Although lyrics generation has achieved significant progress in recent years, it has limited practical applications because the generated lyrics cannot be performed without composing compatible melodies. In this work, we bridge this practical gap by proposing a song rewriting system which rewrites the lyrics of an existing song such that the generated lyrics are compatible with the rhythm of the existing melody and thus singable. In particular, we propose SongRewriter, a controllable Chinese lyric generation and editing system which assists users without prior knowledge of melody composition. The system is trained by a randomized multi-level masking strategy which produces a unified model for generating entirely new lyrics or editing a few fragments. To improve the controllabiliy of the generation process, we further incorporate a keyword prompt to control the lexical choices of the content and propose novel decoding constraints and a vowel modeling task to enable flexible end and internal rhyme schemes. While prior rhyming metrics are mainly for rap lyrics, we propose three novel rhyming evaluation metrics for song lyrics. Both automatic and human evaluations show that the proposed model performs better than the state-of-the-art models in both contents and rhyming quality. Our code and models implemented in MindSpore Lite tool will be available.

从传统上讲，地球系统（例如天气和气候）的预测依赖于具有复杂物理模型的数值模拟，因此在计算中既昂贵又对领域专业知识的需求既昂贵。在过去十年中时空地球观察数据的爆炸性增长中，应用深度学习（DL）的数据驱动模型表明了各种地球系统预测任务的潜力。尽管在其他领域取得了广泛的成功，但作为新兴DL架构的变压器在该领域的采用量有限。在本文中，我们提出了Earthformer，这是一种用于地球系统预测的时空变压器。 Earthformer基于一个通用，灵活和有效的时空注意块，名为Cuboid的注意力。这个想法是将数据分解为立方体，并平行应用立方体级别的自我注意力。这些立方体与全球矢量的集合进一步相关。我们对MovingMnist数据集和新提出的混沌N体MNIST数据集进行了实验，以验证Cuboid注意的有效性，并找出地球形式的最佳设计。关于降水现象和El Nino/Southern振荡（ENSO）预测的两个现实基准测试的实验表明，Earthformer实现了最新的性能。

自主驾驶的当代深度学习对象检测方法通常会假定前缀类别的共同交通参与者，例如行人和汽车。大多数现有的探测器无法检测到罕见的物体和拐角案例（例如，越过街道的狗），这可能会导致某些情况下发生严重的事故，从而使真实世界应用可靠的自动驾驶不确定。阻碍了真正可靠的自动驾驶系统发展的主要原因是缺乏评估对象探测器在角案例上的性能的公共数据集。因此，我们介绍了一个名为CODA的具有挑战性的数据集，该数据集揭示了基于视力的检测器的关键问题。该数据集由1500个精心选择的现实世界驾驶场景组成，每个场景平均包含四个对象级角案例（平均），涵盖30多个对象类别。在CODA上，在大型自动驾驶数据集中训练的标准对象探测器的性能显着下降到3月的12.8％。此外，我们试验了最新的开放世界对象检测器，发现它也无法可靠地识别尾声中的新对象，这表明对自主驾驶的强大感知系统可能远离触及。我们希望我们的CODA数据集有助于对现实世界自动驾驶的可靠检测进行进一步的研究。我们的数据集将在https://coda-dataset.github.io上发布。

The goal of precipitation nowcasting is to predict the future rainfall intensity in a local region over a relatively short period of time. Very few previous studies have examined this crucial and challenging weather forecasting problem from the machine learning perspective. In this paper, we formulate precipitation nowcasting as a spatiotemporal sequence forecasting problem in which both the input and the prediction target are spatiotemporal sequences. By extending the fully connected LSTM (FC-LSTM) to have convolutional structures in both the input-to-state and state-to-state transitions, we propose the convolutional LSTM (ConvLSTM) and use it to build an end-to-end trainable model for the precipitation nowcasting problem. Experiments show that our ConvLSTM network captures spatiotemporal correlations better and consistently outperforms FC-LSTM and the state-of-theart operational ROVER algorithm for precipitation nowcasting.

The task of reconstructing 3D human motion has wideranging applications. The gold standard Motion capture (MoCap) systems are accurate but inaccessible to the general public due to their cost, hardware and space constraints. In contrast, monocular human mesh recovery (HMR) methods are much more accessible than MoCap as they take single-view videos as inputs. Replacing the multi-view Mo- Cap systems with a monocular HMR method would break the current barriers to collecting accurate 3D motion thus making exciting applications like motion analysis and motiondriven animation accessible to the general public. However, performance of existing HMR methods degrade when the video contains challenging and dynamic motion that is not in existing MoCap datasets used for training. This reduces its appeal as dynamic motion is frequently the target in 3D motion recovery in the aforementioned applications. Our study aims to bridge the gap between monocular HMR and multi-view MoCap systems by leveraging information shared across multiple video instances of the same action. We introduce the Neural Motion (NeMo) field. It is optimized to represent the underlying 3D motions across a set of videos of the same action. Empirically, we show that NeMo can recover 3D motion in sports using videos from the Penn Action dataset, where NeMo outperforms existing HMR methods in terms of 2D keypoint detection. To further validate NeMo using 3D metrics, we collected a small MoCap dataset mimicking actions in Penn Action,and show that NeMo achieves better 3D reconstruction compared to various baselines.

