Related papers: Skeleton-Contrastive 3D Action Representation Lear…

In this paper, we propose the $K$-Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual instances. It aims to combine the advantages of inter-instance…

This paper presents a new framework for human action recognition from a 3D skeleton sequence. Previous studies do not fully utilize the temporal relationships between video segments in a human action. Some studies successfully used very…

Multimodal imaging and correlative analysis typically require image alignment. Contrastive learning can generate representations of multimodal images, reducing the challenging task of multimodal image registration to a monomodal one.…

In face-to-face dialogues, the form-meaning relationship of co-speech gestures varies depending on contextual factors such as what the gestures refer to and the individual characteristics of speakers. These factors make co-speech gesture…

Session-based recommendation, which aims to predict the next item of users' interest as per an existing sequence interaction of items, has attracted growing applications of Contrastive Learning (CL) with improved user and item…

Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and identifiable representation learning: Temporal…

Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the…

We present a new deep learning approach for real-time 3D human action recognition from skeletal data and apply it to develop a vision-based intelligent surveillance system. Given a skeleton sequence, we propose to encode skeleton poses and…

Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function. In particular, methods based on contrastive learning that induce linearity of the latent…

Self-supervised deep learning has accelerated 2D natural image analysis but remains difficult to translate into 3D MRI, where data are scarce and pre-trained 2D backbones cannot capture volumetric context. We present a…

The data-driven approach that learns an optimal representation of vision features like skeleton frames or RGB videos is currently a dominant paradigm for activity recognition. While great improvements have been achieved from existing single…

Current state-of-the-art approaches to skeleton-based action recognition are mostly based on recurrent neural networks (RNN). In this paper, we propose a novel convolutional neural networks (CNN) based framework for both action…

Self-supervised learning (SSL) has shown remarkable success in skeleton-based action recognition by leveraging data augmentations to learn meaningful representations. However, existing SSL methods rely on data augmentations that…

Self-supervised learning has been successfully applied to pre-train video representations, which aims at efficient adaptation from pre-training domain to downstream tasks. Existing approaches merely leverage contrastive loss to learn…

Point clouds have attracted increasing attention. Significant progress has been made in methods for point cloud analysis, which often requires costly human annotation as supervision. To address this issue, we propose a novel…

Deep learning models achieve impressive performance for skeleton-based human action recognition. However, the robustness of these models to adversarial attacks remains largely unexplored due to their complex spatio-temporal nature that must…

Learning a good 3D human pose representation is important for human pose related tasks, e.g. human 3D pose estimation and action recognition. Within all these problems, preserving the intrinsic pose information and adapting to view…

Action recognition has been heavily employed in many applications such as autonomous vehicles, surveillance, etc, where its robustness is a primary concern. In this paper, we examine the robustness of state-of-the-art action recognizers…

The success of deep learning based models for computer vision applications requires large scale human annotated data which are often expensive to generate. Self-supervised learning, a subset of unsupervised learning, handles this problem by…

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply…