As an important part of Artificial Intelligence (AI), Question Answering (QA) aims at generating answers to questions phrased in natural language. While there has been substantial progress in open-domain question answering, QA systems are still struggling to answer questions which involve geographic entities or concepts and that require spatial operations. In this paper, we discuss the problem of geographic question answering (GeoQA). We first investigate the reasons why geographic questions are difficult to answer by analyzing challenges of geographic questions. We discuss the uniqueness of geographic questions compared to general QA. Then we review existing work on GeoQA and classify them by the types of questions they can address. Based on this survey, we provide a generic classification framework for geographic questions. Finally, we conclude our work by pointing out unique future research directions for GeoQA.

Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in real-world applications. However, it is particularly challenging to learn a class-invariant spatial-temporal representation in such a setting. To address this, we propose a novel matching-based few-shot learning strategy for video sequences in this work. Our main idea is to introduce an implicit temporal alignment for a video pair, capable of estimating the similarity between them in an accurate and robust manner. Moreover, we design an effective context encoding module to incorporate spatial and feature channel context, resulting in better modeling of intra-class variations. To train our model, we develop a multi-task loss for learning video matching, leading to video features with better generalization. Extensive experimental results on two challenging benchmarks, show that our method outperforms the prior arts with a sizable margin on SomethingSomething-V2 and competitive results on Kinetics.

One of the common problems with learning image processing is the high cost of software. In this course, I entirely use open source software including the Google Earth Engine Python API and Colab. All sample data and script will be provided to you as an added bonus throughout the course. Jump in right now and enroll.

Description Do you want to access satellite sensors using Earth Engine Python API and Google Colab? Do you want to learn the spatial data science on the cloud? Do you want to become a geospatial data scientist? I will provide you with hands-on training with example data, sample scripts, and real-world applications. By taking this course, you be able to install Anaconda and Jupyter Notebook.

Topological data analysis, including persistent homology, has undergone significant development in recent years. However, one outstanding challenge is to build a coherent statistical inference procedure on persistent diagrams. The paired dependent data structure, as birth and death in persistent diagrams, adds additional complexity to the development. In this paper, we present a new lattice path representation for persistent diagrams. A new exact statistical inference procedure is developed for lattice paths via combinatorial enumerations. The proposed lattice path method is applied to the topological characterization of the protein structures of COVID-19 viruse. We demonstrate that there are topological changes during the conformation change of spike proteins that are needed to initiate the infection of host cells.

Spatial reasoning on multi-view line drawings by state-of-the-art supervised deep networks is recently shown with puzzling low performances on the SPARE3D dataset. To study the reason behind the low performance and to further our understandings of these tasks, we design controlled experiments on both input data and network designs. Guided by the hindsight from these experiment results, we propose a simple contrastive learning approach along with other network modifications to improve the baseline performance. Our approach uses a self-supervised binary classification network to compare the line drawing differences between various views of any two similar 3D objects. It enables deep networks to effectively learn detail-sensitive yet view-invariant line drawing representations of 3D objects. Experiments show that our method could significantly increase the baseline performance in SPARE3D, while some popular self-supervised learning methods cannot.

Spatial data is a rich source of information for actuarial applications: knowledge of a risk's location could improve an insurance company's ratemaking, reserving or risk management processes. Insurance companies with high exposures in a territory typically have a competitive advantage since they may use historical losses in a region to model spatial risk non-parametrically. Relying on geographic losses is problematic for areas where past loss data is unavailable. This paper presents a method based on data (instead of smoothing historical insurance claim losses) to construct a geographic ratemaking model. In particular, we construct spatial features within a complex representation model, then use the features as inputs to a simpler predictive model (like a generalized linear model). Our approach generates predictions with smaller bias and smaller variance than other spatial interpolation models such as bivariate splines in most situations. This method also enables us to generate rates in territories with no historical experience.

Artificial intelligence for autonomous driving must meet strict requirements on safety and robustness, which motivates the thorough validation of learned models. However, current validation approaches mostly require ground truth data and are thus both cost-intensive and limited in their applicability. We propose to overcome these limitations by a model agnostic validation using a-priori knowledge from street maps. In particular, we show how to validate semantic segmentation masks and demonstrate the potential of our approach using OpenStreetMap. We introduce validation metrics that indicate false positive or negative road segments. Besides the validation approach, we present a method to correct the vehicle's GPS position so that a more accurate localization can be used for the street-map based validation. Lastly, we present quantitative results on the Cityscapes dataset indicating that our validation approach can indeed uncover errors in semantic segmentation masks.

This paper proposes a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work and is challenging for state-of-the-art language models (LM). We propose a distant supervision method to improve on this task. Specifically, we design grammar and reasoning rules to automatically generate a spatial description of visual scenes and corresponding QA pairs. Experiments show that further pretraining LMs on these automatically generated data significantly improves LMs' capability on spatial understanding, which in turn helps to better solve two external datasets, bAbI, and boolQ. We hope that this work can foster investigations into more sophisticated models for spatial reasoning over text.

Video-based person re-identification (Re-ID) aims to retrieve video sequences of the same person under non-overlapping cameras. Previous methods usually focus on limited views, such as spatial, temporal or spatial-temporal view, which lack of the observations in different feature domains. To capture richer perceptions and extract more comprehensive video representations, in this paper we propose a novel framework named Trigeminal Transformers (TMT) for video-based person Re-ID. More specifically, we design a trigeminal feature extractor to jointly transform raw video data into spatial, temporal and spatial-temporal domain. Besides, inspired by the great success of vision transformer, we introduce the transformer structure for video-based person Re-ID. In our work, three self-view transformers are proposed to exploit the relationships between local features for information enhancement in spatial, temporal and spatial-temporal domains. Moreover, a cross-view transformer is proposed to aggregate the multi-view features for comprehensive video representations. The experimental results indicate that our approach can achieve better performance than other state-of-the-art approaches on public Re-ID benchmarks. We will release the code for model reproduction.