相关论文: Mutual Information Based Method for Unsupervised D…

Our goal is to predict future video frames given a sequence of input frames. Despite large amounts of video data, this remains a challenging task because of the high-dimensionality of video frames. We address this challenge by proposing the…

Temporal modeling is crucial for multi-frame human pose estimation. Most existing methods directly employ optical flow or deformable convolution to predict full-spectrum motion fields, which might incur numerous irrelevant cues, such as a…

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,…

In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation…

Missing data poses significant challenges while learning representations of video sequences. We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that imputes and predicts future video frames in the presence of…

We introduce MGP-VAE (Multi-disentangled-features Gaussian Processes Variational AutoEncoder), a variational autoencoder which uses Gaussian processes (GP) to model the latent space for the unsupervised learning of disentangled…

The key challenge in unaligned multimodal language sequences lies in effectively integrating information from various modalities to obtain a refined multimodal joint representation. Recently, the disentangle and fuse methods have achieved…

Multi-View Clustering (MVC) has gained significant attention for its ability to leverage complementary information across diverse views. However, existing deep MVC methods often struggle with view-distribution entanglement during cross-view…

Establishing correspondence between images or scenes is a significant challenge in computer vision, especially given occlusions, viewpoint changes, and varying object appearances. In this paper, we present Siamese Masked Autoencoders…

Learning interpretable and disentangled representations of data is a key topic in machine learning research. Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. It employs a clear…

We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/decoder framework. Our key principles are symmetry and mutual…

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…

Independent components within low-dimensional representations are essential inputs in several downstream tasks, and provide explanations over the observed data. Video-based disentangled factors of variation provide low-dimensional…

We introduce the Mutual Information Machine (MIM), a probabilistic auto-encoder for learning joint distributions over observations and latent variables. MIM reflects three design principles: 1) low divergence, to encourage the encoder and…

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…

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…

It is crucial to choose actions from an appropriate distribution while learning a sequential decision-making process in which a set of actions is expected given the states and previous reward. Yet, if there are more than two latent…

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…

We introduce a novel representation learning method to disentangle pose-dependent as well as view-dependent factors from 2D human poses. The method trains a network using cross-view mutual information maximization (CV-MIM) which maximizes…

Multi-frame human pose estimation has long been a compelling and fundamental problem in computer vision. This task is challenging due to fast motion and pose occlusion that frequently occur in videos. State-of-the-art methods strive to…