人类对象相互作用（HOI）检测是高级图像理解的核心任务。最近，由于其出色的性能和有效的结构，检测变压器（DETR）基于HOI的检测器已变得流行。但是，这些方法通常对所有测试图像采用固定的HOI查询，这很容易受到一个特定图像中对象的位置变化的影响。因此，在本文中，我们建议通过挖掘硬阳性查询来增强DETR的鲁棒性，这些查询被迫使用部分视觉提示做出正确的预测。首先，我们根据每个训练图像标记的人类对象对的地面真相（GT）位置明确地组成硬阳性查询。具体而言，我们将每个标记的人类对象对的GT边界框移动，以使移位框仅覆盖GT的一定部分。我们将每个标记的人类对象对的移位框的坐标编码为HOI查询。其次，我们通过在解码器层的交叉注意地图中掩盖了最高分数，从而隐式构建了另一组硬阳性查询。然后，掩盖的注意图仅涵盖HOI预测的部分重要提示。最后，提出了一种替代策略，该策略有效地结合了两种类型的硬性查询。在每次迭代中，都采用了Detr的可学习查询和一种选择的硬阳性查询进行损失计算。实验结果表明，我们提出的方法可以广泛应用于现有的基于DITR的HOI探测器。此外，我们始终在三个基准上实现最先进的性能：HICO-DET，V-COCO和HOI-A。代码可在https://github.com/muchhair/hqm上找到。

传统的3D人姿态估计依赖于首次检测2D身体键盘，然后求解2D到3D对应问题。提高有希望的结果，该学习范例高度依赖于2D关键点检测器的质量，这不可避免地易于闭塞和堵塞-of-image缺席。在本文中，我们提出了一种新颖的姿势定向网（PONET），其能够仅通过学习方向估计3D姿势，因此在没有图像证据的情况下绕过错误易于keypoint检测器。对于具有部分不可见的四肢的图像，Ponet通过利用本地图像证据来恢复3D姿势来估计这些肢体的3D方向。通过利用完全看不见的四肢来说，Ponet甚至可以从完全看不见的四肢的图像中推断出完整的3D姿势。可见肢体之间的取向相关性以补充估计的姿势，进一步提高了3D姿态估计的鲁棒性。我们在多个数据集中评估我们的方法，包括Human3.6M，MPII，MPI-INF-3DHP和3DPW。我们的方法在理想设置中实现了与最先进的技术的结果，但显着消除了对关键点检测器和相应的计算负担的依赖性。在截断和擦除等方面的高度挑战性方案中，我们的方法稳健地表现得非常强大，与本领域的状态相比，展示其对现实世界应用的可能性。

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.

近年来，大规模的深层模型取得了巨大的成功，但巨大的计算复杂性和大规模的存储要求使其在资源限制设备中部署它们是一个巨大的挑战。作为模型压缩和加速度方法，知识蒸馏通过从教师探测器转移黑暗知识有效提高了小型模型的性能。然而，大多数基于蒸馏的检测方法主要模仿近边界盒附近的特征，这遭受了两个限制。首先，它们忽略边界盒外面的有益特征。其次，这些方法模仿一些特征，这些特征被教师探测器被错误地被视为背景。为了解决上述问题，我们提出了一种新颖的特征性 - 丰富的评分（FRS）方法，可以选择改善蒸馏过程中的广义可检测性的重要特征。所提出的方法有效地检索边界盒外面的重要特征，并消除边界盒内的有害特征。广泛的实验表明，我们的方法在基于锚和无锚探测器上实现了出色的性能。例如，具有Reset-50的RetinAnet在Coco2017数据集上达到39.7％，甚至超过基于Reset-101的教师检测器38.9％甚至超过0.8％。

鼻咽癌（NPC）是由鼻咽引起的恶性上皮癌。生存预测是NPC患者的主要关注点，因为它提供了早期的预后信息来计划治疗。最近，基于深度学习的深层生存模型已经证明了胜过基于传统放射素学的生存预测模型的潜力。深度存活模型通常使用覆盖整个目标区域的图像贴片（例如，NPC的鼻咽）或仅包含分段肿瘤区域作为输入。但是，使用整个目标区域的模型还将包括非相关的背景信息，而使用分段肿瘤区域的模型将无视原发性肿瘤不存在的潜在预后信息（例如，局部淋巴结转移和相邻的组织侵入）。在这项研究中，我们提出了一个3D端到端的深层多任务生存模型（DEEPMTS），用于从预处理PET/CT的晚期NPC中进行关节存活预测和肿瘤分割。我们的新颖性是引入硬分段分割主链，以指导与原发性肿瘤相关的局部特征的提取，从而减少了非相关背景信息的干扰。此外，我们还引入了一个级联的生存网络，以捕获原发性肿瘤中存在的预后信息，并进一步利用从分段主链中得出的全球肿瘤信息（例如，肿瘤的大小，形状和位置）。我们使用两个临床数据集进行的实验表明，我们的DEEPMT始终超过传统的基于放射线学的生存预测模型和现有的深层生存模型。

