A growing body of research in natural language processing (NLP) and natural language understanding (NLU) is investigating human-like knowledge learned or encoded in the word embeddings from large language models. This is a step towards understanding what knowledge language models capture that resembles human understanding of language and communication. Here, we investigated whether and how the affect meaning of a word (i.e., valence, arousal, dominance) is encoded in word embeddings pre-trained in large neural networks. We used the human-labeled dataset (Mohammad 2018) as the ground truth and performed various correlational and classification tests on four types of word embeddings. The embeddings varied in being static or contextualized, and how much affect specific information was prioritized during the pre-training and fine-tuning phase. Our analyses show that word embedding from the vanilla BERT model (Devlin et al. 2019) did not saliently encode the affect information of English words. Only when the BERT model was fine-tuned on emotion related tasks or contained extra contextualized information from emotion-rich contexts could the corresponding embedding encode more relevant affect information.

Achieving realistic, vivid, and human-like synthesized conversational gestures conditioned on multi-modal data is still an unsolved problem due to the lack of available datasets, models and standard evaluation metrics. To address this, we build Body-Expression-Audio-Text dataset, BEAT, which has i) 76 hours, high-quality, multi-modal data captured from 30 speakers talking with eight different emotions and in four different languages, ii) 32 millions frame-level emotion and semantic relevance annotations. Our statistical analysis on BEAT demonstrates the correlation of conversational gestures with facial expressions, emotions, and semantics, in addition to the known correlation with audio, text, and speaker identity. Based on this observation, we propose a baseline model, Cascaded Motion Network (CaMN), which consists of above six modalities modeled in a cascaded architecture for gesture synthesis. To evaluate the semantic relevancy, we introduce a metric, Semantic Relevance Gesture Recall (SRGR). Qualitative and quantitative experiments demonstrate metrics' validness, ground truth data quality, and baseline's state-of-the-art performance. To the best of our knowledge, BEAT is the largest motion capture dataset for investigating human gestures, which may contribute to a number of different research fields, including controllable gesture synthesis, cross-modality analysis, and emotional gesture recognition.

The global financial crisis and Covid recession have renewed discussion concerning trend-cycle discovery in macroeconomic data, and boosting has recently upgraded the popular HP filter to a modern machine learning device suited to data-rich and rapid computational environments. This paper sheds light on its versatility in trend-cycle determination, explaining in a simple manner both HP filter smoothing and the consistency delivered by boosting for general trend detection. Applied to a universe of time series in FRED databases, boosting outperforms other methods in timely capturing downturns at crises and recoveries that follow. With its wide applicability the boosted HP filter is a useful automated machine learning addition to the macroeconometric toolkit.

Robots operating at night using conventional vision cameras face significant challenges in reconstruction due to noise-limited images. Previous work has demonstrated that burst-imaging techniques can be used to partially overcome this issue. In this paper, we develop a novel feature detector that operates directly on image bursts that enhances vision-based reconstruction under extremely low-light conditions. Our approach finds keypoints with well-defined scale and apparent motion within each burst by jointly searching in a multi-scale and multi-motion space. Because we describe these features at a stage where the images have higher signal-to-noise ratio, the detected features are more accurate than the state-of-the-art on conventional noisy images and burst-merged images and exhibit high precision, recall, and matching performance. We show improved feature performance and camera pose estimates and demonstrate improved structure-from-motion performance using our feature detector in challenging light-constrained scenes. Our feature finder provides a significant step towards robots operating in low-light scenarios and applications including night-time operations.

Recently, the problem of traffic accident risk forecasting has been getting the attention of the intelligent transportation systems community due to its significant impact on traffic clearance. This problem is commonly tackled in the literature by using data-driven approaches that model the spatial and temporal incident impact, since they were shown to be crucial for the traffic accident risk forecasting problem. To achieve this, most approaches build different architectures to capture the spatio-temporal correlations features, making them inefficient for large traffic accident datasets. Thus, in this work, we are proposing a novel unified framework, namely a contextual vision transformer, that can be trained in an end-to-end approach which can effectively reason about the spatial and temporal aspects of the problem while providing accurate traffic accident risk predictions. We evaluate and compare the performance of our proposed methodology against baseline approaches from the literature across two large-scale traffic accident datasets from two different geographical locations. The results have shown a significant improvement with roughly 2\% in RMSE score in comparison to previous state-of-art works (SoTA) in the literature. Moreover, our proposed approach has outperformed the SoTA technique over the two datasets while only requiring 23x fewer computational requirements.

