Accurate forecasting of Tropical cyclone (TC) intensity is crucial for formulating disaster risk reduction strategies. Current methods predominantly rely on limited spatiotemporal information from ERA5 data and neglect the causal relationships between these physical variables, failing to fully capture the spatial and temporal patterns required for intensity forecasting. To address this issue, we propose a Multi-modal multi-Scale Causal AutoRegressive model (MSCAR), which is the first model that combines causal relationships with large-scale multi-modal data for global TC intensity autoregressive forecasting. Furthermore, given the current absence of a TC dataset that offers a wide range of spatial variables, we present the Satellite and ERA5-based Tropical Cyclone Dataset (SETCD), which stands as the longest and most comprehensive global dataset related to TCs. Experiments on the dataset show that MSCAR outperforms the state-of-the-art methods, achieving maximum reductions in global and regional forecast errors of 9.52% and 6.74%, respectively. The code and dataset are publicly available at https://anonymous.4open.science/r/MSCAR.
Cued Speech (CS) is a pure visual coding method used by hearing-impaired people that combines lip reading with several specific hand shapes to make the spoken language visible. Automatic CS recognition (ACSR) seeks to transcribe visual cues of speech into text, which can help hearing-impaired people to communicate effectively. The visual information of CS contains lip reading and hand cueing, thus the fusion of them plays an important role in ACSR. However, most previous fusion methods struggle to capture the global dependency present in long sequence inputs of multi-modal CS data. As a result, these methods generally fail to learn the effective cross-modal relationships that contribute to the fusion. Recently, attention-based transformers have been a prevalent idea for capturing the global dependency over the long sequence in multi-modal fusion, but existing multi-modal fusion transformers suffer from both poor recognition accuracy and inefficient computation for the ACSR task. To address these problems, we develop a novel computation and parameter efficient multi-modal fusion transformer by proposing a novel Token-Importance-Aware Attention mechanism (TIAA), where a token utilization rate (TUR) is formulated to select the important tokens from the multi-modal streams. More precisely, TIAA firstly models the modality-specific fine-grained temporal dependencies over all tokens of each modality, and then learns the efficient cross-modal interaction for the modality-shared coarse-grained temporal dependencies over the important tokens of different modalities. Besides, a light-weight gated hidden projection is designed to control the feature flows of TIAA. The resulting model, named Economical Cued Speech Fusion Transformer (EcoCued), achieves state-of-the-art performance on all existing CS datasets, compared with existing transformer-based fusion methods and ACSR fusion methods.
While Large Language Models (LLMs) dominate tasks like natural language processing and computer vision, harnessing their power for spatial-temporal forecasting remains challenging. The disparity between sequential text and complex spatial-temporal data hinders this application. To address this issue, this paper introduces STG-LLM, an innovative approach empowering LLMs for spatial-temporal forecasting. We tackle the data mismatch by proposing: 1) STG-Tokenizer: This spatial-temporal graph tokenizer transforms intricate graph data into concise tokens capturing both spatial and temporal relationships; 2) STG-Adapter: This minimalistic adapter, consisting of linear encoding and decoding layers, bridges the gap between tokenized data and LLM comprehension. By fine-tuning only a small set of parameters, it can effectively grasp the semantics of tokens generated by STG-Tokenizer, while preserving the original natural language understanding capabilities of LLMs. Extensive experiments on diverse spatial-temporal benchmark datasets show that STG-LLM successfully unlocks LLM potential for spatial-temporal forecasting. Remarkably, our approach achieves competitive performance on par with dedicated SOTA methods.
In multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems, representing the whole channel only based on partial subchannels will significantly reduce the channel acquisition overhead. For such a channel mapping task, inspired by the intrinsic coupling across the space and frequency domains, this letter proposes to use interleaved learning with partial antenna and subcarrier characteristics to represent the whole MIMO-OFDM channel. Specifically, we design a complex-domain multilayer perceptron (MLP)-Mixer (CMixer), which utilizes two kinds of complex-domain MLP modules to learn the space and frequency characteristics respectively and then interleaves them to couple the learned properties. The complex-domain computation facilitates the learning on the complex-valued channel data, while the interleaving tightens the coupling of space and frequency domains. These two designs jointly reduce the learning burden, making the physics-inspired CMixer more effective on channel representation learning than existing data-driven approaches. Simulation shows that the proposed scheme brings 4.6~10dB gains in mapping accuracy compared to existing schemes under different settings. Besides, ablation studies show the necessity of complex-domain computation as well as the extent to which the interleaved learning matches the channel properties.
