通过网络视频的快速增长，视频语言建模引起了很多关注。大多数现有方法都假定视频帧和文本描述是语义上关联的，并专注于视频级别的视频模型。但是，该假设通常是有两个原因的：（1）凭借视频内容丰富的语义，很难用单个视频级别的描述覆盖所有帧； （2）原始视频通常具有嘈杂/毫无意义的信息（例如，镜头，过渡或预告片）。尽管最近的许多作品部署了注意力来减轻此问题，但无关/嘈杂的信息仍然使得很难解决。为了克服此类挑战，我们提出了一个高效有效的模型，称为语言引导网络（LGDN），用于视频语言建模。与使用所有提取的视频帧的大多数现有方法不同，LGDN在语言监督下动态过滤了未对准或冗余的帧，并且每个视频仅获得2---4个显着帧，以进行交叉模式令牌级别的对准。在五个公共数据集上进行的广泛实验表明，我们的LGDN优于最先进的利润率。我们还提供了详细的消融研究，以揭示解决噪声问题的关键重要性，以启发未来的视频语言工作。

人工智能（AI）的基本目标是模仿人类的核心认知活动。尽管在AI研究中取得了巨大的成功，但大多数现有方法仅具有单认知能力。为了克服这一局限性并迈出了朝着人工通用智能（AGI）迈出的坚实一步，我们开发了一个通过庞大的多模式数据进行预训练的基础模型，可以快速适应各种下游认知任务。为了实现这一目标，我们建议通过从Internet上拖延的语义相关数据进行自我监督的学习来预先培训我们的基础模型，并表明可以在各种下游任务上获得有希望的结果。特别是，使用开发的模型解剖工具，我们证明了我们的基础模型现在拥有强大的想象力。我们认为，我们的工作从我们的“弱或狭窄AI”的常见实践到“强或广泛的AI”迈出了转变的迈向AGI。

Brain midline shift (MLS) is one of the most critical factors to be considered for clinical diagnosis and treatment decision-making for intracranial hemorrhage. Existing computational methods on MLS quantification not only require intensive labeling in millimeter-level measurement but also suffer from poor performance due to their dependence on specific landmarks or simplified anatomical assumptions. In this paper, we propose a novel semi-supervised framework to accurately measure the scale of MLS from head CT scans. We formulate the MLS measurement task as a deformation estimation problem and solve it using a few MLS slices with sparse labels. Meanwhile, with the help of diffusion models, we are able to use a great number of unlabeled MLS data and 2793 non-MLS cases for representation learning and regularization. The extracted representation reflects how the image is different from a non-MLS image and regularization serves an important role in the sparse-to-dense refinement of the deformation field. Our experiment on a real clinical brain hemorrhage dataset has achieved state-of-the-art performance and can generate interpretable deformation fields.

Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different domains. Existing UDA approaches highly depend on the accessibility of source domain data, which is usually limited in practical scenarios due to privacy protection, data storage and transmission cost, and computation burden. To tackle this issue, many source-free unsupervised domain adaptation (SFUDA) methods have been proposed recently, which perform knowledge transfer from a pre-trained source model to unlabeled target domain with source data inaccessible. A comprehensive review of these works on SFUDA is of great significance. In this paper, we provide a timely and systematic literature review of existing SFUDA approaches from a technical perspective. Specifically, we categorize current SFUDA studies into two groups, i.e., white-box SFUDA and black-box SFUDA, and further divide them into finer subcategories based on different learning strategies they use. We also investigate the challenges of methods in each subcategory, discuss the advantages/disadvantages of white-box and black-box SFUDA methods, conclude the commonly used benchmark datasets, and summarize the popular techniques for improved generalizability of models learned without using source data. We finally discuss several promising future directions in this field.

Graph Neural Networks (GNNs) have been a prevailing technique for tackling various analysis tasks on graph data. A key premise for the remarkable performance of GNNs relies on complete and trustworthy initial graph descriptions (i.e., node features and graph structure), which is often not satisfied since real-world graphs are often incomplete due to various unavoidable factors. In particular, GNNs face greater challenges when both node features and graph structure are incomplete at the same time. The existing methods either focus on feature completion or structure completion. They usually rely on the matching relationship between features and structure, or employ joint learning of node representation and feature (or structure) completion in the hope of achieving mutual benefit. However, recent studies confirm that the mutual interference between features and structure leads to the degradation of GNN performance. When both features and structure are incomplete, the mismatch between features and structure caused by the missing randomness exacerbates the interference between the two, which may trigger incorrect completions that negatively affect node representation. To this end, in this paper we propose a general GNN framework based on teacher-student distillation to improve the performance of GNNs on incomplete graphs, namely T2-GNN. To avoid the interference between features and structure, we separately design feature-level and structure-level teacher models to provide targeted guidance for student model (base GNNs, such as GCN) through distillation. Then we design two personalized methods to obtain well-trained feature and structure teachers. To ensure that the knowledge of the teacher model is comprehensively and effectively distilled to the student model, we further propose a dual distillation mode to enable the student to acquire as much expert knowledge as possible.

