Related papers: MaCLR: Motion-aware Contrastive Learning of Repres…

In recent years, self-supervised representation learning for skeleton-based action recognition has been developed with the advance of contrastive learning methods. The existing contrastive learning methods use normal augmentations to…

Identifying highlight moments of raw video materials is crucial for improving the efficiency of editing videos that are pervasive on internet platforms. However, the extensive work of manually labeling footage has created obstacles to…

Contrastive learning has emerged as a pivotal framework for representation learning, underpinning advances in both unimodal and bimodal applications like SimCLR and CLIP. To address fundamental limitations like large batch size dependency…

Learning effective motion features is an essential pursuit of video representation learning. This paper presents a simple yet effective sample construction strategy to boost the learning of motion features in video contrastive learning. The…

Prior works on action representation learning mainly focus on designing various architectures to extract the global representations for short video clips. In contrast, many practical applications such as video alignment have strong demand…

Visual-only self-supervised learning has achieved significant improvement in video representation learning. Existing related methods encourage models to learn video representations by utilizing contrastive learning or designing specific…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

Contrastive learning has shown promising potential in self-supervised spatio-temporal representation learning. Most works naively sample different clips to construct positive and negative pairs. However, we observe that this formulation…

Contrastive learning (CL) aims to learn useful representation without relying on expert annotations in the context of medical image segmentation. Existing approaches mainly contrast a single positive vector (i.e., an augmentation of the…

Self-supervised skeleton-based action recognition enjoys a rapid growth along with the development of contrastive learning. The existing methods rely on imposing invariance to augmentations of 3D skeleton within a single data stream, which…

Multifold observations are common for different data modalities, e.g., a 3D shape can be represented by multi-view images and an image can be described with different captions. Existing cross-modal contrastive representation learning…

Improving sample efficiency is a key research problem in reinforcement learning (RL), and CURL, which uses contrastive learning to extract high-level features from raw pixels of individual video frames, is an efficient…

Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a…

Skeleton-based action recognition is widely used in varied areas, e.g., surveillance and human-machine interaction. Existing models are mainly learned in a supervised manner, thus heavily depending on large-scale labeled data which could be…

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank.…

Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that…

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…

Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

We propose a self-supervised learning approach for videos that learns representations of both the RGB frames and the accompanying audio without human supervision. In contrast to images that capture the static scene appearance, videos also…