基于聚类的方法，在伪标签的产生和特征提取网络的优化之间交替，在无监督学习（USL）和无监督的域自适应（UDA）人重新识别（RE-ID）中起着主要作用。为了减轻嘈杂的伪标签的不利影响，现有方法要么放弃不可靠的标签，要么通过相互学习或标签传播来完善伪标签。但是，仍然积累了许多错误的标签，因为这些方法主要采用传统的无监督聚类算法，这些算法依赖于对数据分布的某些假设，并且无法捕获复杂的现实世界数据的分布。在本文中，我们提出了基于插件的伪标签校正网络（GLC），以以监督聚类的方式完善伪标签。训练GLC可以通过任何聚类方法生成的初始伪标签的监督来感知自训练的每个时期的不同数据分布。它可以学会通过K最近的邻居（KNN）图和早期训练策略的样本之间的关系约束来纠正初始嘈杂标签。具体而言，GLC学会从邻居汇总节点特征，并预测是否应在图上链接节点。此外，在对嘈杂的标签进行严重记忆以防止过度拟合嘈杂的伪标签之前，GLC已通过“早停”进行了优化。因此，尽管监督信号包含一些噪音，但GLC提高了伪标签的质量，从而可以更好地进行重新ID性能。在Market-1501和MSMT17上进行了USL和UDA人重新ID的广泛实验表明，我们的方法与各种基于聚类的方法广泛兼容，并始终如一地促进最先进的性能。

在亲自重新识别（REID）中，最近的研究已经验证了未标记的人图像上的模型的预训练要比ImageNet上要好得多。但是，这些研究直接应用了为图像分类设计的现有自我监督学习（SSL）方法，用于REID，而无需在框架中进行任何适应。这些SSL方法将本地视图的输出（例如红色T恤，蓝色短裤）与同时的全球视图相匹配，从而丢失了很多细节。在本文中，我们提出了一种特定于REID的预训练方法，部分意识的自我监督预训练（PASS），该方法可以生成零件级别的功能以提供细粒度的信息，并且更适合REID。通行证将图像分为几个局部区域，每个区域随机裁剪的本地视图都有特定的可学习[部分]令牌。另一方面，所有地方区域的[部分]也附加到全球视图中。通行证学习以匹配同一[部分]上本地视图的输出和全局视图。也就是说，从本地区域获得的本地视图的[部分]仅与从全球视图中学到的相应[部分]相匹配。结果，每个[部分]可以专注于图像的特定局部区域，并提取该区域的细粒度信息。实验显示通行证在Market1501和MSMT17上的新最先进的表演以及各种REID任务（例如Vanilla vit-s/16）通过Pass Achieves 92.2 \％/90.2 \％/88.5 \％地图准确性，例如Vanilla vit-s/16在Market1501上进行监督/UDA/USL REID。我们的代码可在https://github.com/casia-iva-lab/pass-reid上找到。

Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet. However, existing models focus only on optimizing the documentation code pairs by embedding them into latent space, without the association of external knowledge. In this paper, we propose a generation-augmented query expansion framework. Inspired by the human retrieval process - sketching an answer before searching, in this work, we utilize the powerful code generation model to benefit the code retrieval task. Specifically, we demonstrate that rather than merely retrieving the target code snippet according to the documentation query, it would be helpful to augment the documentation query with its generation counterpart - generated code snippets from the code generation model. To the best of our knowledge, this is the first attempt that leverages the code generation model to enhance the code retrieval task. We achieve new state-of-the-art results on the CodeSearchNet benchmark and surpass the baselines significantly.

Traffic accident prediction in driving videos aims to provide an early warning of the accident occurrence, and supports the decision making of safe driving systems. Previous works usually concentrate on the spatial-temporal correlation of object-level context, while they do not fit the inherent long-tailed data distribution well and are vulnerable to severe environmental change. In this work, we propose a Cognitive Accident Prediction (CAP) method that explicitly leverages human-inspired cognition of text description on the visual observation and the driver attention to facilitate model training. In particular, the text description provides a dense semantic description guidance for the primary context of the traffic scene, while the driver attention provides a traction to focus on the critical region closely correlating with safe driving. CAP is formulated by an attentive text-to-vision shift fusion module, an attentive scene context transfer module, and the driver attention guided accident prediction module. We leverage the attention mechanism in these modules to explore the core semantic cues for accident prediction. In order to train CAP, we extend an existing self-collected DADA-2000 dataset (with annotated driver attention for each frame) with further factual text descriptions for the visual observations before the accidents. Besides, we construct a new large-scale benchmark consisting of 11,727 in-the-wild accident videos with over 2.19 million frames (named as CAP-DATA) together with labeled fact-effect-reason-introspection description and temporal accident frame label. Based on extensive experiments, the superiority of CAP is validated compared with state-of-the-art approaches. The code, CAP-DATA, and all results will be released in \url{https://github.com/JWFanggit/LOTVS-CAP}.

