Pre-trained models (PTMs) have gained prominence in Natural Language Processing and Computer Vision domains. When it comes to time-series PTMs, their development has been limited. Previous research on time-series transformers has mainly been devoted to small-scale tasks, yet these models have not consistently outperformed traditional models. Additionally, the performance of these transformers on large-scale data remains unexplored. These findings raise doubts about Transformer's capabilities to scale up and capture temporal dependencies. In this study, we re-examine time-series transformers and identify the shortcomings of prior studies. Drawing from these insights, we then introduce a pioneering architecture called Timely Generative Pre-trained Transformer (\model). This architecture integrates recurrent attention and temporal convolution modules to effectively capture global-local temporal dependencies in long sequences. The relative position embedding with time decay can effectively deal with trend and periodic patterns from time-series. Our experiments show that \model~excels in modeling continuously monitored biosignal as well as irregularly-sampled time-series data commonly observed in longitudinal electronic health records. This breakthrough suggests a priority shift in time-series deep learning research, moving from small-scale modeling from scratch to large-scale pre-training.
In this paper, we address the limitations of the common data annotation and training methods for objective single-label classification tasks. Typically, when annotating such tasks annotators are only asked to provide a single label for each sample and annotator disagreement is discarded when a final hard label is decided through majority voting. We challenge this traditional approach, acknowledging that determining the appropriate label can be difficult due to the ambiguity and lack of context in the data samples. Rather than discarding the information from such ambiguous annotations, our soft label method makes use of them for training. Our findings indicate that additional annotator information, such as confidence, secondary label and disagreement, can be used to effectively generate soft labels. Training classifiers with these soft labels then leads to improved performance and calibration on the hard label test set.
The use of visually-rich documents (VRDs) in various fields has created a demand for Document AI models that can read and comprehend documents like humans, which requires the overcoming of technical, linguistic, and cognitive barriers. Unfortunately, the lack of appropriate datasets has significantly hindered advancements in the field. To address this issue, we introduce \textsc{DocTrack}, a VRD dataset really aligned with human eye-movement information using eye-tracking technology. This dataset can be used to investigate the challenges mentioned above. Additionally, we explore the impact of human reading order on document understanding tasks and examine what would happen if a machine reads in the same order as a human. Our results suggest that although Document AI models have made significant progress, they still have a long way to go before they can read VRDs as accurately, continuously, and flexibly as humans do. These findings have potential implications for future research and development of Document AI models. The data is available at \url{https://github.com/hint-lab/doctrack}.
Low Earth Orbit (LEO) satellites are being extensively researched in the development of secure Internet of Remote Things (IoRT). In scenarios with miniaturized terminals, the limited transmission power and long transmission distance often lead to low Signal-to-Noise Ratio (SNR) at the satellite receiver, which degrades communication performance. A solution to address this issue is the utilization of cooperative satellites, which can combine signals received from multiple satellites, thereby significantly improve SNR. However, in order to maximize the combination gain, the signal coherent combining is necessary, which requires the carrier frequency and phase of each receiving signal to be aligned. Under low SNR circumstances, carrier parameter estimation can be a significant challenge, especially for short burst transmission with no training sequence. In order to tackle it, we propose an iterative code-aided estimation algorithm for joint Carrier Frequency Offset (CFO) and Carrier Phase Offset (CPO). The Cram\'er-Rao Lower Bound (CRLB) is suggested as the limit on the parameter estimation performance. Simulation results demonstrate that the proposed algorithm can approach Bit Error Rate (BER) performance bound within 0.4 dB with regards to four-satellite collaboration.
