Related papers: Contrastive Masked Autoencoders are Stronger Visio…
We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…
Multimodal representation learning is a challenging task in which previous work mostly focus on either uni-modality pre-training or cross-modality fusion. In fact, we regard modeling multimodal representation as building a skyscraper, where…
Masked autoencoding has shown excellent performance on self-supervised video representation learning. Temporal redundancy has led to a high masking ratio and customized masking strategy in VideoMAE. In this paper, we aim to further improve…
Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data. However, we observe that most existing VLP methods focus…
Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information…
Videos captured from multiple viewpoints can help in perceiving the 3D structure of the world and benefit computer vision tasks such as action recognition, tracking, etc. In this paper, we present a method for self-supervised learning from…
Broadcast and media organizations increasingly rely on artificial intelligence to automate the labor-intensive processes of content indexing, tagging, and metadata generation. However, existing AI systems typically operate on a single…
In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrained text encoder into contrastive audio-visual masked…
Vehicle re-identification is a cross-view search task by matching the same target vehicle from different perspectives. It serves an important role in road-vehicle collaboration and intelligent road control. With the large-scale and dynamic…
Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends…
Recently, the advancement of self-supervised learning techniques, like masked autoencoders (MAE), has greatly influenced visual representation learning for images and videos. Nevertheless, it is worth noting that the predominant approaches…
As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…
Self-supervised learning on graphs can be bifurcated into contrastive and generative methods. Contrastive methods, also known as graph contrastive learning (GCL), have dominated graph self-supervised learning in the past few years, but the…
The scarcity of annotated data in LiDAR point cloud understanding hinders effective representation learning. Consequently, scholars have been actively investigating efficacious self-supervised pre-training paradigms. Nevertheless, temporal…
Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…
Referring Image Segmentation (RIS) aims to segment target objects expressed in natural language within a scene at the pixel level. Various recent RIS models have achieved state-of-the-art performance by generating contextual tokens to model…
Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to assist in the…
Self-supervised learning has proved effective for skeleton-based human action understanding, which is an important yet challenging topic. Previous works mainly rely on contrastive learning or masked motion modeling paradigm to model the…
In graph self-supervised learning, masked autoencoders (MAE) and contrastive learning (CL) are two prominent paradigms. MAE focuses on reconstructing masked elements, while CL maximizes similarity between augmented graph views. Recent…
This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS),…