The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

步态识别旨在识别个人特定的步行模式，这高度取决于观察到每个身体部分的不同周期运动。但是，大多数现有方法都平等处理每个部分，并忽略了由于步态序列的高采样率而忽略了数据冗余。在这项工作中，我们提出了一个细粒运动表示网络（GAITFM），以提高三个方面的步态识别性能。首先，细粒部分序列学习（FPSL）模块旨在探索独立于部分的时空表示。其次，一种称为局部运动聚集（LMA）的框架压缩策略用于增强运动变化。最后，加权的广义平均池（WGEM）层可自适应地在空间下采样中保持更多的判别信息。在两个公共数据集Casia-B和OUMVLP上进行的实验表明，我们的方法达到了最先进的表现。在CASIA-B数据集上，我们的方法可实现正常步行，袋装行走和带外套行走的98.0％，95.7％和87.9％的排名1精度。在OUMVLP数据集上，我们的方法的排名准确性为90.5％。

当使用任意异质数据流提供时，我们如何收集最有用的标签来学习模型选择策略？在本文中，我们将此任务制定为一个在线上下文的活动模型选择问题，在每个回合中，学习者在上下文中都会收到一个未标记的数据点以及上下文。目的是在任何给定上下文中输出最佳模型，而不会获得过多的标签。特别是，我们专注于选择预训练的分类器的任务，并提出一种上下文活动模型选择算法（CAM），该算法依赖于在给定策略类别上定义的新型不确定性采样查询标准用于自适应模型选择。与先前的ART相比，我们的算法不假定全球最佳模型。我们提供严格的理论分析，以实现对抗和随机设置下的遗憾和查询复杂性。我们对几个基准分类数据集的实验证明了该算法在遗憾和查询复杂性方面的有效性。值得注意的是，与CIFAR10上最佳的在线型号选择基线相比，CAMS的标签成本少于标签成本的10％。

尽管U-NET体系结构已广泛用于分割医学图像，但我们解决了这项工作中的两个缺点。首先，当分割目标区域的形状和尺寸显着变化时，香草U-NET的精度会降低。即使U-NET已经具有在各种尺度上分析特征的能力，我们建议在U-NET编码器的每个卷积模块中明确添加多尺度特征图，以改善组织学图像的分割。其次，当监督学习的注释嘈杂或不完整时，U-NET模型的准确性也会受到影响。由于人类专家在非常精确，准确地识别和描述所有特定病理的所有实例的固有困难，因此可能发生这种情况。我们通过引入辅助信心图来应对这一挑战，该辅助信心图较少强调给定目标区域的边界。此外，我们利用深网的引导属性智能地解决了丢失的注释问题。在我们对乳腺癌淋巴结私有数据集的实验中，主要任务是分割生发中心和窦性组织细胞增多症，我们观察到了基于两个提出的增强的U-NET基线的显着改善。

事件提取（EE）是信息提取的重要任务，该任务旨在从非结构化文本中提取结构化事件信息。大多数先前的工作都专注于提取平坦的事件，同时忽略重叠或嵌套的事件。多个重叠和嵌套EE的模型包括几个连续的阶段来提取事件触发器和参数，这些阶段患有错误传播。因此，我们设计了一种简单而有效的标记方案和模型，以将EE作为单词关系识别，称为oneee。触发器或参数单词之间的关系在一个阶段同时识别出并行网格标记，从而产生非常快的事件提取速度。该模型配备了自适应事件融合模块，以生成事件感知表示表示和距离感知的预测指标，以整合单词关系识别的相对距离信息，从经验上证明这是有效的机制。对3个重叠和嵌套的EE基准测试的实验，即少数FC，GENIA11和GENIA13，表明Oneee实现了最新的（SOTA）结果。此外，ONEEE的推理速度比相同条件下的基线的推理速度快，并且由于它支持平行推断，因此可以进一步改善。

沟通效率在加速深神经网络（DNN）的分布式训练中起着重要作用。 All-Reduce是减少分布式DNN培训中模型参数的关键沟通原始性。大多数现有的全减少算法都是为传统的电气互连系统设计的，该系统无法满足大型DNN分布式培训的通信要求。电气互连的有希望的替代方案之一是光学互连，可以提供高带宽，低传输延迟和低功率成本。我们提出了一个称为WRHT（波长重复使用的层次树）的有效方案，用于在光学互连系统中实现全降压操作，该系统可以利用WDM（波长多路复用）来减少分布式数据 - 偏置DNN训练的通信时间。我们进一步得出了最少的通信步骤和通信时间，以实现使用WRHT的全面减少。仿真结果表明，与在光学互连系统中模拟的三种传统的全减少算法相比，WRHT的通信时间分别减少了75.59％，49.25％和70.1％。仿真结果还表明，与电气互连系统中的两种现有的全减速算法相比，WRHT可以将所有还原操作的通信时间减少86.69％和84.71％。

为了安全和合理地参与密集和异质的交通，自动驾驶汽车需要充分分析周围交通代理的运动模式，并准确预测其未来的轨迹。这是具有挑战性的，因为交通代理的轨迹不仅受交通代理本身的影响，而且还受到彼此的空间互动的影响。以前的方法通常依赖于长期短期存储网络（LSTMS）的顺序逐步处理，并仅提取单型交通代理之间的空间邻居之间的相互作用。我们提出了时空变压器网络（S2TNET），该网络通过时空变压器对时空相互作用进行建模，并通过时间变压器处理颞序序列。我们将其他类别，形状和标题信息输入到我们的网络中，以处理交通代理的异质性。在Apolloscape轨迹数据集上，所提出的方法在平均值和最终位移误差的加权总和上优于Apolloscape轨迹数据集的最先进方法。我们的代码可在https://github.com/chenghuang66/s2tnet上找到。

Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of <instrument, verb, target> combination delivers comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. The challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. A total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms by competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery.

最近，在一步的Panoptic细分方法上越来越关注，旨在有效地旨在在完全卷积的管道内共同分割实例和材料。但是，大多数现有的工作直接向骨干功能提供给各种分段头，忽略语义和实例分割的需求不同：前者需要语义级别的判别功能，而后者需要跨实例可区分的功能。为了缓解这一点，我们建议首先预测用于增强骨干特征的不同位置之间的语义级和实例级相关性，然后分别将改进的鉴别特征馈送到相应的分割头中。具体地，我们将给定位置与所有位置之间的相关性组织为连续序列，并将其预测为整体。考虑到这种序列可以非常复杂，我们采用离散的傅里叶变换（DFT），一种可以近似由幅度和短语参数化的任意序列的工具。对于不同的任务，我们以完全卷积的方式从骨干网上生成这些参数，该参数通过相应的任务隐含地优化。结果，这些准确和一致的相关性有助于产生符合复杂的Panoptic细分任务的要求的合理辨别特征。为了验证我们的方法的有效性，我们对几个具有挑战性的Panoptic细分数据集进行实验，并以45.1美元\％PQ和ADE20K为32.6美元\％PQ实现最先进的绩效。

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.