Neural Architecture Search (NAS) is an automatic technique that can search for well-performed architectures for a specific task. Although NAS surpasses human-designed architecture in many fields, the high computational cost of architecture evaluation it requires hinders its development. A feasible solution is to directly evaluate some metrics in the initial stage of the architecture without any training. NAS without training (WOT) score is such a metric, which estimates the final trained accuracy of the architecture through the ability to distinguish different inputs in the activation layer. However, WOT score is not an atomic metric, meaning that it does not represent a fundamental indicator of the architecture. The contributions of this paper are in three folds. First, we decouple WOT into two atomic metrics which represent the distinguishing ability of the network and the number of activation units, and explore better combination rules named (Distinguishing Activation Score) DAS. We prove the correctness of decoupling theoretically and confirmed the effectiveness of the rules experimentally. Second, in order to improve the prediction accuracy of DAS to meet practical search requirements, we propose a fast training strategy. When DAS is used in combination with the fast training strategy, it yields more improvements. Third, we propose a dataset called Darts-training-bench (DTB), which fills the gap that no training states of architecture in existing datasets. Our proposed method has 1.04$\times$ - 1.56$\times$ improvements on NAS-Bench-101, Network Design Spaces, and the proposed DTB.

Dialogue state tracking (DST) aims to convert the dialogue history into dialogue states which consist of slot-value pairs. As condensed structural information memorizing all history information, the dialogue state in the last turn is typically adopted as the input for predicting the current state by DST models. However, these models tend to keep the predicted slot values unchanged, which is defined as state momentum in this paper. Specifically, the models struggle to update slot values that need to be changed and correct wrongly predicted slot values in the last turn. To this end, we propose MoNET to tackle state momentum via noise-enhanced training. First, the previous state of each turn in the training data is noised via replacing some of its slot values. Then, the noised previous state is used as the input to learn to predict the current state, improving the model's ability to update and correct slot values. Furthermore, a contrastive context matching framework is designed to narrow the representation distance between a state and its corresponding noised variant, which reduces the impact of noised state and makes the model better understand the dialogue history. Experimental results on MultiWOZ datasets show that MoNET outperforms previous DST methods. Ablations and analysis verify the effectiveness of MoNET in alleviating state momentum and improving anti-noise ability.

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

Most existing text-video retrieval methods focus on cross-modal matching between the visual content of offline videos and textual query sentences. However, in real scenarios, online videos are frequently accompanied by relevant text information such as titles, tags, and even subtitles, which can be utilized to match textual queries. This inspires us to generate associated captions from offline videos to help with existing text-video retrieval methods. To do so, we propose to use the zero-shot video captioner with knowledge of pre-trained web-scale models (e.g., CLIP and GPT-2) to generate captions for offline videos without any training. Given the captions, one question naturally arises: what can auxiliary captions do for text-video retrieval? In this paper, we present a novel framework Cap4Video, which makes use of captions from three aspects: i) Input data: The video and captions can form new video-caption pairs as data augmentation for training. ii) Feature interaction: We perform feature interaction between video and caption to yield enhanced video representations. iii) Output score: The Query-Caption matching branch can be complementary to the original Query-Video matching branch for text-video retrieval. We conduct thorough ablation studies to demonstrate the effectiveness of our method. Without any post-processing, our Cap4Video achieves state-of-the-art performance on MSR-VTT (51.4%), VATEX (66.6%), MSVD (51.8%), and DiDeMo (52.0%).

Vision-language models (VLMs) that are pre-trained on large-scale image-text pairs have demonstrated impressive transferability on a wide range of visual tasks. Transferring knowledge from such powerful pre-trained VLMs is emerging as a promising direction for building effective video recognition models. However, the current exploration is still limited. In our opinion, the greatest charm of pre-trained vision-language models is to build a bridge between visual and textual domains. In this paper, we present a novel framework called BIKE which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We propose a Video Attribute Association mechanism which leverages the Video-to-Text knowledge to generate textual auxiliary attributes to complement video recognition. ii) We also present a Temporal Concept Spotting mechanism which uses the Text-to-Video expertise to capture temporal saliency in a parameter-free manner to yield enhanced video representation. The extensive studies on popular video datasets (ie, Kinetics-400 & 600, UCF-101, HMDB-51 and ActivityNet) show that our method achieves state-of-the-art performance in most recognition scenarios, eg, general, zero-shot, and few-shot video recognition. To the best of our knowledge, our best model achieves a state-of-the-art accuracy of 88.4% on challenging Kinetics-400 with the released CLIP pre-trained model.