This work builds on the models and concepts presented in part 1 to learn approximate dictionary representations of Koopman operators from data. Part I of this paper presented a methodology for arguing the subspace invariance of a Koopman dictionary. This methodology was demonstrated on the state-inclusive logistic lifting (SILL) basis. This is an affine basis augmented with conjunctive logistic functions. The SILL dictionary's nonlinear functions are homogeneous, a norm in data-driven dictionary learning of Koopman operators. In this paper, we discover that structured mixing of heterogeneous dictionary functions drawn from different classes of nonlinear functions achieve the same accuracy and dimensional scaling as the deep-learning-based deepDMD algorithm. We specifically show this by building a heterogeneous dictionary comprised of SILL functions and conjunctive radial basis functions (RBFs). This mixed dictionary achieves the same accuracy and dimensional scaling as deepDMD with an order of magnitude reduction in parameters, while maintaining geometric interpretability. These results strengthen the viability of dictionary-based Koopman models to solving high-dimensional nonlinear learning problems.

Koopman operators model nonlinear dynamics as a linear dynamic system acting on a nonlinear function as the state. This nonstandard state is often called a Koopman observable and is usually approximated numerically by a superposition of functions drawn from a dictionary. In a widely used algorithm, Extended Dynamic Mode Decomposition, the dictionary functions are drawn from a fixed class of functions. Recently, deep learning combined with EDMD has been used to learn novel dictionary functions in an algorithm called deep dynamic mode decomposition (deepDMD). The learned representation both (1) accurately models and (2) scales well with the dimension of the original nonlinear system. In this paper we analyze the learned dictionaries from deepDMD and explore the theoretical basis for their strong performance. We explore State-Inclusive Logistic Lifting (SILL) dictionary functions to approximate Koopman observables. Error analysis of these dictionary functions show they satisfy a property of subspace approximation, which we define as uniform finite approximate closure. Our results provide a hypothesis to explain the success of deep neural networks in learning numerical approximations to Koopman operators. Part 2 of this paper will extend this explanation by demonstrating the subspace invariant of heterogeneous dictionaries and presenting a head-to-head numerical comparison of deepDMD and low-parameter heterogeneous dictionary learning.

Electronic Health Records (EHRs) hold detailed longitudinal information about each patient's health status and general clinical history, a large portion of which is stored within the unstructured text. Temporal modelling of this medical history, which considers the sequence of events, can be used to forecast and simulate future events, estimate risk, suggest alternative diagnoses or forecast complications. While most prediction approaches use mainly structured data or a subset of single-domain forecasts and outcomes, we processed the entire free-text portion of EHRs for longitudinal modelling. We present Foresight, a novel GPT3-based pipeline that uses NER+L tools (i.e. MedCAT) to convert document text into structured, coded concepts, followed by providing probabilistic forecasts for future medical events such as disorders, medications, symptoms and interventions. Since large portions of EHR data are in text form, such an approach benefits from a granular and detailed view of a patient while introducing modest additional noise. On tests in two large UK hospitals (King's College Hospital, South London and Maudsley) and the US MIMIC-III dataset precision@10 of 0.80, 0.81 and 0.91 was achieved for forecasting the next biomedical concept. Foresight was also validated on 34 synthetic patient timelines by 5 clinicians and achieved relevancy of 97% for the top forecasted candidate disorder. Foresight can be easily trained and deployed locally as it only requires free-text data (as a minimum). As a generative model, it can simulate follow-on disorders, medications and interventions for as many steps as required. Foresight is a general-purpose model for biomedical concept modelling that can be used for real-world risk estimation, virtual trials and clinical research to study the progression of diseases, simulate interventions and counterfactuals, and for educational purposes.

Open World Object Detection (OWOD) is a new and challenging computer vision task that bridges the gap between classic object detection (OD) benchmarks and object detection in the real world. In addition to detecting and classifying seen/labeled objects, OWOD algorithms are expected to detect novel/unknown objects - which can be classified and incrementally learned. In standard OD, object proposals not overlapping with a labeled object are automatically classified as background. Therefore, simply applying OD methods to OWOD fails as unknown objects would be predicted as background. The challenge of detecting unknown objects stems from the lack of supervision in distinguishing unknown objects and background object proposals. Previous OWOD methods have attempted to overcome this issue by generating supervision using pseudo-labeling - however, unknown object detection has remained low. Probabilistic/generative models may provide a solution for this challenge. Herein, we introduce a novel probabilistic framework for objectness estimation, where we alternate between probability distribution estimation and objectness likelihood maximization of known objects in the embedded feature space - ultimately allowing us to estimate the objectness probability of different proposals. The resulting Probabilistic Objectness transformer-based open-world detector, PROB, integrates our framework into traditional object detection models, adapting them for the open-world setting. Comprehensive experiments on OWOD benchmarks show that PROB outperforms all existing OWOD methods in both unknown object detection ($\sim 2\times$ unknown recall) and known object detection ($\sim 10\%$ mAP). Our code will be made available upon publication at https://github.com/orrzohar/PROB.

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi.