Related papers: Unsupervised Learning of Disentangled Representati…

Video prediction has been considered a difficult problem because the video contains not only high-dimensional spatial information but also complex temporal information. Video prediction can be performed by finding features in recent frames,…

The recent success in deep learning has lead to various effective representation learning methods for videos. However, the current approaches for video representation require large amount of human labeled datasets for effective learning. We…

We use multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length representation. This representation is decoded using single or…

We propose a new representation of visual data that disentangles object position from appearance. Our method, termed Deep Latent Particles (DLP), decomposes the visual input into low-dimensional latent ``particles'', where each particle is…

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…

Correspondences between frames encode rich information about dynamic content in videos. However, it is challenging to effectively capture and learn those due to their irregular structure and complex dynamics. In this paper, we propose a…

Disentangled representations support a range of downstream tasks including causal reasoning, generative modeling, and fair machine learning. Unfortunately, disentanglement has been shown to be impossible without the incorporation of…

Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using…

Face images are subject to many different factors of variation, especially in unconstrained in-the-wild scenarios. For most tasks involving such images, e.g. expression recognition from video streams, having enough labeled data is…

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a…

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…

Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature of frame prediction; multiple potential futures can arise…

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…

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…

Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to…

While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning - leveraging unlabeled examples to learn about the structure of a domain - remains a difficult…

Video representation learning has recently attracted attention in computer vision due to its applications for activity and scene forecasting or vision-based planning and control. Video prediction models often learn a latent representation…

This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce…

In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames. Existing methods tend to focus only on how to use temporal information, which often leads to networks…

Disentangled representation learning offers useful properties such as dimension reduction and interpretability, which are essential to modern deep learning approaches. Although deep learning techniques have been widely applied to…