Due to its importance in facial behaviour analysis, facial action unit (AU) detection has attracted increasing attention from the research community. Leveraging the online knowledge distillation framework, we propose the ``FANTrans" method for AU detection. Our model consists of a hybrid network of convolution and transformer blocks to learn per-AU features and to model AU co-occurrences. The model uses a pre-trained face alignment network as the feature extractor. After further transformation by a small learnable add-on convolutional subnet, the per-AU features are fed into transformer blocks to enhance their representation. As multiple AUs often appear together, we propose a learnable attention drop mechanism in the transformer block to learn the correlation between the features for different AUs. We also design a classifier that predicts AU presence by considering all AUs' features, to explicitly capture label dependencies. Finally, we make the attempt of adapting online knowledge distillation in the training stage for this task, further improving the model's performance. Experiments on the BP4D and DISFA datasets demonstrating the effectiveness of proposed method.

点云语义分段由于其对光线的稳健性而引起了注意。这使其成为自动驾驶的理想语义解决方案。但是，考虑到神经网络的巨大计算负担和带宽的要求，将所有计算都放入车辆电子控制单元（ECU）不高度或实用。在本文中，我们根据范围视图提出了一个轻巧的点云语义分割网络。由于其简单的预处理和标准卷积，在像DPU这样的深度学习加速器上运行时，它是有效的。此外，为自动驾驶汽车构建了近传感器计算系统。在该系统中，放置在LIDAR传感器旁边的基于FPGA的深度学习加速器核心（DPU），以执行点云预处理和分割神经网络。通过仅将后处理步骤留给ECU，该解决方案大大减轻了ECU的计算负担，因此缩短了决策和车辆反应潜伏期。我们的语义分割网络在Xilinx DPU上获得了10帧（FPS），其计算效率为42.5 GOP/w。

在这项工作中，我们解决了长尾图像识别的具有挑战性的任务。以前的长尾识别方法通常集中于尾巴类别的数据增强或重新平衡策略，以在模型培训期间更加关注尾巴类。但是，由于尾巴类别的训练图像有限，尾部类图像的多样性仍受到限制，从而导致特征表现不佳。在这项工作中，我们假设头部和尾部类中的常见潜在特征可用于提供更好的功能表示。由此激励，我们引入了基于潜在类别的长尾识别（LCREG）方法。具体来说，我们建议学习一组在头和尾巴中共享的类不足的潜在特征。然后，我们通过将语义数据扩展应用于潜在特征，隐式地丰富了训练样本的多样性。对五个长尾图识别数据集进行的广泛实验表明，我们提出的LCREG能够显着超越先前的方法并实现最新结果。

本文提出了一种使用视频中心化的变压器在视频中面部聚类的新方法。以前的作品经常采用对比度学习来学习框架级表示，并使用平均池来汇总沿时间维度的特征。这种方法可能无法完全捕获复杂的视频动态。此外，尽管在基于视频的对比学习方面取得了最新进展，但很少有人试图学习一个自我监视的聚类友好的面部表现，从而使视频面部聚集任务受益。为了克服这些局限性，我们的方法采用了变压器直接学习视频级表示，可以更好地反映视频中面部的时间变化属性，而我们还建议一个以视频为中心的自我监督框架来训练变压器模型。我们还调查了以自我为中心视频的面部聚类，这是一个快速出现的领域，尚未在与面部聚类有关的作品中进行研究。为此，我们介绍并发布了第一个名为EasyCom-Clustering的大规模以egipentric视频群集群数据集。我们在广泛使用的大爆炸理论（BBT）数据集和新的easycom群集数据集上评估了我们的建议方法。结果表明，我们以视频为中心的变压器的性能超过了两个基准测试的所有先前最新方法，对面部视频表现出了自我牵强的理解。

多语言预训练的语言模型在跨语言任务上表现出了令人印象深刻的表现。它极大地促进了自然语言处理在低资源语言上的应用。但是，当前的多语言模型仍然有些语言表现不佳。在本文中，我们提出了Cino（中国少数族裔训练的语言模型），这是一种用于中国少数语言的多语言预训练的语言模型。它涵盖了标准的中文，Yue中文和其他六种少数民族语言。为了评估多语言模型在少数族裔语言上的跨语性能力，我们从Wikipedia和新闻网站收集文档，并构建两个文本分类数据集，WCM（Wiki-Chinese-Minority）和CMNEWS（中国最少的新闻）。我们表明，Cino在各种分类任务上的表现明显优于基准。Cino模型和数据集可在http://cino.hfl-rc.com上公开获得。

