Video-language pre-training has advanced the performance of various downstream video-language tasks. However, most previous methods directly inherit or adapt typical image-language pre-training paradigms to video-language pre-training, thus not fully exploiting the unique characteristic of video, i.e., temporal. In this paper, we propose a Hierarchical Temporal-Aware video-language pre-training framework, HiTeA, with two novel pre-training tasks for modeling cross-modal alignment between moments and texts as well as the temporal relations of video-text pairs. Specifically, we propose a cross-modal moment exploration task to explore moments in videos, which results in detailed video moment representation. Besides, the inherent temporal relations are captured by aligning video-text pairs as a whole in different time resolutions with multi-modal temporal relation exploration task. Furthermore, we introduce the shuffling test to evaluate the temporal reliance of datasets and video-language pre-training models. We achieve state-of-the-art results on 15 well-established video-language understanding and generation tasks, especially on temporal-oriented datasets (e.g., SSv2-Template and SSv2-Label) with 8.6% and 11.1% improvement respectively. HiTeA also demonstrates strong generalization ability when directly transferred to downstream tasks in a zero-shot manner. Models and demo will be available on ModelScope.

Marine waves significantly disturb the unmanned surface vehicle (USV) motion. An unmanned aerial vehicle (UAV) can hardly land on a USV that undergoes irregular motion. An oversized landing platform is usually necessary to guarantee the landing safety, which limits the number of UAVs that can be carried. We propose a landing system assisted by tether and robot manipulation. The system can land multiple UAVs without increasing the USV's size. An MPC controller stabilizes the end-effector and tracks the UAVs, and an adaptive estimator addresses the disturbance caused by the base motion. The working strategy of the system is designed to plan the motion of each device. We have validated the manipulator controller through simulations and well-controlled indoor experiments. During the field tests, the proposed system caught and placed the UAVs when the disturbed USV roll range was approximately 12 degrees.

Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. However, the existing works fail to address all these practical concerns in FL: limited communication resources, dynamic network conditions and heterogeneous client properties, which slow down the convergence of FL. To tackle the above challenges, we propose a heterogeneity-aware FL framework, called FedCG, with adaptive client selection and gradient compression. Specifically, the parameter server (PS) selects a representative client subset considering statistical heterogeneity and sends the global model to them. After local training, these selected clients upload compressed model updates matching their capabilities to the PS for aggregation, which significantly alleviates the communication load and mitigates the straggler effect. We theoretically analyze the impact of both client selection and gradient compression on convergence performance. Guided by the derived convergence rate, we develop an iteration-based algorithm to jointly optimize client selection and compression ratio decision using submodular maximization and linear programming. Extensive experiments on both real-world prototypes and simulations show that FedCG can provide up to 5.3$\times$ speedup compared to other methods.

Is it possible to leverage large scale raw and raw parallel corpora to build a general learned metric? Existing learned metrics have gaps to human judgements, are model-dependent or are limited to the domains or tasks where human ratings are available. In this paper, we propose SEScore2, a model-based metric pretrained over million-scale synthetic dataset constructed by our novel retrieval augmented data synthesis pipeline. SEScore2 achieves high correlation to human judgements without any human rating supervisions. Importantly, our unsupervised SEScore2 can outperform supervised metrics, which are trained on the News human ratings, at the TED domain. We evaluate SEScore2 over four text generation tasks across three languages. SEScore2 outperforms all prior unsupervised evaluation metrics in machine translation, speech translation, data-to-text and dialogue generation, with average Kendall improvements 0.158. SEScore2 even outperforms SOTA supervised BLEURT at data-to-text, dialogue generation and overall correlation.

Deep learning has achieved notable success in 3D object detection with the advent of large-scale point cloud datasets. However, severe performance degradation in the past trained classes, i.e., catastrophic forgetting, still remains a critical issue for real-world deployment when the number of classes is unknown or may vary. Moreover, existing 3D class-incremental detection methods are developed for the single-domain scenario, which fail when encountering domain shift caused by different datasets, varying environments, etc. In this paper, we identify the unexplored yet valuable scenario, i.e., class-incremental learning under domain shift, and propose a novel 3D domain adaptive class-incremental object detection framework, DA-CIL, in which we design a novel dual-domain copy-paste augmentation method to construct multiple augmented domains for diversifying training distributions, thereby facilitating gradual domain adaptation. Then, multi-level consistency is explored to facilitate dual-teacher knowledge distillation from different domains for domain adaptive class-incremental learning. Extensive experiments on various datasets demonstrate the effectiveness of the proposed method over baselines in the domain adaptive class-incremental learning scenario.

