Related papers: Ego-Vehicle Action Recognition based on Semi-Super…

Upscaled video detection is a helpful tool in multimedia forensics, but it is a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and…

While unsupervised change detection using contrastive learning has been significantly improved the performance of literature techniques, at present, it only focuses on the bi-temporal change detection scenario. Previous state-of-the-art…

Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against. A common property among its various methods is that they…

The availability of clean and diverse labeled data is a major roadblock for training models on complex tasks such as visual question answering (VQA). The extensive work on large vision-and-language models has shown that self-supervised…

Ego-centric driving videos available online provide an abundant source of visual data for autonomous driving, yet their lack of annotations makes it difficult to learn representations that capture both semantic structure and 3D geometry.…

Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail…

We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving the place recognition problem with complex radar data. Our method is based on invariant instance feature learning but is tailored for…

Lane detection is an essential part of the perception sub-architecture of any automated driving (AD) or advanced driver assistance system (ADAS). When focusing on low-cost, large scale products for automated driving, model-driven approaches…

To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we…

The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to…

How can we teach a computer to recognize 10,000 different actions? Deep learning has evolved from supervised and unsupervised to self-supervised approaches. In this paper, we present a new contrastive learning-based framework for decision…

In this study, we proposed a novel semi-supervised training method that uses unlabeled data with a class distribution that is completely different from the target data or data without a target label. To this end, we introduce a contrastive…

In this work we address the challenging problem of unsupervised learning from videos. Existing methods utilize the spatio-temporal continuity in contiguous video frames as regularization for the learning process. Typically, this temporal…

Query-based video grounding is an important yet challenging task in video understanding, which aims to localize the target segment in an untrimmed video according to a sentence query. Most previous works achieve significant progress by…

The data collected from a vehicle's Controller Area Network (CAN) can quickly exceed human analysis or annotation capabilities when considering fleets of vehicles, which stresses the importance of unsupervised machine learning methods. This…

Given the difficulty of manually annotating motion in video, the current best motion estimation methods are trained with synthetic data, and therefore struggle somewhat due to a train/test gap. Self-supervised methods hold the promise of…

A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing…

Although deep learning are commonly employed for image recognition, usually huge amount of labeled training data is required, which may not always be readily available. This leads to a noticeable performance disparity when compared to…

In this work, we focus on semi-supervised learning for video action detection. Video action detection requires spatiotemporal localization in addition to classification, and a limited amount of labels makes the model prone to unreliable…