Talking face generation aims at generating photo-realistic video portraits of a target person driven by input audio. Due to its nature of one-to-many mapping from the input audio to the output video (e.g., one speech content may have multiple feasible visual appearances), learning a deterministic mapping like previous works brings ambiguity during training, and thus causes inferior visual results. Although this one-to-many mapping could be alleviated in part by a two-stage framework (i.e., an audio-to-expression model followed by a neural-rendering model), it is still insufficient since the prediction is produced without enough information (e.g., emotions, wrinkles, etc.). In this paper, we propose MemFace to complement the missing information with an implicit memory and an explicit memory that follow the sense of the two stages respectively. More specifically, the implicit memory is employed in the audio-to-expression model to capture high-level semantics in the audio-expression shared space, while the explicit memory is employed in the neural-rendering model to help synthesize pixel-level details. Our experimental results show that our proposed MemFace surpasses all the state-of-the-art results across multiple scenarios consistently and significantly.

This paper presents SimVTP: a Simple Video-Text Pretraining framework via masked autoencoders. We randomly mask out the spatial-temporal tubes of input video and the word tokens of input text and then feed them into a unified autencoder to reconstruct the missing pixels and words. Our SimVTP has several properties: 1) Thanks to the unified autoencoder, SimVTP reconstructs the masked signal of one modality with the help from another modality, which implicitly learns the cross-modal alignment between video tubes and text tokens. 2) SimVTP not only benefits from a high video masking ratio (e.g. 90%) due to the temporal redundancy of video, but also needs a high text masking ratio (e.g. 75%), which is much higher than BERT (e.g. 15%), to achieve optimal performance. This is because the aid of video modality makes text reconstruction less challenging, which thus needs a higher mask ratio to make the pretext harder for useful feature learning. 3) Equipping SimVTP with video-text contrastive learning (VTC) and video-text matching (VTM), which are two commonly used cross-modal training strategies, could further improve the transferable performance significantly. 4) SimVTP is dataefficent, e.g., pre-training only on 10% data of WebVid-2M, SimVTP achieves surprisingly good results (43.8 R@1) on MSRVTT, which is far above recent state-of-the-art methods pre-trained on both CC3M and WebVid-2M. We transfer our pre-trained model to various downstream tasks and achieve superior performance. The codes and models will be released at https://github.com/mayuelala/SimVTP.

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

Deep learning methods have contributed substantially to the rapid advancement of medical image segmentation, the quality of which relies on the suitable design of loss functions. Popular loss functions, including the cross-entropy and dice losses, often fall short of boundary detection, thereby limiting high-resolution downstream applications such as automated diagnoses and procedures. We developed a novel loss function that is tailored to reflect the boundary information to enhance the boundary detection. As the contrast between segmentation and background regions along the classification boundary naturally induces heterogeneity over the pixels, we propose the piece-wise two-sample t-test augmented (PTA) loss that is infused with the statistical test for such heterogeneity. We demonstrate the improved boundary detection power of the PTA loss compared to benchmark losses without a t-test component.

最近，知识表示学习（KRL）正在作为对知识图（kgs）处理查询的最新方法的出现，其中kg实体和查询被嵌入到一个潜在空间中，以使回答查询的实体是嵌入在查询附近。然而，尽管对KRL进行了深入的研究，但大多数现有研究要么侧重于同质KG，要么承担kg完成任务（即缺失事实的推断），同时回答对具有多个方面的kgs的复杂逻辑查询（多视图kg）仍然是一个开放的挑战。为了弥合这一差距，在本文中，我们提出了罗马，这是一个新颖的KRL框架，用于回答多视图KGS的逻辑查询。与先前的工作相比，罗姆人在主要方面离开。 （i）它将多视图kg建模为一组覆盖子kg，每个kg对应于一种视图，该视图集成了文献中研究的许多类型的kg（例如，颞kg）。 （ii）它支持具有不同关系和视图约束的复杂逻辑查询（例如，具有复杂的拓扑和/或从多个视图中）； （iii）它比例扩大到大小（例如，数百万个事实）和细粒状视图（例如，数十个观点）； （iv）它概括地查询训练过程中未观察到的结构和kg观点。对现实世界KGS的广泛经验评估表明，\系统明显优于替代方法。