目的：基于深度学习的放射素学（DLR）在医学图像分析中取得了巨大的成功，并被认为是依赖手工特征的常规放射线学的替代。在这项研究中，我们旨在探索DLR使用预处理PET/CT预测鼻咽癌（NPC）中5年无进展生存期（PFS）的能力。方法：总共招募了257名患者（内部/外部队列中的170/87），具有晚期NPC（TNM III期或IVA）。我们开发了一个端到端的多模式DLR模型，其中优化了3D卷积神经网络以从预处理PET/CT图像中提取深度特征，并预测了5年PFS的概率。作为高级临床特征，TNM阶段可以集成到我们的DLR模型中，以进一步提高预后性能。为了比较常规放射素学和DLR，提取了1456个手工制作的特征，并从54种特征选择方法和9种分类方法的54个交叉组合中选择了最佳常规放射线方法。此外，使用临床特征，常规放射线学签名和DLR签名进行风险组分层。结果：我们使用PET和CT的多模式DLR模型比最佳常规放射线方法获得了更高的预后性能。此外，多模式DLR模型仅使用PET或仅CT优于单模式DLR模型。对于风险组分层，常规的放射线学签名和DLR签名使内部和外部队列中的高风险患者群体之间有显着差异，而外部队列中的临床特征则失败。结论：我们的研究确定了高级NPC中生存预测的潜在预后工具，表明DLR可以为当前TNM分期提供互补值。

This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.

Supervised Question Answering systems (QA systems) rely on domain-specific human-labeled data for training. Unsupervised QA systems generate their own question-answer training pairs, typically using secondary knowledge sources to achieve this outcome. Our approach (called PIE-QG) uses Open Information Extraction (OpenIE) to generate synthetic training questions from paraphrased passages and uses the question-answer pairs as training data for a language model for a state-of-the-art QA system based on BERT. Triples in the form of <subject, predicate, object> are extracted from each passage, and questions are formed with subjects (or objects) and predicates while objects (or subjects) are considered as answers. Experimenting on five extractive QA datasets demonstrates that our technique achieves on-par performance with existing state-of-the-art QA systems with the benefit of being trained on an order of magnitude fewer documents and without any recourse to external reference data sources.

Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale labeled dataset (e.g., ImageNet) for achieving satisfactory performance, which is usually unavailable for medical images. Additionally, due to the gap between medical and natural images, the improvement generated by the ImageNet pretrained weights significantly degrades while transferring the weights to medical image processing tasks. In this paper, we propose Bootstrap Own Latent of Transformer (BOLT), a self-supervised learning approach specifically for medical image classification with the Transformer backbone. Our BOLT consists of two networks, namely online and target branches, for self-supervised representation learning. Concretely, the online network is trained to predict the target network representation of the same patch embedding tokens with a different perturbation. To maximally excavate the impact of Transformer from limited medical data, we propose an auxiliary difficulty ranking task. The Transformer is enforced to identify which branch (i.e., online/target) is processing the more difficult perturbed tokens. Overall, the Transformer endeavours itself to distill the transformation-invariant features from the perturbed tokens to simultaneously achieve difficulty measurement and maintain the consistency of self-supervised representations. The proposed BOLT is evaluated on three medical image processing tasks, i.e., skin lesion classification, knee fatigue fracture grading and diabetic retinopathy grading. The experimental results validate the superiority of our BOLT for medical image classification, compared to ImageNet pretrained weights and state-of-the-art self-supervised learning approaches.

Knowledge graph embedding (KGE), which maps entities and relations in a knowledge graph into continuous vector spaces, has achieved great success in predicting missing links in knowledge graphs. However, knowledge graphs often contain incomplete triples that are difficult to inductively infer by KGEs. To address this challenge, we resort to analogical inference and propose a novel and general self-supervised framework AnKGE to enhance KGE models with analogical inference capability. We propose an analogical object retriever that retrieves appropriate analogical objects from entity-level, relation-level, and triple-level. And in AnKGE, we train an analogy function for each level of analogical inference with the original element embedding from a well-trained KGE model as input, which outputs the analogical object embedding. In order to combine inductive inference capability from the original KGE model and analogical inference capability enhanced by AnKGE, we interpolate the analogy score with the base model score and introduce the adaptive weights in the score function for prediction. Through extensive experiments on FB15k-237 and WN18RR datasets, we show that AnKGE achieves competitive results on link prediction task and well performs analogical inference.