Recent studies have shown that using an external Language Model (LM) benefits the end-to-end Automatic Speech Recognition (ASR). However, predicting tokens that appear less frequently in the training set is still quite challenging. The long-tail prediction problems have been widely studied in many applications, but only been addressed by a few studies for ASR and LMs. In this paper, we propose a new memory augmented lookup dictionary based Transformer architecture for LM. The newly introduced lookup dictionary incorporates rich contextual information in training set, which is vital to correctly predict long-tail tokens. With intensive experiments on Chinese and English data sets, our proposed method is proved to outperform the baseline Transformer LM by a great margin on both word/character error rate and tail tokens error rate. This is achieved without impact on the decoding efficiency. Overall, we demonstrate the effectiveness of our proposed method in boosting the ASR decoding performance, especially for long-tail tokens.

Video-language pre-training has advanced the performance of various downstream video-language tasks. However, most previous methods directly inherit or adapt typical image-language pre-training paradigms to video-language pre-training, thus not fully exploiting the unique characteristic of video, i.e., temporal. In this paper, we propose a Hierarchical Temporal-Aware video-language pre-training framework, HiTeA, with two novel pre-training tasks for modeling cross-modal alignment between moments and texts as well as the temporal relations of video-text pairs. Specifically, we propose a cross-modal moment exploration task to explore moments in videos, which results in detailed video moment representation. Besides, the inherent temporal relations are captured by aligning video-text pairs as a whole in different time resolutions with multi-modal temporal relation exploration task. Furthermore, we introduce the shuffling test to evaluate the temporal reliance of datasets and video-language pre-training models. We achieve state-of-the-art results on 15 well-established video-language understanding and generation tasks, especially on temporal-oriented datasets (e.g., SSv2-Template and SSv2-Label) with 8.6% and 11.1% improvement respectively. HiTeA also demonstrates strong generalization ability when directly transferred to downstream tasks in a zero-shot manner. Models and demo will be available on ModelScope.

Accompanying rapid industrialization, humans are suffering from serious air pollution problems. The demand for air quality prediction is becoming more and more important to the government's policy-making and people's daily life. In this paper, We propose GreenEyes -- a deep neural network model, which consists of a WaveNet-based backbone block for learning representations of sequences and an LSTM with a Temporal Attention module for capturing the hidden interactions between features of multi-channel inputs. To evaluate the effectiveness of our proposed method, we carry out several experiments including an ablation study on our collected and preprocessed air quality data near HKUST. The experimental results show our model can effectively predict the air quality level of the next timestamp given any segment of the air quality data from the data set. We have also released our standalone dataset at https://github.com/AI-Huang/IAQI_Dataset The model and code for this paper are publicly available at https://github.com/AI-Huang/AirEvaluation

Interoperability issue is a significant problem in Building Information Modeling (BIM). Object type, as a kind of critical semantic information needed in multiple BIM applications like scan-to-BIM and code compliance checking, also suffers when exchanging BIM data or creating models using software of other domains. It can be supplemented using deep learning. Current deep learning methods mainly learn from the shape information of BIM objects for classification, leaving relational information inherent in the BIM context unused. To address this issue, we introduce a two-branch geometric-relational deep learning framework. It boosts previous geometric classification methods with relational information. We also present a BIM object dataset IFCNet++, which contains both geometric and relational information about the objects. Experiments show that our framework can be flexibly adapted to different geometric methods. And relational features do act as a bonus to general geometric learning methods, obviously improving their classification performance, thus reducing the manual labor of checking models and improving the practical value of enriched BIM models.

This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting. It is optimized specifically for low-power processor units like microcontrollers. ML operators exhibit heterogeneous efficiency profiles on power-efficient hardware. Given the exact theoretical computation cost, int8 operators are more computation-effective than float operators, and linear layers are often more efficient than other layers. The proposed LiCo-Net is a dual-phase system that uses the efficient int8 linear operators at the inference phase and applies streaming convolutions at the training phase to maintain a high model capacity. The experimental results show that LiCo-Net outperforms single-value decomposition filter (SVDF) on hardware efficiency with on-par detection performance. Compared to SVDF, LiCo-Net reduces cycles by 40% on HiFi4 DSP.

