Hence, which layer(s) we choose as our feature embedding will have an effect on the outcome of the local spatial prediction problem. While more abstract high-level features are expected to better capture the internal predictive structure of an object, it will be more difficult to attribute the error of the prediction network to the exact image location. On the other hand, while more low-level features can be localized more accurately, they may lack the expressiveness to capture high-level properties of objects. Nonetheless, in practice we find that a spatial feature embedding based on earlier layers of the encoder works well (see also Section 5.3 for an ablation). Local Spatial Prediction Task Using the learned spatial feature embedding we seek out salient regions of the input image that correspond to object parts. Our approach is based on the idea that objects correspond to local regions in feature space that have high internal predictive structure, which allows us to formulate the following local spatial prediction (LSP) task. For each location in the learned spatial feature embedding, we seek to predict the value of the features (across the feature maps) from its neighbouring feature values. When neighbouring areas correspond to the same object-(part), i.e. they regularly appear together, we expect that this prediction problem is easy (green arrow in Figure 3).

We present a novel way for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it hierarchically to encourage multi-scale understanding. Motivated by their effectiveness in supervised learning, we first introduce spatial-temporal feature learning decoupling and hierarchical learning to the context of unsupervised video learning. In particular, our method directs the network to separately capture spatial and temporal features on the basis of contrastive learning via manipulating augmentations as regularization, and further solve such proxy tasks hierarchically by optimizing towards a compound contrastive loss. Experiments show that our proposed Hierarchically Decoupled Spatial-Temporal Contrast (HDC) achieves substantial gains over directly learning spatial-temporal features as a whole and significantly outperforms other state-of-the-art unsupervised methods on downstream action recognition benchmarks on UCF101 and HMDB51. We will release our code and pretrained weights.

Geospatial development links your data to places on the Earth's surface. Its analysis is used in almost every industry to answer location type questions. Combined with the power of the Python programming language, which is becoming the de facto spatial scripting choice for developers and analysts worldwide, this technology will help you to solve real-world spatial problems. This book begins by tackling the installation of the necessary software dependencies and libraries needed to perform spatial analysis with Python. From there, the next logical step is to prepare our data for analysis; we will do this by building up our tool box to deal with data preparation, transformations, and projections.

Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity. In the recent months, a wide spectrum of efficient, fast Transformers have been proposed to tackle this problem, more often than not claiming superior or comparable model quality to vanilla Transformer models. To this date, there is no well-established consensus on how to evaluate this class of models. Moreover, inconsistent benchmarking on a wide spectrum of tasks and datasets makes it difficult to assess relative model quality amongst many models. This paper proposes a systematic and unified benchmark, Long-Range Arena, specifically focused on evaluating model quality under long-context scenarios. Our benchmark is a suite of tasks consisting of sequences ranging from 1K to 16K tokens, encompassing a wide range of data types and modalities such as text, natural, synthetic images, and mathematical expressions requiring similarity, structural, and visual-spatial reasoning. We systematically evaluate ten well-established long-range Transformer models (Reformers, Linformers, Linear Transformers, Sinkhorn Transformers, Performers, Synthesizers, Sparse Transformers, and Longformers) on our newly proposed benchmark suite. Long-Range Arena paves the way towards better understanding this class of efficient Transformer models, facilitates more research in this direction, and presents new challenging tasks to tackle. Transformers (Vaswani et al., 2017) are ubiquitously state-of-the-art across many modalities, from language (Devlin et al., 2018; Raffel et al., 2019; Child et al., 2019) to images (Tan & Bansal, 2019; Lu et al., 2019) to protein sequences (Rives et al., 2019). A common weakness of Transformers is their quadratic memory complexity within the self-attention mechanism that restricts their potential application to domains requiring longer sequence lengths. To date, a dizzying number of efficient Transformer models ('xformers') have been proposed to tackle this problem (Liu et al., 2018; Kitaev et al., 2020; Wang et al., 2020; Tay et al., 2020b; Katharopoulos et al., 2020). Many of these models demonstrate comparable performance to the vanilla Transformer model while successfully reducing the memory complexity of the self-attention mechanism. An overview of this research area can be found in (Tay et al., 2020c).

