相关论文: ParamCrop: Parametric Cubic Cropping for Video Con…

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…

We propose a self-supervised method to learn feature representations from videos. A standard approach in traditional self-supervised methods uses positive-negative data pairs to train with contrastive learning strategy. In such a case,…

Robotic grasping faces challenges in adapting to objects with varying shapes and sizes. In this paper, we introduce MISCGrasp, a volumetric grasping method that integrates multi-scale feature extraction with contrastive feature enhancement…

Multi-view clustering aims to study the complementary information across views and discover the underlying structure. For solving the relatively high computational cost for the existing approaches, works based on anchor have been presented…

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…

Recent works have advanced the performance of self-supervised representation learning by a large margin. The core among these methods is intra-image invariance learning. Two different transformations of one image instance are considered as…

Graph contrastive learning (GCL) is a popular method for leaning graph representations by maximizing the consistency of features across augmented views. Traditional GCL methods utilize single-perspective i.e. data or model-perspective)…

Deep clustering has attracted increasing attention in recent years due to its capability of joint representation learning and clustering via deep neural networks. In its latest developments, the contrastive learning has emerged as an…

We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness,…

Self-supervised 3D representation learning aims to learn effective representations from large-scale unlabeled point clouds. Most existing approaches adopt point discrimination as the pretext task, which assigns matched points in two…

The existing contrastive learning methods mainly focus on single-grained representation learning, e.g., part-level, object-level or scene-level ones, thus inevitably neglecting the transferability of representations on other granularity…

Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional…

Multi-view representation learning captures comprehensive information from multiple views of a shared context. Recent works intuitively apply contrastive learning (CL) to learn representations, regarded as a pairwise manner, which is still…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

We present a new self-supervised paradigm on point cloud sequence understanding. Inspired by the discriminative and generative self-supervised methods, we design two tasks, namely point cloud sequence based Contrastive Prediction and…

Inspired by the impressive success of contrastive learning (CL), a variety of graph augmentation strategies have been employed to learn node representations in a self-supervised manner. Existing methods construct the contrastive samples by…

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…

Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various neural architectures, spanning Transformer-based models like Vision Transformers (ViTs) to Convolutional Networks…

Existing vision-text contrastive learning like CLIP aims to match the paired image and caption embeddings while pushing others apart, which improves representation transferability and supports zero-shot prediction. However, medical…

Self-supervised representation learning is a fundamental problem in computer vision with many useful applications (e.g., image search, instance level recognition, copy detection). In this paper we present a new contrastive self-supervised…