Ming Yin

The prediction of future trajectories for vehicle in the field of autonomous driving is of utmost importance to ensure safe driving. However, it is challenging as the existing methods still suffer from noise sensitivity, limited representation ability and time-consuming inference. To this end, we propose a novel Driving Mode Centric Denoising Diffusion Model for trajectory prediction, namely DMC-Diffuser. Specifically, we first devise a driving mode token generator by utilizing different time-scale information from noisy trajectories. Subsequently, we employ an attention-based denoiser, which leverages the driving mode token along with the driving context to learn the potential trajectories. Furthermore, aided by a flexible denoiser structure with an accelerated sampling algorithm, the proposed method can achieve the comparable performance at the cost of low-complexity inference. Experimental results on two datasets show that DMC-Diffuser has achieved superior performance compared to the state-of-the-art methods, e.g., a comprehensive performance gain of nearly 9% over other diffusion based methods.

Audio-visual scene classification (AVSC) aims at classifying a video recording into one of the predefined scene categories, using both audio and visual modalities, which is a fundamental yet challenging problem in scene understanding. Although some impressive results for AVSC have been achieved recently, the modeling of object semantics and long-term dependencies from various modalities remains fully unexplored in the literature. To this end, in this paper, a novel Multimodal Multi-scale Temporal Enhancement Network, namely M2TE-Net, is proposed for audio-visual scene classification. In particular, to handle the temporal information of audio-visual modalities, the Multi-Scale Temporal Enhancement Modules(MSTEM) are devised from global and local perspectives. Then, a U-shape Multimodal Interactive Module (UMIM) is designed to mine the interaction between two modalities, where the shared semantic information from different modalities is fused by exploiting the consistency and complementary ones. Experimental results on two benchmark datasets demonstrate that the proposed M2TE-Net outperforms state-of-the-art models, with competitive performance. The code is available at: https://github.com/TinwaiLeung/M2TE-Net.

Multimodal sentiment analysis (MSA) aims to accurately predict the user's emotional tendency by integrating multimodal data such as text, audio and visual information posted by users. However, in most prior studies, the information differences between modalities are not fully considered as these modalities are treated equally. In fact, text modality usually contains more richer semantics to exhibit emotion, while audio and visual ones cover more redundant and even noisy information. Though some works have highlighted the key role of text modality, they still fail to fully utilize the non-text modalities, leading to sub-optimal performance for MSA. To this end, we propose a novel Text-centric Bidirectional Modality Enhancement Network (TB-MEN) in this paper, which recognizes the core role of text and fully exploits the audio and visual modalities at the same time. First, in light of the text features extracted by BERT and non-text features extracted by LSTM respectively, we develop a trimodal multi-scale bottleneck fusion (TMBF) module to capture semantically enhanced text features. Specifically, this is achieved by bottleneck fusion mechanism and transferring the audio and visual modalities to text one. Furthermore, for non-text modalities enhancement, a sparse subspace alignment strategy is employed in text-dominant subspace alignment (TDSA) module, which sparsely maps non-text features into the text subspace to aggregate semantic information. Experimental results show that on several public datasets, including CMU-MOSI, CMU-MOSEI and CH-SIMS, our model has achieved significant gains over the state-of-the-arts. For example, on the CMU-MOSI dataset, TB-MEN improves Acc-2, Acc-5, Acc-7, and F1 by 0.45$\%$, 2.04$\%$, 2.62$\%$, and 0.4$\%$, respectively, compared to the second-best one.

This paper systematically discusses how the inherent properties of chaotic attractors influence the results of discovering causal relationships from time series using convergent cross mapping, particularly how convergent cross mapping misleads the bidirectional causal relationship as unidirectional when the chaotic attractor exhibits symmetry. We propose a novel method based on the k-means clustering method to address the challenges when the measurement function defines even parity, which may cause this issue. This method is demonstrated to recover the symmetry of the latent chaotic attractor and discover the correct causal links between time series without introducing information from other variables. We validate the accuracy of this method using time series derived from numerical simulations and a real-world system for which convergent cross mapping may conclude erroneous results.