Nonlinear metamaterials with tailored mechanical properties have applications in engineering, medicine, robotics, and beyond. While modeling their macromechanical behavior is challenging in itself, finding structure parameters that lead to ideal approximation of high-level performance goals is a challenging task. In this work, we propose Neural Metamaterial Networks (NMN) -- smooth neural representations that encode the nonlinear mechanics of entire metamaterial families. Given structure parameters as input, NMN return continuously differentiable strain energy density functions, thus guaranteeing conservative forces by construction. Though trained on simulation data, NMN do not inherit the discontinuities resulting from topological changes in finite element meshes. They instead provide a smooth map from parameter to performance space that is fully differentiable and thus well-suited for gradient-based optimization. On this basis, we formulate inverse material design as a nonlinear programming problem that leverages neural networks for both objective functions and constraints. We use this approach to automatically design materials with desired strain-stress curves, prescribed directional stiffness and Poisson ratio profiles. We furthermore conduct ablation studies on network nonlinearities and show the advantages of our approach compared to native-scale optimization.
The past decade has witnessed the huge success of deep learning in well-known artificial intelligence applications such as face recognition, autonomous driving, and large language model like ChatGPT. Recently, the application of deep learning has been extended to a much wider range, with neural network-based video coding being one of them. Neural network-based video coding can be performed at two different levels: embedding neural network-based (NN-based) coding tools into a classical video compression framework or building the entire compression framework upon neural networks. This paper elaborates some of the recent exploration efforts of JVET (Joint Video Experts Team of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC29) in the name of neural network-based video coding (NNVC), falling in the former category. Specifically, this paper discusses two major NN-based video coding technologies, i.e. neural network-based intra prediction and neural network-based in-loop filtering, which have been investigated for several meeting cycles in JVET and finally adopted into the reference software of NNVC. Extensive experiments on top of the NNVC have been conducted to evaluate the effectiveness of the proposed techniques. Compared with VTM-11.0_nnvc, the proposed NN-based coding tools in NNVC-4.0 could achieve {11.94%, 21.86%, 22.59%}, {9.18%, 19.76%, 20.92%}, and {10.63%, 21.56%, 23.02%} BD-rate reductions on average for {Y, Cb, Cr} under random-access, low-delay, and all-intra configurations respectively.
This paper describes the FlySpeech speaker diarization system submitted to the second \textbf{M}ultimodal \textbf{I}nformation Based \textbf{S}peech \textbf{P}rocessing~(\textbf{MISP}) Challenge held in ICASSP 2022. We develop an end-to-end audio-visual speaker diarization~(AVSD) system, which consists of a lip encoder, a speaker encoder, and an audio-visual decoder. Specifically, to mitigate the degradation of diarization performance caused by separate training, we jointly train the speaker encoder and the audio-visual decoder. In addition, we leverage the large-data pretrained speaker extractor to initialize the speaker encoder.
We propose a dense neural simultaneous localization and mapping (SLAM) approach for monocular RGBD input which anchors the features of a neural scene representation in a point cloud that is iteratively generated in an input-dependent data-driven manner. We demonstrate that both tracking and mapping can be performed with the same point-based neural scene representation by minimizing an RGBD-based re-rendering loss. In contrast to recent dense neural SLAM methods which anchor the scene features in a sparse grid, our point-based approach allows dynamically adapting the anchor point density to the information density of the input. This strategy reduces runtime and memory usage in regions with fewer details and dedicates higher point density to resolve fine details. Our approach performs either better or competitive to existing dense neural RGBD SLAM methods in tracking, mapping and rendering accuracy on the Replica, TUM-RGBD and ScanNet datasets. The source code is available at https://github.com/tfy14esa/Point-SLAM.
Considering a conversation thread, stance classification aims to identify the opinion (e.g. agree or disagree) of replies towards a given target. The target of the stance is expected to be an essential component in this task, being one of the main factors that make it different from sentiment analysis. However, a recent study shows that a target-oblivious model outperforms target-aware models, suggesting that targets are not useful when predicting stance. This paper re-examines this phenomenon for rumour stance classification (RSC) on social media, where a target is a rumour story implied by the source tweet in the conversation. We propose adversarial attacks in the test data, aiming to assess the models robustness and evaluate the role of the data in the models performance. Results show that state-of-the-art models, including approaches that use the entire conversation thread, overly relying on superficial signals. Our hypothesis is that the naturally high occurrence of target-independent direct replies in RSC (e.g. "this is fake" or just "fake") results in the impressive performance of target-oblivious models, highlighting the risk of target instances being treated as noise during training.