Frost damage is one of the main factors leading to wheat yield reduction. Therefore, the detection of wheat frost accurately and efficiently is beneficial for growers to take corresponding measures in time to reduce economic loss. To detect the wheat frost, in this paper we create a hyperspectral wheat frost data set by collecting the data characterized by temperature, wheat yield, and hyperspectral information provided by the handheld hyperspectral spectrometer. However, due to the imbalance of data, that is, the number of healthy samples is much higher than the number of frost damage samples, a deep learning algorithm tends to predict biasedly towards the healthy samples resulting in model overfitting of the healthy samples. Therefore, we propose a method based on deep cost-sensitive learning, which uses a one-dimensional convolutional neural network as the basic framework and incorporates cost-sensitive learning with fixed factors and adjustment factors into the loss function to train the network. Meanwhile, the accuracy and score are used as evaluation metrics. Experimental results show that the detection accuracy and the score reached 0.943 and 0.623 respectively, this demonstration shows that this method not only ensures the overall accuracy but also effectively improves the detection rate of frost samples.

Independent component analysis (ICA) is a blind source separation method to recover source signals of interest from their mixtures. Most existing ICA procedures assume independent sampling. Second-order-statistics-based source separation methods have been developed based on parametric time series models for the mixtures from the autocorrelated sources. However, the second-order-statistics-based methods cannot separate the sources accurately when the sources have temporal autocorrelations with mixed spectra. To address this issue, we propose a new ICA method by estimating spectral density functions and line spectra of the source signals using cubic splines and indicator functions, respectively. The mixed spectra and the mixing matrix are estimated by maximizing the Whittle likelihood function. We illustrate the performance of the proposed method through simulation experiments and an EEG data application. The numerical results indicate that our approach outperforms existing ICA methods, including SOBI algorithms. In addition, we investigate the asymptotic behavior of the proposed method.

Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field. To address it, we propose a progressive estimation strategy by converting large-baseline homography into multiple intermediate ones, cumulatively multiplying these intermediate items can reconstruct the initial homography. Meanwhile, a semi-supervised homography identity loss, which consists of two components: a supervised objective and an unsupervised objective, is introduced. The first supervised loss is acting to optimize intermediate homographies, while the second unsupervised one helps to estimate a large-baseline homography without photometric losses. To validate our method, we propose a large-scale dataset that covers regular and challenging scenes. Experiments show that our method achieves state-of-the-art performance in large-baseline scenes while keeping competitive performance in small-baseline scenes. Code and dataset are available at https://github.com/megvii-research/LBHomo.

本文衡量了跨语言寄存器变化的稳定性。寄存器是各种与语言上下文相关的语言。寄存器及其上下文之间的关系是功能的：构成寄存器的语言特征是由交流状况的需求和约束所激发的。该观点假设寄存器应该是通用的，因此我们期望定义寄存器的语言外部环境与寄存器所包含的语言特征集之间存在稳定的关系。在本文中，使用在可比的交流情况下生成的Corpora在60种语言中比较寄存器特定语言中的变化来测试寄存器变化的普遍性和鲁棒性：推文和Wikipedia文章。我们的发现证实了寄存器变化实际上是普遍的预测。

图像介入已取得了显着的进步和启发的丰富方法，其中关键瓶颈被确定为如何实现具有语义上掩盖区域的高频结构和低频纹理信息。为此，深层模型具有强大的优势来捕捉它们，但对当地空间区域受到限制。在本文中，我们在全球范围内深入研究纹理和构造信息，以便很好地捕获图像插入图像的语义。与被困在独立本地补丁上的现有艺术相反，每个贴片的纹理信息都是从整个图像上的所有其他补丁中重建的，以匹配填充的信息，特别是掩盖区域上的结构信息。与用于图像插入的像素级别内的当前仅解码器变压器不同，我们的模型采用了与编码器和解码器配对的变压器管道。一方面，编码器通过自我发项模块捕获了图像跨图像的所有贴片的纹理语义相关性。另一方面，在解码器中，在掩盖区域上填充的贴片的解码器中，自适应贴片词汇是动态建立的。在此基础上，锚定在已知区域上的结构文本匹配的注意模块嫁给了这两个世界中最好的，以通过概率扩散过程进行渐进的介绍。我们的模型与时尚艺术是正交的，例如卷积神经网络（CNN），注意力和变压器模型，从纹理和结构信息的角度用于图像插入图像。基准的广泛实验验证了其优越性。我们的代码可在https://github.com/htyjers/dgts-inpainting上找到。