Crowd counting is usually handled in a density map regression fashion, which is supervised via a L2 loss between the predicted density map and ground truth. To effectively regulate models, various improved L2 loss functions have been proposed to find a better correspondence between predicted density and annotation positions. In this paper, we propose to predict the density map at one resolution but measure the density map at multiple resolutions. By maximizing the posterior probability in such a setting, we obtain a log-formed multi-resolution L2-difference loss, where the traditional single-resolution L2 loss is its particular case. We mathematically prove it is superior to a single-resolution L2 loss. Without bells and whistles, the proposed loss substantially improves several baselines and performs favorably compared to state-of-the-art methods on four crowd counting datasets, ShanghaiTech A & B, UCF-QNRF, and JHU-Crowd++.

Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseudo labels and self-refining anomaly scores with these labels. As the pseudo labels play a crucial role, we propose an enhancement framework by exploiting completeness and uncertainty properties for effective self-training. Specifically, we first design a multi-head classification module (each head serves as a classifier) with a diversity loss to maximize the distribution differences of predicted pseudo labels across heads. This encourages the generated pseudo labels to cover as many abnormal events as possible. We then devise an iterative uncertainty pseudo label refinement strategy, which improves not only the initial pseudo labels but also the updated ones obtained by the desired classifier in the second stage. Extensive experimental results demonstrate the proposed method performs favorably against state-of-the-art approaches on the UCF-Crime, TAD, and XD-Violence benchmark datasets.

Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realize global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissues structures. Inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting anatomies of 133 structures in brain, 14 organs in abdomen, 4 hierarchical components in kidney, and inter-connected kidney tumors). We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in single network, outperforms prior state-of-the-art method SLANT27 ensembled with 27 network tiles, our model performance increases the mean DSC score of the publicly available Colin and CANDI dataset from 0.7264 to 0.7444 and from 0.6968 to 0.7025, respectively.

常规作品通常采用两阶段模型，其中生成器选择最重要的部分，然后是根据所选零件进行预测的预测因子。但是，这样的两相模型可能会引起变性问题，其中预测变量过度适合尚未训练的发电机生成的噪声，然后导致发电机收敛到倾向于选择无意义的碎片的亚最佳模型。为了应对这一挑战，我们提出了折叠的合理化（FR），将理由模型的两个阶段折叠成一个文本语义提取的角度。FR的关键思想是在发电机和预测器之间采用统一的编码器，基于FR可以通过访问传统两相模型中发电机阻止的有价值的信息来促进更好的预测指标，从而带来更好的生成器。从经验上讲，我们表明，与最先进的方法相比，FR将F1得分提高了10.3％。

由于维度的诅咒和训练数据的限制，即使对于强大的深度神经网络，近似高维功能是一个非常具有挑战性的任务。灵感来自使用可逆剩余网络（REVNET）的非线性级别集学习（NLL）方法，本文提出了一种通过学习级别集（钻头）的尺寸减少方法，用于函数近似。我们的方法包含两个主要组件：一个是伪可逆神经网络（PRNN）模块，有效地将高维输入变量转换为低维活动变量，另一个是基于变换的近似函数值的合成回归模块低维空间中的数据。 PRNN由于使用RevEN而言，PRNN不仅放宽了NLL方法中存在的非线性变换的可逆性约束，还可以自适应地重量每个样本的影响并控制函数对学习的活动变量的灵敏度。合成的回归使用输入空间中的欧几里德距离来选择相邻样本，其在活动变量的空间上的投影用于执行局部最小二乘性多项式拟合。这有助于解决传统本地和全球回归中存在的数值振荡问题。广泛的实验结果表明，我们的钻探方法优于NLL和有源子空间方法，特别是当目标函数在其输入域内部拥有临界点时。

部分微分方程通常用于模拟各种物理现象，例如热扩散，波传播，流体动力学，弹性，电动力学和图像处理，并且已经开发了许多分析方法或传统的数值方法并广泛用于其溶液。受深度学习对科学和工程研究的迅速影响的启发，在本文中，我们提出了一个新型的神经网络GF-NET，以无监督的方式学习绿色的线性反应扩散方程的功能。所提出的方法克服了通过使用物理信息的方法和绿色功能的对称性来查找任意域上方程函数的挑战。结果，它尤其导致了在不同边界条件和来源下解决目标方程的有效方法。我们还通过正方形，环形和L形域中的实验证明了所提出的方法的有效性。

