Related papers: Scaling Language-Free Visual Representation Learni…
Self-supervised learning (SSL) has become the de facto training paradigm of large models, where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Despite demonstrating comparable performance with…
Self-Supervised Learning (SSL) surmises that inputs and pairwise positive relationships are enough to learn meaningful representations. Although SSL has recently reached a milestone: outperforming supervised methods in many modalities\dots…
In learning vision-language representations from web-scale data, the contrastive language-image pre-training (CLIP) mechanism has demonstrated a remarkable performance in many vision tasks. However, its application to the widely studied…
Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view…
Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has diminished significantly in recent years, indicating that a…
Self-supervised learning (SSL) has become the de facto training paradigm of large models where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Hypothesizing that SSL models would learn more generic,…
Recent advancements in vision-language pre-training via contrastive learning have significantly improved performance across computer vision tasks. However, in the medical domain, obtaining multimodal data is often costly and challenging due…
Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in vision-language representation learning, powering diverse downstream tasks and serving as the default vision backbone in multimodal large language models (MLLMs).…
Self-supervised learning (SSL), which aims to learn meaningful prior representations from unlabeled data, has been proven effective for skeleton-based action understanding. Different from the image domain, skeleton data possesses sparser…
How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment methods do not directly translate to how these models are used in practical vision-language tasks. In…
Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need…
Sign language recognition (SLR) is a machine learning task aiming to identify signs in videos. Due to the scarcity of annotated data, unsupervised methods like contrastive learning have become promising in this field. They learn meaningful…
Accurate and efficient Video Quality Assessment (VQA) has long been a key research challenge. Current mainstream VQA methods typically improve performance by pretraining on large-scale classification datasets (e.g., ImageNet, Kinetics-400),…
Many vision-language models (VLMs) that prove very effective at a range of multimodal task, build on CLIP-based vision encoders, which are known to have various limitations. We investigate the hypothesis that the strong language backbone in…
Self-supervised learning has attracted plenty of recent research interest. However, most works for self-supervision in speech are typically unimodal and there has been limited work that studies the interaction between audio and visual…
Self-supervision has shown outstanding results for natural language processing, and more recently, for image recognition. Simultaneously, vision transformers and its variants have emerged as a promising and scalable alternative to…
Large-scale multi-modal contrastive pre-training has demonstrated great utility to learn transferable features for a range of downstream tasks by mapping multiple modalities into a shared embedding space. Typically, this has employed…
We introduce S$^2$VS, a video similarity learning approach with self-supervision. Self-Supervised Learning (SSL) is typically used to train deep models on a proxy task so as to have strong transferability on target tasks after fine-tuning.…
Multimodal large language models (MLLMs) perform well on many vision-language tasks but often struggle with vision-centric problems that require fine-grained visual reasoning. Recent evidence suggests that this limitation arises not from…
Recently, self-supervised learning (SSL) has demonstrated strong performance in speaker recognition, even if the pre-training objective is designed for speech recognition. In this paper, we study which factor leads to the success of…