To balance the annotation labor and the granularity of supervision, single-frame annotation has been introduced in temporal action localization. It provides a rough temporal location for an action but implicitly overstates the supervision from the annotated-frame during training, leading to the confusion between actions and backgrounds, i.e., action incompleteness and background false positives. To tackle the two challenges, in this work, we present the Snippet Classification model and the Dilation-Erosion module. In the Dilation-Erosion module, we expand the potential action segments with a loose criterion to alleviate the problem of action incompleteness and then remove the background from the potential action segments to alleviate the problem of action incompleteness. Relying on the single-frame annotation and the output of the snippet classification, the Dilation-Erosion module mines pseudo snippet-level ground-truth, hard backgrounds and evident backgrounds, which in turn further trains the Snippet Classification model. It forms a cyclic dependency. Furthermore, we propose a new embedding loss to aggregate the features of action instances with the same label and separate the features of actions from backgrounds. Experiments on THUMOS14 and ActivityNet 1.2 validate the effectiveness of the proposed method. Code has been made publicly available (https://github.com/LingJun123/single-frame-TAL).

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.

In this paper we revisit endless online level generation with the recently proposed experience-driven procedural content generation via reinforcement learning (EDRL) framework, from an observation that EDRL tends to generate recurrent patterns. Inspired by this phenomenon, we formulate a notion of state space closure, which means that any state that may appear in an infinite-horizon online generation process can be found in a finite horizon. Through theoretical analysis we find that though state space closure arises a concern about diversity, it makes the EDRL trained on a finite-horizon generalised to the infinite-horizon scenario without deterioration of content quality. Moreover, we verify the quality and diversity of contents generated by EDRL via empirical studies on the widely used Super Mario Bros. benchmark. Experimental results reveal that the current EDRL approach's ability of generating diverse game levels is limited due to the state space closure, whereas it does not suffer from reward deterioration given a horizon longer than the one of training. Concluding our findings and analysis, we argue that future works in generating online diverse and high-quality contents via EDRL should address the issue of diversity on the premise of state space closure which ensures the quality.

Facial attractiveness prediction (FAP) aims to assess the facial attractiveness automatically based on human aesthetic perception. Previous methods using deep convolutional neural networks have boosted the performance, but their giant models lead to a deficiency in flexibility. Besides, most of them fail to take full advantage of the dataset. In this paper, we present a novel end-to-end FAP approach integrating dual label distribution and lightweight design. To make the best use of the dataset, the manual ratings, attractiveness score, and standard deviation are aggregated explicitly to construct a dual label distribution, including the attractiveness distribution and the rating distribution. Such distributions, as well as the attractiveness score, are optimized under a joint learning framework based on the label distribution learning (LDL) paradigm. As for the lightweight design, the data processing is simplified to minimum, and MobileNetV2 is selected as our backbone. Extensive experiments are conducted on two benchmark datasets, where our approach achieves promising results and succeeds in striking a balance between performance and efficiency. Ablation studies demonstrate that our delicately designed learning modules are indispensable and correlated. Additionally, the visualization indicates that our approach is capable of perceiving facial attractiveness and capturing attractive facial regions to facilitate semantic predictions.

We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC), for video-text retrieval tasks. Our MAC aims to reduce video representation's spatial and temporal redundancy in the VidLP model by a mask sampling mechanism to improve pre-training efficiency. Comparing conventional temporal sparse sampling, we propose to randomly mask a high ratio of spatial regions and only feed visible regions into the encoder as sparse spatial sampling. Similarly, we adopt the mask sampling technique for text inputs for consistency. Instead of blindly applying the mask-then-prediction paradigm from MAE, we propose a masked-then-alignment paradigm for efficient video-text alignment. The motivation is that video-text retrieval tasks rely on high-level alignment rather than low-level reconstruction, and multimodal alignment with masked modeling encourages the model to learn a robust and general multimodal representation from incomplete and unstable inputs. Coupling these designs enables efficient end-to-end pre-training: reduce FLOPs (60% off), accelerate pre-training (by 3x), and improve performance. Our MAC achieves state-of-the-art results on various video-text retrieval datasets, including MSR-VTT, DiDeMo, and ActivityNet. Our approach is omnivorous to input modalities. With minimal modifications, we achieve competitive results on image-text retrieval tasks.

