrated remarkable capability in representation learning for skeleton-based action recognition. Existing methods mainly focus on applying global data augmentation to generate different views of the skeleton…
Humans can learn incrementally, whereas neural networks forget previously acquired information catastrophically. Continual Learning (CL) approaches seek to bridge this gap by facilitating the transfer of knowledge to both previous tasks…