Visual odometry is crucial for many robotic tasks such as autonomous exploration and path planning. Despite many progresses, existing methods are still not robust enough to dynamic illumination environments. In this paper, we present AirVO, an illumination-robust and accurate stereo visual odometry system based on point and line features. To be robust to illumination variation, we introduce the learning-based feature extraction and matching method and design a novel VO pipeline, including feature tracking, triangulation, key-frame selection, and graph optimization etc. We also employ long line features in the environment to improve the accuracy of the system. Different from the traditional line processing pipelines in visual odometry systems, we propose an illumination-robust line tracking method, where point feature tracking and distribution of point and line features are utilized to match lines. In the experiments, the proposed system is extensively evaluated in environments with dynamic illumination and the results show that it achieves superior performance to the state-of-the-art algorithms.

Solving real-world sequential manipulation tasks requires robots to have a repertoire of skills applicable to a wide range of circumstances. To acquire such skills using data-driven approaches, we need massive and diverse training data which is often labor-intensive and non-trivial to collect and curate. In this work, we introduce Active Task Randomization (ATR), an approach that learns visuomotor skills for sequential manipulation by automatically creating feasible and novel tasks in simulation. During training, our approach procedurally generates tasks using a graph-based task parameterization. To adaptively estimate the feasibility and novelty of sampled tasks, we develop a relational neural network that maps each task parameter into a compact embedding. We demonstrate that our approach can automatically create suitable tasks for efficiently training the skill policies to handle diverse scenarios with a variety of objects. We evaluate our method on simulated and real-world sequential manipulation tasks by composing the learned skills using a task planner. Compared to baseline methods, the skills learned using our approach consistently achieve better success rates.

常规的识别抑郁症的方法无法扩展，公众对心理健康的认识有限，尤其是在发展中国家。从最近的研究中可以明显看出，社交媒体有可能更涉及心理健康筛查。按时间顺序排列的大量第一人称叙事帖子可以在一段时间内为人们的思想，感觉，行为或情绪提供见解，从而更好地理解在线空间中反映的抑郁症状。在本文中，我们提出了SERCNN，该文章通过（1）从不同域中堆叠两个预处理的嵌入方式以及（2）将嵌入环境重新引入MLP分类器来改善用户表示。我们的Sercnn在最先进的基线和其他基线方面表现出色，在5倍的交叉验证设置中达到93.7％的精度。由于并非所有用户都共享相同级别的在线活动，因此我们介绍了固定观察窗口的概念，该窗口量化了预定义的帖子中的观察期。 Sercnn的精度非常出色，其精度与BERT模型相当，而参数数量却少98％，Sercnn的表现出色，其精度非常出色。我们的发现为在社交媒体上检测抑郁症的方向开辟了一个有希望的方向，并较少的推断帖子，以为具有成本效益和及时干预的解决方案。我们希望我们的工作能够使该研究领域在现有临床实践中更接近现实世界的采用。

通过一系列联邦举措和命令，美国政府一直在努力确保美国在AI中的领导。这些广泛的战略文件影响了美国空军美国部（DAF）等组织。DAF-MIT AI加速器是DAF和MIT之间的一项计划，以弥合AI研究人员与DAF任务要求之间的差距。DAF-MIT AI加速器支持的几个项目正在开发公共挑战问题，这些问题解决了许多联邦AI研究的重点。这些挑战是通过公开可用的大型AI-Ready数据集，激励开源解决方案，并为可以激发进一步研究的双重使用技术创建需求信号，来针对优先事项。在本文中，我们描述了正在开发的这些公共挑战以及它们的应用如何促进科学进步。

我们研究了与任何已经训练的分类器兼容的简单方法（OOD）图像检测，仅依靠其预测或学会的表示。当使用Resnet-50和Swin Transformer模型使用时，评估各种方法的OOD检测性能，我们找到了仅考虑学会表示的模型预测的方法，可以轻松地胜过模型的预测。基于我们的分析，我们主张在其他研究中忽略了一种死去的方法：仅作为OOD图像标记，其平均距离与他们最近的邻居的平均距离很大（在图像分类器的表示空间中，经过训练的图像分类器的空间分销数据）。

从消息传递机制中受益，图形神经网络（GNN）在图形数据上的繁荣任务上已经成功。但是，最近的研究表明，攻击者可以通过恶意修改图形结构来灾难性地降低GNN的性能。解决此问题的直接解决方案是通过在两个末端节点的成对表示之间学习度量函数来建模边缘权重，该指标函数试图将低权重分配给对抗边缘。现有方法使用监督GNN学到的原始功能或表示形式来对边缘重量进行建模。但是，两种策略都面临着一些直接问题：原始特征不能代表节点的各种特性（例如结构信息），而受监督的GNN学到的表示可能会遭受分类器在中毒图上的差异性能。我们需要携带特征信息和尽可能糊状的结构信息并且对结构扰动不敏感的表示形式。为此，我们提出了一条名为stable的无监督管道，以优化图形结构。最后，我们将精心设计的图输入到下游分类器中。对于这一部分，我们设计了一个高级GCN，可显着增强香草GCN的鲁棒性，而不会增加时间复杂性。在四个现实世界图基准上进行的广泛实验表明，稳定的表现优于最先进的方法，并成功防御各种攻击。