Related papers: Contrastive Learning under Noisy Temporal Self-Sup…

Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label,…

Video self-supervised learning is a challenging task, which requires significant expressive power from the model to leverage rich spatial-temporal knowledge and generate effective supervisory signals from large amounts of unlabeled videos.…

The fast evolution and widespread of deepfake techniques in real-world scenarios require stronger generalization abilities of face forgery detectors. Some works capture the features that are unrelated to method-specific artifacts, such as…

Learning rich visual representations using contrastive self-supervised learning has been extremely successful. However, it is still a major question whether we could use a similar approach to learn superior auditory representations. In this…

Contrastive learning is commonly applied to self-supervised learning, and has been shown to outperform traditional approaches such as the triplet loss and N-pair loss. However, the requirement of large batch sizes and memory banks has made…

Contrastive learning, which aims at minimizing the distance between positive pairs while maximizing that of negative ones, has been widely and successfully applied in unsupervised feature learning, where the design of positive and negative…

Accurate detection of polyps is of critical importance for the early and intermediate stages of colorectal cancer diagnosis. Compared to static images, dynamic colonoscopy videos provide more comprehensive visual information, which can…

We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is…

Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information and the inability to generate reliable pseudo-labels for effective unsupervised data use. To address these…

Linking sheet music images to audio recordings remains a key problem for the development of efficient cross-modal music retrieval systems. One of the fundamental approaches toward this task is to learn a cross-modal embedding space via deep…

The diagnosis process of colorectal cancer mainly focuses on the localization and characterization of abnormal growths in the colon tissue known as polyps. Despite recent advances in deep object localization, the localization of polyps…

The colorectal polyps classification is a critical clinical examination. To improve the classification accuracy, most computer-aided diagnosis algorithms recognize colorectal polyps by adopting Narrow-Band Imaging (NBI). However, the NBI…

Trigger-word detection plays an important role as the entry point of user's communication with voice assistants. But supporting a particular word as a trigger-word involves huge amount of data collection, augmentation and labelling for that…

Contrastive learning of auditory and visual perception has been extremely successful when investigated individually. However, there are still major questions on how we could integrate principles learned from both domains to attain effective…

We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips…

The purpose of this study is to develop a computer-aided diagnosis system for classifying benign and malignant lung lesions, and to assist physicians in real-time analysis of radial probe endobronchial ultrasound (EBUS) videos. During the…

Colonoscopy videos provide richer information in polyp segmentation for rectal cancer diagnosis. However, the endoscope's fast moving and close-up observing make the current methods suffer from large spatial incoherence and continuous…

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on…

With the onset of the COVID-19 pandemic, ultrasound has emerged as an effective tool for bedside monitoring of patients. Due to this, a large amount of lung ultrasound scans have been made available which can be used for AI based diagnosis…

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…