Related papers: AlignMamba-2: Enhancing Multimodal Fusion and Sent…

Multimodal learning has gained much success in recent years. However, current multimodal fusion methods adopt the attention mechanism of Transformers to implicitly learn the underlying correlation of multimodal features. As a result, the…

Sufficient cross-task interaction is crucial for success in multi-task dense prediction. However, sufficient interaction often results in high computational complexity, forcing existing methods to face the trade-off between interaction…

Micro-gesture recognition (MGR) targets the identification of subtle and fine-grained human motions and requires accurate modeling of both long-range and local spatiotemporal dependencies. While CNNs are effective at capturing local…

Human activity recognition (HAR) from inertial sensors is essential for ubiquitous computing, mobile health, and ambient intelligence. Conventional deep models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs),…

Facial Expression Recognition (FER) plays a pivotal role in understanding human emotional cues. However, traditional FER methods based on visual information have some limitations, such as preprocessing, feature extraction, and multi-stage…

The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and…

Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity. However, its lack of local inductive…

Multimodal foundation models have achieved impressive progress across a wide range of vision-language tasks. However, existing approaches often adopt fixed or task-specific fusion strategies, neglecting the intrinsic variability of modality…

Precise alignment of multi-modal images with inherent feature discrepancies poses a pivotal challenge in deformable image registration. Traditional learning-based approaches often consider registration networks as black boxes without…

By sharing complementary perceptual information, multi-agent collaborative perception fosters a deeper understanding of the environment. Recent studies on collaborative perception mostly utilize CNNs or Transformers to learn feature…

Multimodal semantic segmentation has emerged as a powerful paradigm for enhancing scene understanding by leveraging complementary information from multiple sensing modalities (e.g., RGB, depth, and thermal). However, existing cross-modal…

Multimodal Sentiment Analysis (MSA) is critical for human-computer interaction but faces challenges when the modalities are incomplete or missing. Existing methods often assume pre-defined missing modalities or fixed missing rates, limiting…

While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited…

Multimodal sentiment analysis is a key technology in the fields of human-computer interaction and affective computing. Accurately recognizing human emotional states is crucial for facilitating smooth communication between humans and…

Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the…

Multimodal aspect-based sentiment analysis(MABSA) seeks to identify aspect terms within paired image-text data and determine their fine grained sentiment polarities, representing a fundamental task for improving the effectiveness of…

Recent Transformer-based diffusion models have shown remarkable performance, largely attributed to the ability of the self-attention mechanism to accurately capture both global and local contexts by computing all-pair interactions among…

Human trajectory forecasting is crucial for safe navigation in crowded environments, requiring models that balance accuracy with computational efficiency. Efficiently modeling social interactions is key to performance in dense crowds. Yet,…

State space models (SSMs) like Mamba have recently attracted much attention. Compared to Transformer-based large language models (LLMs), Mamba achieves linear computation complexity with the sequence length and demonstrates superior…

As an important task in sentiment analysis, Multimodal Aspect-Based Sentiment Analysis (MABSA) has attracted increasing attention in recent years. However, previous approaches either (i) use separately pre-trained visual and textual models,…