近年来，自动对色素，非色素和脱发的非胸膜皮肤病变的分类引起了很多关注。但是，皮肤纹理，病变形状，脱位对比度，照明条件等的成像变化。阻碍了鲁棒的特征提取，从而影响分类精度。在本文中，我们提出了一个新的深神经网络，该网络利用输入数据进行鲁棒特征提取。具体而言，我们分析了卷积网络的行为（视野），以找到深度监督的位置，以改善特征提取。为了实现这一目标，首先，我们执行激活映射以生成对象掩码，突出显示对分类输出生成最重要的输入区域。然后，选择层的有效接收场的网络层与对象掩模中的近似对象形状相匹配，以作为我们进行深度监督的焦点。利用三个黑色素瘤检测数据集和两个白癜风检测数据集上的不同类型的卷积特征提取器和分类器，我们验证了新方法的有效性。

本文回顾了AIM 2022上压缩图像和视频超级分辨率的挑战。这项挑战包括两条曲目。轨道1的目标是压缩图像的超分辨率，轨迹〜2靶向压缩视频的超分辨率。在轨道1中，我们使用流行的数据集DIV2K作为培训，验证和测试集。在轨道2中，我们提出了LDV 3.0数据集，其中包含365个视频，包括LDV 2.0数据集（335个视频）和30个其他视频。在这一挑战中，有12支球队和2支球队分别提交了赛道1和赛道2的最终结果。所提出的方法和解决方案衡量了压缩图像和视频上超分辨率的最先进。提出的LDV 3.0数据集可在https://github.com/renyang-home/ldv_dataset上找到。此挑战的首页是在https://github.com/renyang-home/aim22_compresssr。

基于匹配的方法，尤其是基于时空记忆的方法，在半监督视频对象分割（VOS）中明显领先于其他解决方案。但是，不断增长和冗余的模板特征导致推断效率低下。为了减轻这一点，我们提出了一个新型的顺序加权期望最大化（SWEM）网络，以大大降低记忆特征的冗余。与以前仅检测帧之间特征冗余的方法不同，Swem通过利用顺序加权EM算法来合并框架内和框架间的相似特征。此外，框架特征的自适应权重具有代表硬样品的灵活性，从而改善了模板的歧视。此外，该提出的方法在内存中保留了固定数量的模板特征，从而确保了VOS系统的稳定推理复杂性。对常用的戴维斯和YouTube-VOS数据集进行了广泛的实验，验证了SWEM的高效率（36 fps）和高性能（84.3 \％$ \ Mathcal {J} \＆\ Mathcal {F} $代码可在以下网址获得：https：//github.com/lmm077/swem。

使用增强现实（AR）用于导航目的，这表明在手术手术过程中协助医生有益。这些应用通常需要知道外科手术工具和患者的姿势，以提供外科医生在任务执行过程中可以使用的视觉信息。现有的医学级跟踪系统使用放置在手术室内的红外摄像头（OR）来识别感兴趣的对象附加并计算其姿势的复古反射标记。一些市售的AR头式显示器（HMD）使用类似的摄像头进行自定位，手动跟踪和估算对象的深度。这项工作提出了一个使用AR HMD的内置摄像机来准确跟踪复古反射标记的框架，例如在手术过程中使用的标记，而无需集成任何其他组件。该框架还能够同时跟踪多个工具。我们的结果表明，横向翻译的准确度为0.09 +-0.06毫米，可以实现标记的跟踪和检测，纵向翻译的0.42 +-0.32 mm，绕垂直轴旋转的0.80 +-0.39 ver。此外，为了展示所提出的框架的相关性，我们在手术程序的背景下评估了系统的性能。该用例旨在在骨科过程中复制K-Wire插入的场景。为了进行评估，为两名外科医生和一名生物医学研究人员提供了视觉导航，每次都进行了21次注射。该用例的结果提供了与基于AR的导航程序报告的相当精度。

在“知识图”（kgs）的表示领域中，超级关系的事实由主要三重和几个辅助属性描述组成，这被认为比基于三重的事实更全面，更具体。但是，由于代表实体之间的隶属关系的层次结构削弱，因此，单个视图中现有的超相关KG嵌入方法受到限制。为了打破这一限制，我们提出了一个双视性超相关kg（DH-kg）结构，该结构包含实体的超相关实例视图，以及对从实体到共同模型超相关的概念的超相关本体论视图和分层信息。在本文中，我们首先定义了DH-KG上的链接预测和实体键入任务，并根据医疗数据构建了两个DH-KG数据集，即从Wikidata和HTDM中提取的JW44K-6K。此外，我们根据Gran编码器，HGNN和联合学习提出了DH-KG嵌入模型DHGE。实验结果表明，DHGE在DH-KG上的表现优于基线模型。我们还提供了该技术在高血压药物领域中应用的示例。我们的模型和数据集公开可用。