Esports, despite its expanding interest, lacks fundamental sports analytics resources such as accessible data or proven and reproducible analytical frameworks. Even Counter-Strike: Global Offensive (CSGO), the second most popular esport, suffers from these problems. Thus, quantitative evaluation of CSGO players, a task important to teams, media, bettors and fans, is difficult. To address this, we introduce (1) a data model for CSGO with an open-source implementation; (2) a graph distance measure for defining distances in CSGO; and (3) a context-aware framework to value players' actions based on changes in their team's chances of winning. Using over 70 million in-game CSGO events, we demonstrate our framework's consistency and independence compared to existing valuation frameworks. We also provide use cases demonstrating high-impact play identification and uncertainty estimation.

Navigation is an essential ability for mobile agents to be completely autonomous and able to perform complex actions. However, the problem of navigation for agents with limited (or no) perception of the world, or devoid of a fully defined motion model, has received little attention from research in AI and Robotics. One way to tackle this problem is to use guided navigation, in which other autonomous agents, endowed with perception, can combine their distinct viewpoints to infer the localisation and the appropriate commands to guide a sensory deprived agent through a particular path. Due to the limited knowledge about the physical and perceptual characteristics of the guided agent, this task should be conducted on a level of abstraction allowing the use of a generic motion model, and high-level commands, that can be applied by any type of autonomous agents, including humans. The main task considered in this work is, given a group of autonomous agents perceiving their common environment with their independent, egocentric and local vision sensors, the development and evaluation of algorithms capable of producing a set of high-level commands (involving qualitative directions: e.g. move left, go straight ahead) capable of guiding a sensory deprived robot to a goal location.

Modeling place functions from a computational perspective is a prevalent research topic. The technology of embedding enables a new approach that allows modeling the function of a place by its chronological context as part of a trajectory. The embedding similarity was previously proposed as a new metric for measuring the similarity of place functions, with some preliminary results. This study explores if this approach is meaningful for geographical units at a much smaller geographical granularity compared to previous studies. In addition, this study investigates if the geographical distance can influence the embedding similarity. The empirical evaluations based on a big vehicle trajectory data set confirm that the embedding similarity can be a metric proxy for place functions. However, the results also show that the embedding similarity is still bounded by the distance at the local scale.

A month ago we finished Why R? 2020 conference. We had an pleasure to host Roger Bivand, a professor at Norwegian School of Economics and Member of R Foundation. This post contains a biography of the speaker and an abstract of his talk: Applied Spatial Data Analysis with R – retrospect and prospect. When we began over 20 years ago, spatial data was usually found in proprietary software, usually geographical information systems, and most positional data was very hard to acquire. Statistics for spatial data existed, but largely without convenient access to positional data.

Spatial knowledge is a fundamental building block for the development of advanced perceptive and cognitive abilities. Traditionally, in robotics, the Euclidean (x, y, z) coordinate system and the agent's forward model are defined a priori. We show that a naive agent can autonomously build an internal coordinate system, with the same dimension and metric regularity as the external space, simply by learning to predict the outcome of sensorimotor transitions in a self-supervised way.

Collections of probability distributions arise in a variety of statistical applications ranging from user activity pattern analysis to brain connectomics. In practice these distributions are represented by histograms over diverse domain types including finite intervals, circles, cylinders, spheres, other manifolds, and graphs. This paper introduces an approach for detecting differences between two collections of histograms over such general domains. To this end, we introduce the intrinsic slicing construction that yields a novel class of Wasserstein distances on manifolds and graphs. These distances are Hilbert embeddable, which allows us to reduce the histogram collection comparison problem to the comparison of means in a high-dimensional Euclidean space. We develop a hypothesis testing procedure based on conducting t-tests on each dimension of this embedding, then combining the resulting p-values using recently proposed p-value combination techniques. Our numerical experiments in a variety of data settings show that the resulting tests are powerful and the p-values are well-calibrated. Example applications to user activity patterns, spatial data, and brain connectomics are provided.