English
Related papers

Related papers: A causal convolutional neural network for multi-su…

200 papers

We present a generative model that learns to synthesize human motion from limited training sequences. Our framework provides conditional generation and blending across multiple temporal resolutions. The model adeptly captures human motion…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 David Eduardo Moreno-Villamarín , Anna Hilsmann , Peter Eisert

We present Causal Generative Neural Networks (CGNNs) to learn functional causal models from observational data. CGNNs leverage conditional independencies and distributional asymmetries to discover bivariate and multivariate causal…

We introduce a new approach to functional causal modeling from observational data, called Causal Generative Neural Networks (CGNN). CGNN leverages the power of neural networks to learn a generative model of the joint distribution of the…

Traditional machine learning methods for movement recognition often struggle with limited model interpretability and a lack of insight into human movement dynamics. This study introduces a novel representation learning framework based on…

Machine Learning · Computer Science 2025-07-01 Xingrui Gu , Chuyi Jiang , Erte Wang , Qiang Cui , Leimin Tian , Lianlong Wu , Siyang Song , Chuang Yu

Recent years have seen rapid progress at the intersection between causality and machine learning. Motivated by scientific applications involving high-dimensional data, in particular in biomedicine, we propose a deep neural architecture for…

Machine Learning · Computer Science 2022-12-12 Kai Lagemann , Christian Lagemann , Bernd Taschler , Sach Mukherjee

We study the problem of synthesizing a number of likely future frames from a single input image. In contrast to traditional methods that have tackled this problem in a deterministic or non-parametric way, we propose to model future frames…

Computer Vision and Pattern Recognition · Computer Science 2019-08-13 Tianfan Xue , Jiajun Wu , Katherine L. Bouman , William T. Freeman

Data-driven modeling of human motions is ubiquitous in computer graphics and computer vision applications, such as synthesizing realistic motions or recognizing actions. Recent research has shown that such problems can be approached by…

Graphics · Computer Science 2019-08-21 He Wang , Edmond S. L. Ho , Hubert P. H. Shum , Zhanxing Zhu

This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to…

Machine Learning · Computer Science 2019-07-23 Aravind Sankar , Xinyang Zhang , Kevin Chen-Chuan Chang

We study the problem of synthesizing a number of likely future frames from a single input image. In contrast to traditional methods, which have tackled this problem in a deterministic or non-parametric way, we propose a novel approach that…

Computer Vision and Pattern Recognition · Computer Science 2016-07-12 Tianfan Xue , Jiajun Wu , Katherine L. Bouman , William T. Freeman

Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of…

Computer Vision and Pattern Recognition · Computer Science 2015-11-09 Leon A. Gatys , Alexander S. Ecker , Matthias Bethge

Existing conditional video prediction approaches train a network from large databases and generalize to previously unseen data. We take the opposite stance, and introduce a model that learns from the first frames of a given video and…

Computer Vision and Pattern Recognition · Computer Science 2018-12-27 Veronique Prinet

We propose a new attribution method for neural networks developed using first principles of causality (to the best of our knowledge, the first such). The neural network architecture is viewed as a Structural Causal Model, and a methodology…

Machine Learning · Computer Science 2019-07-04 Aditya Chattopadhyay , Piyushi Manupriya , Anirban Sarkar , Vineeth N Balasubramanian

It is commonplace to encounter heterogeneous or nonstationary data, of which the underlying generating process changes across domains or over time. Such a distribution shift feature presents both challenges and opportunities for causal…

Machine Learning · Computer Science 2020-06-26 Biwei Huang , Kun Zhang , Jiji Zhang , Joseph Ramsey , Ruben Sanchez-Romero , Clark Glymour , Bernhard Schölkopf

Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks. A reoccurring challenge is how to enable a model to generate a rich variety of samples from the entire target distribution, rather…

Graphics · Computer Science 2019-09-04 Nadav Schor , Oren Katzir , Hao Zhang , Daniel Cohen-Or

Imitation learning enables high-fidelity, vision-based learning of policies within rich, photorealistic environments. However, such techniques often rely on traditional discrete-time neural models and face difficulties in generalizing to…

Machine Learning · Computer Science 2021-08-18 Charles Vorbach , Ramin Hasani , Alexander Amini , Mathias Lechner , Daniela Rus

We propose a novel skeleton-based representation for 3D action recognition in videos using Deep Convolutional Neural Networks (D-CNNs). Two key issues have been addressed: First, how to construct a robust representation that easily captures…

Computer Vision and Pattern Recognition · Computer Science 2018-07-19 Huy Hieu Pham , Louahdi Khoudour , Alain Crouzil , Pablo Zegers , Sergio A. Velastin

We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Chengzhi Mao , Augustine Cha , Amogh Gupta , Hao Wang , Junfeng Yang , Carl Vondrick

We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes…

Traditional Low-Light Image Enhancement (LLIE) methods primarily focus on uniform brightness adjustment, often neglecting instance-level semantic information and the inherent characteristics of different features. To address these…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Tongshun Zhang , Pingping Liu , Yubing Lu , Mengen Cai , Zijian Zhang , Zhe Zhang , Qiuzhan Zhou

In this paper, we proposed a effective but extensible residual one-dimensional convolution neural network as base network, based on the this network, we proposed four subnets to explore the features of skeleton sequences from each aspect.…

Computer Vision and Pattern Recognition · Computer Science 2018-08-01 Yangyang Xu , Lei Wang
‹ Prev 1 2 3 10 Next ›