用于提取和抽象性摘要系统的传统培训范例始终仅使用令牌级别或句子级培训目标。但是，始终从摘要级别评估输出摘要，从而导致培训和评估的不一致。在本文中，我们提出了一个基于对比度学习的重新排列框架，用于一阶段的摘要，称为COLO。通过建模对比目标，我们表明摘要模型能够根据摘要级别的分数直接生成摘要，而无需其他模块和参数。广泛的实验表明，CORO在CNN/DailyMail基准测试中提高了单阶段系统的提取和抽象结果，将其提高到44.58和46.33 Rouge-1得分，同时保留了参数效率和推断效率。与最先进的多阶段系统相比，我们节省了100多个GPU训练时间，并在推理期间获得3〜8加速比，同时保持可比的结果。

本文重新讨论了一个非常简单但非常有效的计算范式，深度共同学习（DML）。我们观察到，有效性与其出色的概括质量高度相关。在本文中，我们从新的角度来解释了DML的性能改善，即这大约是贝叶斯后的采样程序。这也为应用R \'{e} nyi Divergence改善原始DML的基础建立了基础，因为它带来了先验的差异控制（在DML的上下文中）。因此，我们提出了r \'{e} nyi Divergence深度共同学习（RDML）。我们的经验结果代表了DML和\ renyi {}差异的婚姻的优势。R \'{E} nyi Divergence施加的灵活控制能够进一步改进DML，以学习更好的广义模型。

深度估计对于各种重要的现实世界应用至关重要，例如自动驾驶。但是，在高速场景中，它遭受了严重的性能退化，因为传统相机只能捕获模糊的图像。为了解决这个问题，Spike摄像头旨在以高框架速率捕获像素的亮度强度。但是，使用传统的单眼或立体声深度估计算法，使用尖峰摄像机的深度估计仍然非常具有挑战性，这些算法基于光度一致性。在本文中，我们提出了一种新型的不确定性引导深度融合（UGDF）框架，以融合Spike摄像机的单眼和立体声深度估计网络的预测。我们的框架是由于立体声尖峰深度估计在近距离取得更好的结果，而单眼尖峰深度估计获得了更好的结果。因此，我们引入了具有联合培训策略的双任务深度估计结构，并估算了分布式不确定性以融合单眼和立体声结果。为了证明尖峰深度估计比传统的摄像头深度估计的优势，我们为一个名为CitySpike20k的尖峰深度数据集，其中包含20k配对的样品，以进行尖峰深度估计。 UGDF在CitySpike20k上取得了最新的结果，超过了所有单眼或立体声尖峰深度估计基线。我们进行了广泛的实验，以评估我们方法对CitySpike20k的有效性和概括。据我们所知，我们的框架是第一个用于尖峰摄像头深度估算的双任务融合框架。代码和数据集将发布。

神经形态尖峰摄像机以生物启发的方式生成具有高时间分辨率的数据流，该方式在自动驾驶等现实世界应用中具有巨大的潜力。与RGB流相反，Spike流具有克服运动模糊的固有优势，从而导致对高速对象的更准确的深度估计。但是，几乎不可能以监督的方式培训尖峰深度估计网络，因为获得时间密集的尖峰流的配对深度标签非常费力和挑战。在本文中，我们没有构建带有完整深度标签的Spike流数据集，而是以不受监督的方式从开源RGB数据集（例如Kitti）和估算峰值深度转移知识。此类问题的关键挑战在于RGB和SPIKE模式之间的模态差距，以及标记的源RGB和未标记的目标尖峰域之间的域间隙。为了克服这些挑战，我们引入了无监督的尖峰深度估计的跨模式跨域（BICROSS）框架。我们的方法通过引入中介模拟的源尖峰域来缩小源RGB和目标尖峰之间的巨大差距。要具体而言，对于跨模式阶段，我们提出了一种新颖的粗到精细知识蒸馏（CFKD），将图像和像素级知识从源RGB转移到源尖峰。这种设计分别利用了RGB和SPIKE模式的大量语义和密集的时间信息。对于跨域阶段，我们引入了不确定性引导的均值老师（UGMT），以生成具有不确定性估计的可靠伪标签，从而减轻了源尖峰和目标尖峰域之间的变化。此外，我们提出了一种全局级特征对齐方法（GLFA），以对齐两个域之间的特征并生成更可靠的伪标签。

组合多个传感器使机器人能够最大程度地提高其对环境的感知意识，并增强其对外部干扰的鲁棒性，对机器人导航至关重要。本文提出了可融合的基准测试，这是一个完整的多传感器数据集，具有多种移动机器人序列。本文提出了三项贡献。我们首先推进便携式和通用的多传感器套件，可提供丰富的感官测量值：10Hz激光镜点云，20Hz立体声框架图像，来自立体声事件相机的高速率和异步事件，来自IMU的200Hz惯性读数以及10Hz GPS信号。传感器已经在硬件中暂时同步。该设备轻巧，独立，并为移动机器人提供插件支持。其次，我们通过收集17个序列来构建数据集，该序列通过利用多个机器人平台进行数据收集来涵盖校园上各种环境。一些序列对现有的SLAM算法具有挑战性。第三，我们为将本地化和映射绩效评估提供了基础真理。我们还评估最新的大满贯方法并确定其局限性。该数据集将发布由原始传感器的设置，地面真相，校准数据和评估算法组成：https：//ram-lab.com/file/site/site/multi-sensor-dataset。