User-generated-content (UGC) videos have dominated the Internet during recent years. While many methods attempt to objectively assess the quality of these UGC videos, the mechanisms of human quality perception in the UGC-VQA problem is still yet to be explored. To better explain the quality perception mechanisms and learn more robust representations, we aim to disentangle the effects of aesthetic quality issues and technical quality issues risen by the complicated video generation processes in the UGC-VQA problem. To overcome the absence of respective supervisions during disentanglement, we propose the Limited View Biased Supervisions (LVBS) scheme where two separate evaluators are trained with decomposed views specifically designed for each issue. Composed of an Aesthetic Quality Evaluator (AQE) and a Technical Quality Evaluator (TQE) under the LVBS scheme, the proposed Disentangled Objective Video Quality Evaluator (DOVER) reach excellent performance (0.91 SRCC for KoNViD-1k, 0.89 SRCC for LSVQ, 0.88 SRCC for YouTube-UGC) in the UGC-VQA problem. More importantly, our blind subjective studies prove that the separate evaluators in DOVER can effectively match human perception on respective disentangled quality issues. Codes and demos are released in https://github.com/teowu/dover.

当前的深度视频质量评估（VQA）方法通常在评估高分辨率视频时具有高计算成本。这使他们无法通过端到端培训学习更好的视频质量相关表示。现有方法通常考虑幼稚的采样以降低计算成本，例如调整大小和裁剪。但是，它们显然在视频中损坏了与质量相关的信息，因此并不是学习VQA的良好表示形式的最佳选择。因此，渴望为VQA设计一种新的质量保留抽样方案。在本文中，我们提出了网格迷你斑点采样（GMS），该采样允许通过在原始分辨率下采样贴片来考虑局部质量，并通过以统一网格采样的迷你绘制来涵盖全球质量。这些迷你斑点是剪接和对齐的，称为片段。我们进一步构建了专门设计的碎片注意网络（粉丝），以适应碎片作为输入。由片段和粉丝组成，VQA（快速VQA）提出的片段样品变压器可实现有效的端到端深VQA，并学习有效的与视频质量相关的表示。它可以提高最新准确性约10％，同时减少1080p高分辨率视频的99.5％的失败。新学习的与视频质量相关的表示形式也可以转移到较小的VQA数据集中，从而在这些情况下提高性能。广泛的实验表明，Fast-VQA在各种分辨率的输入方面具有良好的性能，同时保持高效率。我们在https://github.com/timothyhtimothy/fast-vqa上发布代码。

人的步态被认为是一种独特的生物识别标识符，其可以在距离处以覆盖方式获取。但是，在受控场景中捕获的现有公共领域步态数据集接受的模型导致应用于现实世界无约束步态数据时的剧烈性能下降。另一方面，视频人员重新识别技术在大规模公共可用数据集中实现了有希望的性能。鉴于服装特性的多样性，衣物提示对于人们的认可不可靠。因此，实际上尚不清楚为什么最先进的人重新识别方法以及他们的工作。在本文中，我们通过从现有的视频人重新识别挑战中提取剪影来构建一个新的步态数据集，该挑战包括1,404人以不受约束的方式行走。基于该数据集，可以进行步态认可与人重新识别之间的一致和比较研究。鉴于我们的实验结果表明，目前在受控情景收集的数据下设计的目前的步态识别方法不适合真实监视情景，我们提出了一种名为Realgait的新型步态识别方法。我们的结果表明，在实际监视情景中识别人的步态是可行的，并且潜在的步态模式可能是视频人重新设计在实践中的真正原因。

舞蹈挑战现在是Tiktok这样的视频社区中的病毒性。一旦挑战变得流行，就会在几天内上传成千上万的短型视频。因此，来自舞蹈挑战的病毒预测具有很大的商业价值，具有广泛的应用，例如智能推荐和普及促销。本文提出了一种集成骨骼，整体外观，面部和景区提示的新型多模态框架，以综合舞蹈病毒预测。为了模拟身体运动，我们提出了一种层次地改进了时空骨架图的金字塔骨架图卷积网络（PSGCN）。同时，我们介绍了一个关系时间卷积网络（RTCN），以利用非局部时间关系利用外观动态。最终提出了一种细心的融合方法，以自适应地从不同方式汇总预测。为了验证我们的方法，我们介绍了一个大规模的病毒舞蹈视频（VDV）数据集，其中包含超过4,000个病毒舞蹈挑战的舞蹈剪辑。 VDV数据集的广泛实验证明了我们模型的功效。对VDV数据集的广泛实验良好地证明了我们方法的有效性。此外，我们表明，可以从我们的模型中派生类似多维推荐和动作反馈等的短视频应用。