The counting task, which plays a fundamental rule in numerous applications (e.g., crowd counting, traffic statistics), aims to predict the number of objects with various densities. Existing object counting tasks are designed for a single object class. However, it is inevitable to encounter newly coming data with new classes in our real world. We name this scenario as \textit{evolving object counting}. In this paper, we build the first evolving object counting dataset and propose a unified object counting network as the first attempt to address this task. The proposed model consists of two key components: a class-agnostic mask module and a class-increment module. The class-agnostic mask module learns generic object occupation prior via predicting a class-agnostic binary mask (e.g., 1 denotes there exists an object at the considering position in an image and 0 otherwise). The class-increment module is used to handle new coming classes and provides discriminative class guidance for density map prediction. The combined outputs of class-agnostic mask module and image feature extractor are used to predict the final density map. When new classes come, we first add new neural nodes into the last regression and classification layers of this module. Then, instead of retraining the model from scratch, we utilize knowledge distilling to help the model remember what have already learned about previous object classes. We also employ a support sample bank to store a small number of typical training samples of each class, which are used to prevent the model from forgetting key information of old data. With this design, our model can efficiently and effectively adapt to new coming classes while keeping good performance on already seen data without large-scale retraining. Extensive experiments on the collected dataset demonstrate the favorable performance.

Accurate spatial-temporal traffic flow forecasting is essential for helping traffic managers to take control measures and drivers to choose the optimal travel routes. Recently, graph convolutional networks (GCNs) have been widely used in traffic flow prediction owing to their powerful ability to capture spatial-temporal dependencies. The design of the spatial-temporal graph adjacency matrix is a key to the success of GCNs, and it is still an open question. This paper proposes reconstructing the binary adjacency matrix via tensor decomposition, and a traffic flow forecasting method is proposed. First, we reformulate the spatial-temporal fusion graph adjacency matrix into a three-way adjacency tensor. Then, we reconstructed the adjacency tensor via Tucker decomposition, wherein more informative and global spatial-temporal dependencies are encoded. Finally, a Spatial-temporal Synchronous Graph Convolutional module for localized spatial-temporal correlations learning and a Dilated Convolution module for global correlations learning are assembled to aggregate and learn the comprehensive spatial-temporal dependencies of the road network. Experimental results on four open-access datasets demonstrate that the proposed model outperforms state-of-the-art approaches in terms of the prediction performance and computational cost.

Existing approaches for vision-and-language navigation (VLN) are mainly based on cross-modal reasoning over discrete views. However, this scheme may hamper an agent's spatial and numerical reasoning because of incomplete objects within a single view and duplicate observations across views. A potential solution is mapping discrete views into a unified birds's-eye view, which can aggregate partial and duplicate observations. Existing metric maps could achieve this goal, but they suffer from less expressive semantics (e.g. usually predefined labels) and limited map size, which weakens an agent's language grounding and long-term planning ability. Inspired by the robotics community, we introduce hybrid topo-metric maps into VLN, where a topological map is used for long-term planning and a metric map for short-term reasoning. Beyond mapping with more expressive deep features, we further design a pre-training framework via the hybrid map to learn language-informed map representations, which enhances cross-modal grounding and facilitates the final language-guided navigation goal. Extensive experiments demonstrate the effectiveness of the map-based route for VLN, and the proposed method sets the new state-of-the-art on three VLN benchmarks.

Crowd localization aims to predict the spatial position of humans in a crowd scenario. We observe that the performance of existing methods is challenged from two aspects: (i) ranking inconsistency between test and training phases; and (ii) fixed anchor resolution may underfit or overfit crowd densities of local regions. To address these problems, we design a supervision target reassignment strategy for training to reduce ranking inconsistency and propose an anchor pyramid scheme to adaptively determine the anchor density in each image region. Extensive experimental results on three widely adopted datasets (ShanghaiTech A\&B, JHU-CROWD++, UCF-QNRF) demonstrate the favorable performance against several state-of-the-art methods.