相关论文: Unsupervised Learning from Continuous Video in a S…

Deep networks have recently enjoyed enormous success when applied to recognition and classification problems in computer vision, but their use in graphics problems has been limited. In this work, we present a novel deep architecture that…

Deep learning-based video inpainting has yielded promising results and gained increasing attention from researchers. Generally, these methods usually assume that the corrupted region masks of each frame are known and easily obtained.…

Object recognition and motion understanding are key components of perception that complement each other. While self-supervised learning methods have shown promise in their ability to learn from unlabeled data, they have primarily focused on…

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise.…

We present a novel approach to unsupervised learning for video object segmentation (VOS). Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. We rely on uniform grid…

We propose a realistic scenario for the unsupervised video learning where neither task boundaries nor labels are provided when learning a succession of tasks. We also provide a non-parametric learning solution for the under-explored problem…

We present a semi-supervised approach that localizes multiple unknown object instances in long videos. We start with a handful of labeled boxes and iteratively learn and label hundreds of thousands of object instances. We propose criteria…

We present a meta-learning framework for weakly supervised anomaly detection in videos, where the detector learns to adapt to unseen types of abnormal activities effectively when only video-level annotations of binary labels are available.…

Video coding has traditionally been developed to support services such as video streaming, videoconferencing, digital TV, and so on. The main intent was to enable human viewing of the encoded content. However, with the advances in deep…

Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to infer the state of parts of the world that are currently…

Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations, or to translate signals from one domain to another (as in image captioning, or…

For visual estimation of optical flow, a crucial function for many vision tasks, unsupervised learning, using the supervision of view synthesis has emerged as a promising alternative to supervised methods, since ground-truth flow is not…

Estimating the parameters of a model describing a set of observations using a neural network is in general solved in a supervised way. In cases when we do not have access to the model's true parameters this approach can not be applied.…

A visual system has to learn both which features to extract from images and how to group locations into (proto-)objects. Those two aspects are usually dealt with separately, although predictability is discussed as a cue for both. To…

Most current super-resolution methods rely on low and high resolution image pairs to train a network in a fully supervised manner. However, such image pairs are not available in real-world applications. Instead of directly addressing this…

Automating the analysis of surveillance video footage is of great interest when urban environments or industrial sites are monitored by a large number of cameras. As anomalies are often context-specific, it is hard to predefine events of…

Semi-supervised learning improves the performance of supervised machine learning by leveraging methods from unsupervised learning to extract information not explicitly available in the labels. Through the design of a system that enables a…

A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment. Many existing methods for learning the dynamics of physical interactions require labeled object information.…

In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch. We identify that three major challenges, i.e., moving object discovery, rich temporal variation exploitation, and online update, are the central…

Learning is an inherently continuous phenomenon. When humans learn a new task there is no explicit distinction between training and inference. As we learn a task, we keep learning about it while performing the task. What we learn and how we…