We introduce RJUA-QA, a novel medical dataset for question answering (QA) and reasoning with clinical evidence, contributing to bridge the gap between general large language models (LLMs) and medical-specific LLM applications. RJUA-QA is derived from realistic clinical scenarios and aims to facilitate LLMs in generating reliable diagnostic and advice. The dataset contains 2,132 curated Question-Context-Answer pairs, corresponding about 25,000 diagnostic records and clinical cases. The dataset covers 67 common urological disease categories, where the disease coverage exceeds 97.6\% of the population seeking medical services in urology. Each data instance in RJUA-QA comprises: (1) a question mirroring real patient to inquiry about clinical symptoms and medical conditions, (2) a context including comprehensive expert knowledge, serving as a reference for medical examination and diagnosis, (3) a doctor response offering the diagnostic conclusion and suggested examination guidance, (4) a diagnosed clinical disease as the recommended diagnostic outcome, and (5) clinical advice providing recommendations for medical examination. RJUA-QA is the first medical QA dataset for clinical reasoning over the patient inquiries, where expert-level knowledge and experience are required for yielding diagnostic conclusions and medical examination advice. A comprehensive evaluation is conducted to evaluate the performance of both medical-specific and general LLMs on the RJUA-QA dataset. Our data is are publicly available at \url{https://github.com/alipay/RJU_Ant_QA}.
Cross-modal object tracking is an important research topic in the field of information fusion, and it aims to address imaging limitations in challenging scenarios by integrating switchable visible and near-infrared modalities. However, existing tracking methods face some difficulties in adapting to significant target appearance variations in the presence of modality switch. For instance, model update based tracking methods struggle to maintain stable tracking results during modality switching, leading to error accumulation and model drift. Template based tracking methods solely rely on the template information from first frame and/or last frame, which lacks sufficient representation ability and poses challenges in handling significant target appearance changes. To address this problem, we propose a prototype-based cross-modal object tracker called ProtoTrack, which introduces a novel prototype learning scheme to adapt to significant target appearance variations, for cross-modal object tracking. In particular, we design a multi-modal prototype to represent target information by multi-kind samples, including a fixed sample from the first frame and two representative samples from different modalities. Moreover, we develop a prototype generation algorithm based on two new modules to ensure the prototype representative in different challenges......
Visual tracking often faces challenges such as invalid targets and decreased performance in low-light conditions when relying solely on RGB image sequences. While incorporating additional modalities like depth and infrared data has proven effective, existing multi-modal imaging platforms are complex and lack real-world applicability. In contrast, near-infrared (NIR) imaging, commonly used in surveillance cameras, can switch between RGB and NIR based on light intensity. However, tracking objects across these heterogeneous modalities poses significant challenges, particularly due to the absence of modality switch signals during tracking. To address these challenges, we propose an adaptive cross-modal object tracking algorithm called Modality-Aware Fusion Network (MAFNet). MAFNet efficiently integrates information from both RGB and NIR modalities using an adaptive weighting mechanism, effectively bridging the appearance gap and enabling a modality-aware target representation. It consists of two key components: an adaptive weighting module and a modality-specific representation module......
As an exemplary self-supervised approach for representation learning, time-series contrastive learning has exhibited remarkable advancements in contemporary research. While recent contrastive learning strategies have focused on how to construct appropriate positives and negatives, in this study, we conduct theoretical analysis and find they have overlooked the fundamental issues: false negatives and class imbalance inherent in the InfoNCE loss-based framework. Therefore, we introduce a straightforward modification grounded in the SimCLR framework, universally adaptable to models engaged in the instance discrimination task. By constructing instance graphs to facilitate interactive learning among instances, we emulate supervised contrastive learning via the multiple-instances discrimination task, mitigating the harmful impact of false negatives. Moreover, leveraging the graph structure and few-labeled data, we perform semi-supervised consistency classification and enhance the representative ability of minority classes. We compared our method with the most popular time-series contrastive learning methods on four real-world time-series datasets and demonstrated our significant advantages in overall performance.