扩张的卷曲广泛用于深度语义分段模型，因为它们可以扩大过滤器的接收领域而不增加额外的权重，也不牺牲空间分辨率。然而，正如扩张的卷积滤波器在语义上有意义的轮廓上没有关于像素的位置知识，它们可能导致对象边界的模糊预测。另外，虽然扩张过滤器可以扩展其接收领域，但是采样像素的总数保持不变，这通常包括一小部分接收领域的总面积。灵感来自人类视觉系统中的横向抑制（LI）机制，我们提出了具有横向抑制（LI-CONVS）的扩张卷积以克服这些限制。介绍锂机制提高了卷积滤波器对语义对象边界的敏感性。此外，由于LI-DIVS也隐含地考虑从横向禁止的区域中的像素考虑，因此它们还可以以密度刻度提取特征。通过将锂致常规集成到Deeplabv3 +架构中，我们提出了横向抑制的不受欢迎的空间金字塔汇集（Li-Aspp），横向抑制的Mobilenet-V2（Li-MnV2）和横向抑制的Reset（Li-Reset）。在三个基准数据集（Pascal VOC 2012，Celebamask-HQ和Ade20k）的实验结果表明，我们的李氏分割模型越来越突出了所有这些的基线，从而验证了拟议的LI-CONN的有效性和一般性。

Real-world robotic grasping can be done robustly if a complete 3D Point Cloud Data (PCD) of an object is available. However, in practice, PCDs are often incomplete when objects are viewed from few and sparse viewpoints before the grasping action, leading to the generation of wrong or inaccurate grasp poses. We propose a novel grasping strategy, named 3DSGrasp, that predicts the missing geometry from the partial PCD to produce reliable grasp poses. Our proposed PCD completion network is a Transformer-based encoder-decoder network with an Offset-Attention layer. Our network is inherently invariant to the object pose and point's permutation, which generates PCDs that are geometrically consistent and completed properly. Experiments on a wide range of partial PCD show that 3DSGrasp outperforms the best state-of-the-art method on PCD completion tasks and largely improves the grasping success rate in real-world scenarios. The code and dataset will be made available upon acceptance.

Given an untrimmed video and natural language query, video sentence grounding aims to localize the target temporal moment in the video. Existing methods mainly tackle this task by matching and aligning semantics of the descriptive sentence and video segments on a single temporal resolution, while neglecting the temporal consistency of video content in different resolutions. In this work, we propose a novel multi-resolution temporal video sentence grounding network: MRTNet, which consists of a multi-modal feature encoder, a Multi-Resolution Temporal (MRT) module, and a predictor module. MRT module is an encoder-decoder network, and output features in the decoder part are in conjunction with Transformers to predict the final start and end timestamps. Particularly, our MRT module is hot-pluggable, which means it can be seamlessly incorporated into any anchor-free models. Besides, we utilize a hybrid loss to supervise cross-modal features in MRT module for more accurate grounding in three scales: frame-level, clip-level and sequence-level. Extensive experiments on three prevalent datasets have shown the effectiveness of MRTNet.

Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels. \mr{Intuitively, Flattening-Net implicitly approximates a locally smooth 3D-to-2D surface flattening process while effectively preserving neighborhood consistency.} \mr{As a generic representation modality, PGI inherently encodes the intrinsic property of the underlying manifold structure and facilitates surface-style point feature aggregation.} To demonstrate its potential, we construct a unified learning framework directly operating on PGIs to achieve \mr{diverse types of high-level and low-level} downstream applications driven by specific task networks, including classification, segmentation, reconstruction, and upsampling. Extensive experiments demonstrate that our methods perform favorably against the current state-of-the-art competitors. We will make the code and data publicly available at https://github.com/keeganhk/Flattening-Net.

We explore the usage of the Levenberg-Marquardt (LM) algorithm for regression (non-linear least squares) and classification (generalized Gauss-Newton methods) tasks in neural networks. We compare the performance of the LM method with other popular first-order algorithms such as SGD and Adam, as well as other second-order algorithms such as L-BFGS , Hessian-Free and KFAC. We further speed up the LM method by using adaptive momentum, learning rate line search, and uphill step acceptance.