过度参数化神经网络（NNS）的小概括误差可以通过频率偏见现象来部分解释，在频率偏置现象中，基于梯度的算法将低频失误最小化，然后再减少高频残差。使用神经切线内核（NTK），可以为训练提供理论上严格的分析，其中数据是从恒定或分段构剂概率密度绘制的数据。由于大多数训练数据集不是从此类分布中汲取的，因此我们使用NTK模型和数据依赖性的正交规则来理论上量化NN训练的频率偏差，给定完全不均匀的数据。通过用精心选择的Sobolev规范替换损失函数，我们可以进一步扩大，抑制，平衡或逆转NN训练中的内在频率偏差。

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.

Knowledge graphs (KG) have served as the key component of various natural language processing applications. Commonsense knowledge graphs (CKG) are a special type of KG, where entities and relations are composed of free-form text. However, previous works in KG completion and CKG completion suffer from long-tail relations and newly-added relations which do not have many know triples for training. In light of this, few-shot KG completion (FKGC), which requires the strengths of graph representation learning and few-shot learning, has been proposed to challenge the problem of limited annotated data. In this paper, we comprehensively survey previous attempts on such tasks in the form of a series of methods and applications. Specifically, we first introduce FKGC challenges, commonly used KGs, and CKGs. Then we systematically categorize and summarize existing works in terms of the type of KGs and the methods. Finally, we present applications of FKGC models on prediction tasks in different areas and share our thoughts on future research directions of FKGC.

Few Shot Instance Segmentation (FSIS) requires models to detect and segment novel classes with limited several support examples. In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework. Our key insights are two folds: Firstly, with the aid of support masks, we can generate dynamic class centers more appropriately to re-weight query features. Secondly, we find that support object queries have already encoded key factors after base training. In this way, the query features can be enhanced twice from two aspects, i.e., feature-level and instance-level. In particular, we firstly design a mask-based dynamic weighting module to enhance support features and then propose to link object queries for better calibration via cross-attention. After the above steps, the novel classes can be improved significantly over our strong baseline. Additionally, our new framework can be easily extended to incremental FSIS with minor modification. When benchmarking results on the COCO dataset for FSIS, gFSIS, and iFSIS settings, our method achieves a competitive performance compared to existing approaches across different shots, e.g., we boost nAP by noticeable +8.2/+9.4 over the current state-of-the-art FSIS method for 10/30-shot. We further demonstrate the superiority of our approach on Few Shot Object Detection. Code and model will be available.

Graph Neural Networks (GNNs) have shown satisfying performance on various graph learning tasks. To achieve better fitting capability, most GNNs are with a large number of parameters, which makes these GNNs computationally expensive. Therefore, it is difficult to deploy them onto edge devices with scarce computational resources, e.g., mobile phones and wearable smart devices. Knowledge Distillation (KD) is a common solution to compress GNNs, where a light-weighted model (i.e., the student model) is encouraged to mimic the behavior of a computationally expensive GNN (i.e., the teacher GNN model). Nevertheless, most existing GNN-based KD methods lack fairness consideration. As a consequence, the student model usually inherits and even exaggerates the bias from the teacher GNN. To handle such a problem, we take initial steps towards fair knowledge distillation for GNNs. Specifically, we first formulate a novel problem of fair knowledge distillation for GNN-based teacher-student frameworks. Then we propose a principled framework named RELIANT to mitigate the bias exhibited by the student model. Notably, the design of RELIANT is decoupled from any specific teacher and student model structures, and thus can be easily adapted to various GNN-based KD frameworks. We perform extensive experiments on multiple real-world datasets, which corroborates that RELIANT achieves less biased GNN knowledge distillation while maintaining high prediction utility.

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.