Related papers: Mutual Information Based Method for Unsupervised D…
Video frame interpolation and prediction aim to synthesize frames in-between and subsequent to existing frames, respectively. Despite being closely-related, these two tasks are traditionally studied with different model architectures, or…
We propose Video Gaussian Masked Autoencoders (Video-GMAE), a self-supervised approach for representation learning that encodes a sequence of images into a set of Gaussian splats moving over time. Representing a video as a set of Gaussians…
Visual data can be understood at different levels of granularity, where global features correspond to semantic-level information and local features correspond to texture patterns. In this work, we propose a framework, called SPLIT, which…
We introduce physics-informed multimodal autoencoders (PIMA) - a variational inference framework for discovering shared information in multimodal scientific datasets representative of high-throughput testing. Individual modalities are…
Multimodal VAEs seek to model the joint distribution over heterogeneous data (e.g.\ vision, language), whilst also capturing a shared representation across such modalities. Prior work has typically combined information from the modalities…
We propose a deep video prediction model conditioned on a single image and an action class. To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints. The input image is…
Scene Text Recognition requires modeling visual structures that evolve from coarse layouts to fine-grained character strokes. Training such models relies on large amounts of annotated data. Recent self-supervised approaches, such as Masked…
Despite the remarkable capabilities of Multimodal Large Language Models (MLLMs), they still suffer from visual fading in long-context scenarios. Specifically, the attention to visual tokens diminishes as the text sequence lengthens, leading…
In monocular videos that capture dynamic scenes, estimating the 3D geometry of video contents has been a fundamental challenge in computer vision. Specifically, the task is significantly challenged by the object motion, where existing…
Video prediction, predicting future frames from the previous ones, has broad applications such as autonomous driving and weather forecasting. Existing state-of-the-art methods typically focus on extracting either spatial, temporal, or…
Understanding how neural populations in higher visual areas encode object-centered visual information remains a central challenge in computational neuroscience. Prior works have investigated representational alignment between artificial…
Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost…
This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore actual motion when aligning…
A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting…
Video extrapolation in space and time (VEST) enables viewers to forecast a 3D scene into the future and view it from novel viewpoints. Recent methods propose to learn an entangled representation, aiming to model layered scene geometry,…
Multi-modal visual understanding of images with prompts involves using various visual and textual cues to enhance the semantic understanding of images. This approach combines both vision and language processing to generate more accurate…
In modern video coding standards, block-based inter prediction is widely adopted, which brings high compression efficiency. However, in natural videos, there are usually multiple moving objects of arbitrary shapes, resulting in complex…
Stochastic video prediction enables the consideration of uncertainty in future motion, thereby providing a better reflection of the dynamic nature of the environment. Stochastic video prediction methods based on image auto-regressive…
Most existing works on disentangled representation learning are solely built upon an marginal independence assumption: all factors in disentangled representations should be statistically independent. This assumption is necessary but…
Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the…