Related papers: Rethinking Vision Transformer and Masked Autoencod…

Though the success of CLIP-based training recipes in vision-language models, their scalability to more modalities (e.g., 3D, audio, etc.) is limited to large-scale data, which is expensive or even inapplicable for rare modalities. In this…

Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimodal features in…

Self-supervised learning has attracted increasing attention as it learns data-driven representation from data without annotations. Vision transformer-based autoencoder (ViT-AE) by He et al. (2021) is a recent self-supervised learning…

Effective multimodal reasoning depends on the alignment of visual and linguistic representations, yet the mechanisms by which vision-language models (VLMs) achieve this alignment remain poorly understood. Following the LiMBeR framework, we…

Multimodal Face Anti-Spoofing (FAS) methods, which integrate multiple visual modalities, often suffer even more severe performance degradation than unimodal FAS when deployed in unseen domains. This is mainly due to two overlooked risks…

Recently, masked image modeling (MIM) has become a promising direction for visual pre-training. In the context of vision transformers, MIM learns effective visual representation by aligning the token-level features with a pre-defined space…

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input…

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on…

Face recognition is a crucial task in various multimedia applications such as security check, credential access and motion sensing games. However, the task is challenging when an input face is noisy (e.g. poor-condition RGB image) or lacks…

Learning 3D representation plays a critical role in masked autoencoder (MAE) based pre-training methods for point cloud, including single-modal and cross-modal based MAE. Specifically, although cross-modal MAE methods learn strong 3D…

Automatic modulation recognition (AMR) is critical for cognitive radio, spectrum monitoring, and secure wireless communication. However, existing solutions often rely on large labeled datasets or multi-stage training pipelines, which limit…

The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various…

Multimodal magnetic resonance imaging (MRI) constitutes the first line of investigation for clinicians in the care of brain tumors, providing crucial insights for surgery planning, treatment monitoring, and biomarker identification.…

In this work, we focus on unsupervised vision-language-action mapping in the area of robotic manipulation. Recently, multiple approaches employing pre-trained large language and vision models have been proposed for this task. However, they…

This work asks: with abundant, unlabeled real faces, how to learn a robust and transferable facial representation that boosts various face security tasks with respect to generalization performance? We make the first attempt and propose a…

Integrating information from multiple modalities is arguably one of the essential prerequisites for grounding artificial intelligence systems with an understanding of the real world. Recent advances in video transformers that jointly learn…

Self-supervised foundation models have shown great potential in computer vision thanks to the pre-training paradigm of masked autoencoding. Scale is a primary factor influencing the performance of these foundation models. However, these…

Face anti-spoofing (FAS) is crucial for protecting facial recognition systems from presentation attacks. Previous methods approached this task as a classification problem, lacking interpretability and reasoning behind the predicted results.…

Visible-Infrared Person Re-Identification (VI-ReID) is a challenging retrieval task under complex modality changes. Existing methods usually focus on extracting discriminative visual features while ignoring the reliability and commonality…

The Masked autoencoder (MAE) has drawn attention as a representative self-supervised approach for masked image modeling with vision transformers. However, even though MAE shows better generalization capability than fully supervised training…