Social media has been one of the main information consumption sources for the public, allowing people to seek and spread information more quickly and easily. However, the rise of various social media platforms also enables the proliferation of online misinformation. In particular, misinformation in the health domain has significant impacts on our society such as the COVID-19 infodemic. Therefore, health misinformation in social media has become an emerging research direction that attracts increasing attention from researchers of different disciplines. Compared to misinformation in other domains, the key differences of health misinformation include the potential of causing actual harm to humans' bodies and even lives, the hardness to identify for normal people, and the deep connection with medical science. In addition, health misinformation on social media has distinct characteristics from conventional channels such as television on multiple dimensions including the generation, dissemination, and consumption paradigms. Because of the uniqueness and importance of combating health misinformation in social media, we conduct this survey to further facilitate interdisciplinary research on this problem. In this survey, we present a comprehensive review of existing research about online health misinformation in different disciplines. Furthermore, we also systematically organize the related literature from three perspectives: characterization, detection, and intervention. Lastly, we conduct a deep discussion on the pressing open issues of combating health misinformation in social media and provide future directions for multidisciplinary researchers.

Automatic Speech Recognition (ASR) systems typically yield output in lexical form. However, humans prefer a written form output. To bridge this gap, ASR systems usually employ Inverse Text Normalization (ITN). In previous works, Weighted Finite State Transducers (WFST) have been employed to do ITN. WFSTs are nicely suited to this task but their size and run-time costs can make deployment on embedded applications challenging. In this paper, we describe the development of an on-device ITN system that is streaming, lightweight & accurate. At the core of our system is a streaming transformer tagger, that tags lexical tokens from ASR. The tag informs which ITN category might be applied, if at all. Following that, we apply an ITN-category-specific WFST, only on the tagged text, to reliably perform the ITN conversion. We show that the proposed ITN solution performs equivalent to strong baselines, while being significantly smaller in size and retaining customization capabilities.

Lifelong learners must recognize concept vocabularies that evolve over time. A common yet underexplored scenario is learning with class labels over time that refine/expand old classes. For example, humans learn to recognize ${\tt dog}$ before dog breeds. In practical settings, dataset $\textit{versioning}$ often introduces refinement to ontologies, such as autonomous vehicle benchmarks that refine a previous ${\tt vehicle}$ class into ${\tt school-bus}$ as autonomous operations expand to new cities. This paper formalizes a protocol for studying the problem of $\textit{Learning with Evolving Class Ontology}$ (LECO). LECO requires learning classifiers in distinct time periods (TPs); each TP introduces a new ontology of "fine" labels that refines old ontologies of "coarse" labels (e.g., dog breeds that refine the previous ${\tt dog}$). LECO explores such questions as whether to annotate new data or relabel the old, how to leverage coarse labels, and whether to finetune the previous TP's model or train from scratch. To answer these questions, we leverage insights from related problems such as class-incremental learning. We validate them under the LECO protocol through the lens of image classification (CIFAR and iNaturalist) and semantic segmentation (Mapillary). Our experiments lead to surprising conclusions; while the current status quo is to relabel existing datasets with new ontologies (such as COCO-to-LVIS or Mapillary1.2-to-2.0), LECO demonstrates that a far better strategy is to annotate $\textit{new}$ data with the new ontology. However, this produces an aggregate dataset with inconsistent old-vs-new labels, complicating learning. To address this challenge, we adopt methods from semi-supervised and partial-label learning. Such strategies can surprisingly be made near-optimal, approaching an "oracle" that learns on the aggregate dataset exhaustively labeled with the newest ontology.

变压器验证引起了机器学习研究和行业的越来越多的关注。它正式验证了变压器对对抗性攻击的鲁棒性，例如用同义词交换单词。但是，由于以中线为中心的计算，变压器验证的性能仍然不令人满意，这与标准神经网络有显着差异。在本文中，我们提出了信仰，这是用于GPU的变压器验证的有效框架。我们首先提出一个语义意识的计算图转换，以识别语义信息，例如变压器验证中的结合计算。我们利用此类语义信息，以在计算图级别启用有效的内核融合。其次，我们提出了一个验证专门的内核手工艺品，以有效地将变压器验证映射到现代GPU。该手工艺者利用了一组GPU硬件支持，以加速通常是内存密集型的验证专业操作。第三，我们提出了一个专家指导的自动调整，以纳入有关GPU后端的专家知识，以促进大型搜索空间探索。广泛的评估表明，Faith在最先进的框架上实现了$ 2.1 \ times $至$ 3.4 \ times $（$ 2.6 \ times $）的加速。

电子商务搜索的关键是如何最好地利用大型但嘈杂的日志数据。在本文中，我们在Instacart介绍了基于嵌入的杂货搜索模型。该系统通过基于两个塔式变压器的编码器体系结构学习查询和产品表示。为了解决冷门问题，我们专注于基于内容的功能。为了在嘈杂的数据上有效地培训模型，我们提出了一种自我分歧学习方法和级联培训方法。Accon是一个离线人类评估数据集，我们在召回@20方面取得了10％的相对改善，对于在线A/B测试，我们每次搜索（CAPS）获得4.1％的Cart-Addds（CAPS）和1.5％的总商品价值（GMV）改进。我们描述了如何训练和部署基于嵌入的搜索模型，并对我们方法的有效性进行详细分析。