Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy.
To tackle the aforementioned challenges, in this paper, we propose a novel algorithm for exploring influential users in unknown networks, which can estimate the influential relationships among users based on their historical behaviors and without knowing the topology of the network.
First, we conduct a critical point analysis of the error function and provide technical insights on optimisation and design choices for neural networks.
Distance-based dynamic texture recognition is an important research field in multimedia processing with applications ranging from retrieval to segmentation of video data.
This white paper provides an introduction and discussion of this emerging field in machine learning research.
Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem.
Ranked #11 on Video Instance Segmentation on YouTube-VIS validation
Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and localization of vision-based robots.
In this paper, we employ collaborative subgraphs (CSGs) and metapaths to form metapath-aware subgraphs, which explicitly capture sequential semantics in graph structures.
Ranked #1 on Link Prediction on Yelp
Camera localization is a fundamental and key component of autonomous driving vehicles and mobile robots to localize themselves globally for further environment perception, path planning and motion control.
Accordingly, we decompose the instance segmentation into two parallel subtasks: Local Shape prediction that separates instances even in overlapping conditions, and Global Saliency generation that segments the whole image in a pixel-to-pixel manner.
The dataset is publicly accessible to the community for boosting the advance of face parsing. 1 Second, a simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a three-branch network with elaborately developed loss functions to fully exploit the boundary information.
Ranked #5 on Face Parsing on LaPa
Each image is provided with accurate annotation of a 11-category pixel-level label map along with coordinates of 106-point landmarks.
no code implementations • 9 May 2019 • Yinglu Liu, Hao Shen, Yue Si, Xiaobo Wang, Xiangyu Zhu, Hailin Shi, Zhibin Hong, Hanqi Guo, Ziyuan Guo, Yanqin Chen, Bi Li, Teng Xi, Jun Yu, Haonian Xie, Guochen Xie, Mengyan Li, Qing Lu, Zengfu Wang, Shenqi Lai, Zhenhua Chai, Xiaoming Wei
However, previous competitions on facial landmark localization (i. e., the 300-W, 300-VW and Menpo challenges) aim to predict 68-point landmarks, which are incompetent to depict the structure of facial components.
There are some inadequacies in the language description of this paper that require further improvement.
For localization, we show that Generative Map achieves comparable performance with current regression models.
Among many unsolved puzzles in theories of Deep Neural Networks (DNNs), there are three most fundamental challenges that highly demand solutions, namely, expressibility, optimisability, and generalisability.
We propose a generic algorithmic framework, which leverages two classic representation learning paradigms, i. e., sparse representation and the trace quotient criterion.
This work studies the problem of modeling visual processes by leveraging deep generative architectures for learning linear, Gaussian representations from observed sequences.
Training deep neural networks for solving machine learning problems is one great challenge in the field, mainly due to its associated optimisation problem being highly non-convex.
In this work, we investigate the application of Reinforcement Learning to two well known decision dilemmas, namely Newcomb's Problem and Prisoner's Dilemma.
This paper presents an algorithm that allows to learn low dimensional representations of images in an unsupervised manner.
Our approach employs a recently developed method, the so-called Scattering transform, for the process of feature extraction in texture retrieval.