Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries. 2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model. To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding. Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets.

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.

High order structures (cavities and cliques) of the gene network of influenza A virus reveal tight associations among viruses during evolution and are key signals that indicate viral cross-species infection and cause pandemics. As indicators for sensing the dynamic changes of viral genes, these higher order structures have been the focus of attention in the field of virology. However, the size of the viral gene network is usually huge, and searching these structures in the networks introduces unacceptable delay. To mitigate this issue, in this paper, we propose a simple-yet-effective model named HyperSearch based on deep learning to search cavities in a computable complex network for influenza virus genetics. Extensive experiments conducted on a public influenza virus dataset demonstrate the effectiveness of HyperSearch over other advanced deep-learning methods without any elaborated model crafting. Moreover, HyperSearch can finish the search works in minutes while 0-1 programming takes days. Since the proposed method is simple and easy to be transferred to other complex networks, HyperSearch has the potential to facilitate the monitoring of dynamic changes in viral genes and help humans keep up with the pace of virus mutations.

Dynamic interaction graphs have been widely adopted to model the evolution of user-item interactions over time. There are two crucial factors when modelling user preferences for link prediction in dynamic interaction graphs: 1) collaborative relationship among users and 2) user personalized interaction patterns. Existing methods often implicitly consider these two factors together, which may lead to noisy user modelling when the two factors diverge. In addition, they usually require time-consuming parameter learning with back-propagation, which is prohibitive for real-time user preference modelling. To this end, this paper proposes FreeGEM, a parameter-free dynamic graph embedding method for link prediction. Firstly, to take advantage of the collaborative relationships, we propose an incremental graph embedding engine to obtain user/item embeddings, which is an Online-Monitor-Offline architecture consisting of an Online module to approximately embed users/items over time, a Monitor module to estimate the approximation error in real time and an Offline module to calibrate the user/item embeddings when the online approximation errors exceed a threshold. Meanwhile, we integrate attribute information into the model, which enables FreeGEM to better model users belonging to some under represented groups. Secondly, we design a personalized dynamic interaction pattern modeller, which combines dynamic time decay with attention mechanism to model user short-term interests. Experimental results on two link prediction tasks show that FreeGEM can outperform the state-of-the-art methods in accuracy while achieving over 36X improvement in efficiency. All code and datasets can be found in https://github.com/FudanCISL/FreeGEM.

社会建议利用社会关系来增强建议的代表性学习。大多数社会推荐模型都将用户互动（协作领域）和社会关系（社会领域）的用户表示统一。但是，这种方法可能无法模拟用户在两个域中的异质行为模式，从而损害了用户表示的表现力。在这项工作中，为了解决这种局限性，我们为社会建议提出了一个新颖的截面对比度学习框架DCREC。更具体地说，我们建议从项目和社会域中学习分开的用户表示。此外，分离的对比度学习旨在在分散的用户表示之间进行社交建议之间的知识转移。各种现实世界数据集的全面实验证明了我们提出的模型的优势。

深度学习方法论为高光谱图像（HSI）分析社区的发展做出了很大贡献。但是，这也使HSI分析系统容易受到对抗攻击的影响。为此，我们在本文中提出了一个掩盖的空间光谱自动编码器（MSSA），根据自我监督的学习理论，以增强HSI分析系统的鲁棒性。首先，进行了一个掩盖的序列注意学习模块，以促进沿光谱通道的HSI分析系统的固有鲁棒性。然后，我们开发了一个具有可学习的图形结构的图形卷积网络，以建立全局像素的组合。这样，每种组合中的所有相关像素都可以分散攻击效果，并且在空间方面可以实现更好的防御性能。最后，为了提高防御能力并解决有限标记样品的问题，MSSA采用光谱重建作为借口任务，并以自我监督的方式适合数据集。 - 高光谱分类方法和代表性的对抗防御策略。

在线对话说明是在现实世界在线教育环境中使用的一系列教学说明，以激励学生，帮助了解学习材料并建立有效的学习习惯。尽管在线学习的受欢迎程度和优势，但教育技术和教育数据挖掘社区仍然缺乏缺乏大规模，高质量和良好的教学教学指导数据集来研究计算方法，以自动检测在线对话说明并进一步提高在线教学效果。因此，在本文中，我们提供了一个在线对话说明检测的数据集\ textsc {dialogId}，其中包含30,431个有效的对话说明。这些教学说明很好地注释分为8个类别。此外，我们还利用了普遍的预训练的语言模型（PLM），并提出一个简单而有效的对抗训练学习范式来提高对话指导检测的质量和概括。广泛的实验表明，我们的方法的表现优于多种基线方法。数据和我们的代码可用于研究目的：\ url {https://github.com/ai4ed/dialogid}。

我们提出了一种简单但有效的方法，建议为学生提供高质量和多样性的练习。我们的方法由三个关键组成部分组成：（1）候选生成模块；（2）促进多样性的模块；（3）范围限制模块。提出的方法在召回方面提高了总体建议性能，与基线相比，推荐候选者的多样性增加了0.81 \％。

知识跟踪（KT）是使用学生的历史学习互动数据来对其知识掌握的任务，以便对他们未来的互动绩效进行预测。最近，使用各种深度学习技术来解决KT问题已经取得了显着的进步。但是，基于深度学习的知识追踪（DLKT）方法的成功仍然有些神秘，适当的测量以及对这些DLKT方法的分析仍然是一个挑战。首先，现有作品中的数据预处理程序通常是私人和/或自定义，这限制了实验标准化。此外，现有的DLKT研究通常在评估方案方面有所不同，并且是现实世界中的教育环境。为了解决这些问题，我们介绍了一个综合基于Python的基准平台\ TextSc {Pykt}，以确保通过彻底评估进行跨DLKT方法的有效比较。 \ textsc {pykt}库由不同域的7个流行数据集上的一组标准化的数据预处理程序组成，而10个经常比较了用于透明实验的DLKT模型实现。我们细粒度和严格的经验KT研究的结果产生了一系列观察结果和有效DLKT的建议，例如，错误的评估设置可能会导致标签泄漏，这通常会导致性能膨胀；与Piech等人提出的第一个DLKT模型相比，许多DLKT方法的改进是最小的。 \ cite {piech2015 -Deep}。我们已经开源\ textsc {pykt}，并在\ url {https://pykt.org/}上进行了实验结果。我们欢迎其他研究小组和从业人员的贡献。

我们提出蒙版频率建模（MFM），这是一种基于统一的基于频域的方法，用于自我监督的视觉模型预训练。在本文中，我们将视角转移到了频域中，而不是将蒙版令牌随机插入到空间域中的输入嵌入。具体而言，MFM首先掩盖了输入图像的一部分频率分量，然后预测频谱上的缺失频率。我们的关键见解是，由于沉重的空间冗余，预测频域中的屏蔽组件更理想地揭示了基础图像模式，而不是预测空间域中的掩盖斑块。我们的发现表明，通过对蒙版和预测策略的正确配置，高频组件中的结构信息和低频对应物中的低级统计信息都有用。 MFM首次证明，对于VIT和CNN，即使没有使用以下内容，简单的非叙事框架也可以学习有意义的表示形式：（i）额外的数据，（ii）额外的模型，（iii）蒙版令牌。与最近的蒙版图像建模方法相比，对成像网和几个鲁棒性基准的实验结果表明，MFM的竞争性能和高级鲁棒性。此外，我们还全面研究了从统一的频率角度来表示经典图像恢复任务对表示学习的有效性，并揭示了他们与MFM方法的有趣关系。项目页面：https：//www.mmlab-ntu.com/project/mfm/index.html。