Recent works on multi-modal emotion recognition move towards end-to-end models, which can extract the task-specific features supervised by the target task compared with the two-phase pipeline. However, previous methods only model the feature interactions between the textual and either acoustic and visual modalities, ignoring capturing the feature interactions between the acoustic and visual modalities. In this paper, we propose the multi-modal end-to-end transformer (ME2ET), which can effectively model the tri-modal features interaction among the textual, acoustic, and visual modalities at the low-level and high-level. At the low-level, we propose the progressive tri-modal attention, which can model the tri-modal feature interactions by adopting a two-pass strategy and can further leverage such interactions to significantly reduce the computation and memory complexity through reducing the input token length. At the high-level, we introduce the tri-modal feature fusion layer to explicitly aggregate the semantic representations of three modalities. The experimental results on the CMU-MOSEI and IEMOCAP datasets show that ME2ET achieves the state-of-the-art performance. The further in-depth analysis demonstrates the effectiveness, efficiency, and interpretability of the proposed progressive tri-modal attention, which can help our model to achieve better performance while significantly reducing the computation and memory cost. Our code will be publicly available.

Entity alignment (EA) aims to find entities in different knowledge graphs (KGs) that refer to the same object in the real world. Recent studies incorporate temporal information to augment the representations of KGs. The existing methods for EA between temporal KGs (TKGs) utilize a time-aware attention mechanism to incorporate relational and temporal information into entity embeddings. The approaches outperform the previous methods by using temporal information. However, we believe that it is not necessary to learn the embeddings of temporal information in KGs since most TKGs have uniform temporal representations. Therefore, we propose a simple graph neural network (GNN) model combined with a temporal information matching mechanism, which achieves better performance with less time and fewer parameters. Furthermore, since alignment seeds are difficult to label in real-world applications, we also propose a method to generate unsupervised alignment seeds via the temporal information of TKG. Extensive experiments on public datasets indicate that our supervised method significantly outperforms the previous methods and the unsupervised one has competitive performance.

Significant efforts are being invested to bring state-of-the-art classification and recognition to edge devices with extreme resource constraints (memory, speed, and lack of GPU support). Here, we demonstrate the first deep network for acoustic recognition that is small, flexible and compression-friendly yet achieves state-of-the-art performance for raw audio classification. Rather than handcrafting a once-off solution, we present a generic pipeline that automatically converts a large deep convolutional network via compression and quantization into a network for resource-impoverished edge devices. After introducing ACDNet, which produces above state-of-the-art accuracy on ESC-10 (96.65%), ESC-50 (87.10%), UrbanSound8K (84.45%) and AudioEvent (92.57%), we describe the compression pipeline and show that it allows us to achieve 97.22% size reduction and 97.28% FLOP reduction while maintaining close to state-of-the-art accuracy 96.25%, 83.65%, 78.27% and 89.69% on these datasets. We describe a successful implementation on a standard off-the-shelf microcontroller and, beyond laboratory benchmarks, report successful tests on real-world datasets.

Recently, Multi-modal Named Entity Recognition (MNER) has attracted a lot of attention. Most of the work utilizes image information through region-level visual representations obtained from a pretrained object detector and relies on an attention mechanism to model the interactions between image and text representations. However, it is difficult to model such interactions as image and text representations are trained separately on the data of their respective modality and are not aligned in the same space. As text representations take the most important role in MNER, in this paper, we propose {\bf I}mage-{\bf t}ext {\bf A}lignments (ITA) to align image features into the textual space, so that the attention mechanism in transformer-based pretrained textual embeddings can be better utilized. ITA first aligns the image into regional object tags, image-level captions and optical characters as visual contexts, concatenates them with the input texts as a new cross-modal input, and then feeds it into a pretrained textual embedding model. This makes it easier for the attention module of a pretrained textual embedding model to model the interaction between the two modalities since they are both represented in the textual space. ITA further aligns the output distributions predicted from the cross-modal input and textual input views so that the MNER model can be more practical in dealing with text-only inputs and robust to noises from images. In our experiments, we show that ITA models can achieve state-of-the-art accuracy on multi-modal Named Entity Recognition datasets, even without image information.

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive transformer decoder complicating the integration of external language models. In this paper, we explore relaxed attention, a simple and easy-to-implement smoothing of the attention weights, yielding a two-fold improvement to the general transformer architecture: First, relaxed attention provides regularization when applied to the self-attention layers in the encoder. Second, we show that it naturally supports the integration of an external language model as it suppresses the implicitly learned internal language model by relaxing the cross attention in the decoder. We demonstrate the benefit of relaxed attention across several tasks with clear improvement in combination with recent benchmark approaches. Specifically, we exceed the former state-of-the-art performance of 26.90% word error rate on the largest public lip-reading LRS3 benchmark with a word error rate of 26.31%, as well as we achieve a top-performing BLEU score of 37.67 on the IWSLT14 (DE$\rightarrow$EN) machine translation task without external language models and virtually no additional model parameters. Code and models will be made publicly available.