Deep neural networks (DNNs) are sensitive and susceptible to tiny perturbation by adversarial attacks which causes erroneous predictions. Various methods, including adversarial defense and uncertainty inference (UI), have been developed in recent years to overcome the adversarial attacks. In this paper, we propose a multi-head uncertainty inference (MH-UI) framework for detecting adversarial attack examples. We adopt a multi-head architecture with multiple prediction heads (i.e., classifiers) to obtain predictions from different depths in the DNNs and introduce shallow information for the UI. Using independent heads at different depths, the normalized predictions are assumed to follow the same Dirichlet distribution, and we estimate distribution parameter of it by moment matching. Cognitive uncertainty brought by the adversarial attacks will be reflected and amplified on the distribution. Experimental results show that the proposed MH-UI framework can outperform all the referred UI methods in the adversarial attack detection task with different settings.

Weakly supervised semantic segmentation (WSSS) with image-level labels is a challenging task in computer vision. Mainstream approaches follow a multi-stage framework and suffer from high training costs. In this paper, we explore the potential of Contrastive Language-Image Pre-training models (CLIP) to localize different categories with only image-level labels and without any further training. To efficiently generate high-quality segmentation masks from CLIP, we propose a novel framework called CLIP-ES for WSSS. Our framework improves all three stages of WSSS with special designs for CLIP: 1) We introduce the softmax function into GradCAM and exploit the zero-shot ability of CLIP to suppress the confusion caused by non-target classes and backgrounds. Meanwhile, to take full advantage of CLIP, we re-explore text inputs under the WSSS setting and customize two text-driven strategies: sharpness-based prompt selection and synonym fusion. 2) To simplify the stage of CAM refinement, we propose a real-time class-aware attention-based affinity (CAA) module based on the inherent multi-head self-attention (MHSA) in CLIP-ViTs. 3) When training the final segmentation model with the masks generated by CLIP, we introduced a confidence-guided loss (CGL) to mitigate noise and focus on confident regions. Our proposed framework dramatically reduces the cost of training for WSSS and shows the capability of localizing objects in CLIP. Our CLIP-ES achieves SOTA performance on Pascal VOC 2012 and MS COCO 2014 while only taking 10% time of previous methods for the pseudo mask generation. Code is available at https://github.com/linyq2117/CLIP-ES.

Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long videos. In this paper, we introduce a new framework of contrastive action representation learning (CARL) to learn frame-wise action representation in a self-supervised or weakly-supervised manner, especially for long videos. Specifically, we introduce a simple but effective video encoder that considers both spatial and temporal context by combining convolution and transformer. Inspired by the recent massive progress in self-supervised learning, we propose a new sequence contrast loss (SCL) applied to two related views obtained by expanding a series of spatio-temporal data in two versions. One is the self-supervised version that optimizes embedding space by minimizing KL-divergence between sequence similarity of two augmented views and prior Gaussian distribution of timestamp distance. The other is the weakly-supervised version that builds more sample pairs among videos using video-level labels by dynamic time wrapping (DTW). Experiments on FineGym, PennAction, and Pouring datasets show that our method outperforms previous state-of-the-art by a large margin for downstream fine-grained action classification and even faster inference. Surprisingly, although without training on paired videos like in previous works, our self-supervised version also shows outstanding performance in video alignment and fine-grained frame retrieval tasks.

Homography estimation is a basic computer vision task, which aims to obtain the transformation from multi-view images for image alignment. Unsupervised learning homography estimation trains a convolution neural network for feature extraction and transformation matrix regression. While the state-of-theart homography method is based on convolution neural networks, few work focuses on transformer which shows superiority in highlevel vision tasks. In this paper, we propose a strong-baseline model based on the Swin Transformer, which combines convolution neural network for local features and transformer module for global features. Moreover, a cross non-local layer is introduced to search the matched features within the feature maps coarsely. In the homography regression stage, we adopt an attention layer for the channels of correlation volume, which can drop out some weak correlation feature points. The experiment shows that in 8 Degree-of-Freedoms(DOFs) homography estimation our method overperforms the state-of-the-art method.

Online learning naturally arises in many statistical and machine learning problems. The most widely used methods in online learning are stochastic first-order algorithms. Among this family of algorithms, there is a recently developed algorithm, Recursive One-Over-T SGD (ROOT-SGD). ROOT-SGD is advantageous in that it converges at a non-asymptotically fast rate, and its estimator further converges to a normal distribution. However, this normal distribution has unknown asymptotic covariance; thus cannot be directly applied to measure the uncertainty. To fill this gap, we develop two estimators for the asymptotic covariance of ROOT-SGD. Our covariance estimators are useful for statistical inference in ROOT-SGD. Our first estimator adopts the idea of plug-in. For each unknown component in the formula of the asymptotic covariance, we substitute it with its empirical counterpart. The plug-in estimator converges at the rate $\mathcal{O}(1/\sqrt{t})$, where $t$ is the sample size. Despite its quick convergence, the plug-in estimator has the limitation that it relies on the Hessian of the loss function, which might be unavailable in some cases. Our second estimator is a Hessian-free estimator that overcomes the aforementioned limitation. The Hessian-free estimator uses the random-scaling technique, and we show that it is an asymptotically consistent estimator of the true covariance.