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in the absence of expert annotations. However, existing contrastive approaches generally treat each instance independently, which leads to false negative pairs that share the same semantics. To tackle this problem, we propose MHCCL, a Masked Hierarchical Cluster-wise Contrastive Learning model, which exploits semantic information obtained from the hierarchical structure consisting of multiple latent partitions for multivariate time series. Motivated by the observation that fine-grained clustering preserves higher purity while coarse-grained one reflects higher-level semantics, we propose a novel downward masking strategy to filter out fake negatives and supplement positives by incorporating the multi-granularity information from the clustering hierarchy. In addition, a novel upward masking strategy is designed in MHCCL to remove outliers of clusters at each partition to refine prototypes, which helps speed up the hierarchical clustering process and improves the clustering quality. We conduct experimental evaluations on seven widely-used multivariate time series datasets. The results demonstrate the superiority of MHCCL over the state-of-the-art approaches for unsupervised time series representation learning.

变压器在图像处理领域取得了显着的成就。受到这一巨大成功的启发，变形金刚在3D点云处理中的应用引起了越来越多的关注。本文提出了一个新颖的点云表示学习网络，具有双重自我注意的3D点云变压器（3DPCT）和一个编码器解码器结构。具体而言，3DPCT具有一个层次编码器，该编码器包含两个用于分类任务的局部全球双重注意模块（分段任务的三个模块），每个模块都包含一个局部特征聚合（LFA）块和全局特征学习（ GFL）块。 GFL块是双重的自我注意事项，既有在点上的自我注意力，又可以提高特征提取。此外，在LFA中，为更好地利用了提取的本地信息，设计了一种新颖的点自我发明模型，称为点斑点自我注意力（PPSA）。在分类和分割数据集上都评估了性能，其中包含合成数据和现实世界数据。广泛的实验表明，所提出的方法在分类和分割任务上都达到了最新的结果。

尽管目前基于深度学习的方法在盲目的单图像超分辨率（SISR）任务中已获得了有希望的表现，但其中大多数主要集中在启发式上构建多样化的网络体系结构，并更少强调对Blur之间的物理发电机制的明确嵌入内核和高分辨率（HR）图像。为了减轻这个问题，我们提出了一个模型驱动的深神经网络，称为blind SISR。具体而言，为了解决经典的SISR模型，我们提出了一种简单的效果迭代算法。然后，通过将所涉及的迭代步骤展开到相应的网络模块中，我们自然构建了KXNET。所提出的KXNET的主要特异性是整个学习过程与此SISR任务的固有物理机制完全合理地集成在一起。因此，学习的模糊内核具有清晰的物理模式，并且模糊内核和HR图像之间的相互迭代过程可以很好地指导KXNET沿正确的方向发展。关于合成和真实数据的广泛实验很好地证明了我们方法的卓越准确性和一般性超出了当前代表性的最先进的盲目SISR方法。代码可在：\ url {https://github.com/jiahong-fu/kxnet}中获得。

在没有解密的情况下对加密数据进行神经网络推断是一种流行的方法，可以使隐私神经网络（PNET）作为服务。与用于机器学习的常规神经网络相比，PNET需要额外的编码，例如量化精确数字和多项式激活。加密输入还引入了新颖的挑战，例如对抗性鲁棒性和安全性。据我们所知，我们是第一个研究问题，包括（i）PNET是否比常规神经网络对对抗性输入更强大？ （ii）如何在没有解密的情况下设计强大的PNET？我们建议使用PNET攻击来生成黑框对抗示例，这些示例可以成功攻击目标和非目标方式。攻击结果表明，需要改进针对对抗输入的PNET鲁棒性。这不是一项琐碎的任务，因为PNET模型所有者无法访问输入值的明文，这阻止了现有检测和防御方法的应用，例如输入调整，模型归一化和对抗性培训。为了应对这一挑战，我们提出了一种新的快速准确的噪声插入方法，称为RPNET，以设计强大的私人神经网络。我们的综合实验表明，PNET-ITSTACK比先前的工作减少了至少$ 2.5 \ times $的查询。我们从理论上分析了我们的RPNET方法，并证明RPNET可以降低$ \ sim 91.88 \％$ $攻击成功率。

AI的创作（例如诗歌或歌词产生）吸引了行业和学术社区的越来越多的关注，在过去的几年中，许多有前途的模型提出了许多有前途的模型。现有方法通常基于单个和独立的视觉或文本信息估算输出。但是，实际上，人类通常会根据自己的经验进行创作，这可能涉及不同的方式并依次相关。为了模拟这种人类能力，在本文中，我们根据人类的经验来定义和解决一个新颖的AI创建问题。更具体地说，我们研究了如何基于顺序多模式信息生成文本。与以前的作品相比，此任务要困难得多，因为设计的模型必须很好地理解和适应不同模式之间的语义，并以顺序的方式有效地将其转化为输出。为了减轻这些困难，我们首先设计了配备有多模式注意力网络的多通道序列到序列体系结构。为了获得更有效的优化，我们然后提出了针对顺序输入量身定制的课程负抽样策略。为了基准这个问题并证明我们的模型的有效性，我们手动标记了一个新的多模式体验数据集。使用该数据集，我们通过将模型与一系列代表性基线进行比较，进行了广泛的实验，我们可以基于自动和以人为中心的指标来证明模型的显着改进。代码和数据可在：\ url {https://github.com/aman-4-real/mmtg}中获得。