Related papers: Not Like Transformers: Drop the Beat Representatio…
Recent advancements in sequence modeling have led to the development of the Mamba architecture, noted for its selective state space approach, offering a promising avenue for efficient long sequence handling. However, its application in 3D…
Music-to-dance generation aims to translate auditory signals into expressive human motion, with broad applications in virtual reality, choreography, and digital entertainment. Despite promising progress, the limited generation efficiency of…
Multi-modality image fusion aims to integrate the merits of images from different sources and render high-quality fusion images. However, existing feature extraction and fusion methods are either constrained by inherent local reduction bias…
Synthesising appropriate choreographies from music remains an open problem. We introduce MDLT, a novel approach that frames the choreography generation problem as a translation task. Our method leverages an existing data set to learn to…
In recent developments, the Mamba architecture, known for its selective state space approach, has shown potential in the efficient modeling of long sequences. However, its application in image generation remains underexplored. Traditional…
Diffusion models have emerged as a widely utilized and successful methodology in human motion synthesis. Task-oriented diffusion models have significantly advanced action-to-motion, text-to-motion, and audio-to-motion applications. In this…
Image generation models have encountered challenges related to scalability and quadratic complexity, primarily due to the reliance on Transformer-based backbones. In this study, we introduce MaskMamba, a novel hybrid model that combines…
Diffusion models currently demonstrate impressive performance over various generative tasks. Recent work on image diffusion highlights the strong capabilities of Mamba (state space models) due to its efficient handling of long-range…
Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is quadratic to the number of tokens, leading to significant…
Parametric Computer-Aided Design (CAD) is crucial in industrial applications, yet existing approaches often struggle to generate long sequence parametric commands due to complex CAD models' geometric and topological constraints. To address…
Text-to-motion generation holds potential for film, gaming, and robotics, yet current methods often prioritize short motion generation, making it challenging to produce long motion sequences effectively: (1) Current methods struggle to…
Computational dance generation is crucial in many areas, such as art, human-computer interaction, virtual reality, and digital entertainment, particularly for generating coherent and expressive long dance sequences. Diffusion-based…
Transformers have been the most successful architecture for various speech modeling tasks, including speech separation. However, the self-attention mechanism in transformers with quadratic complexity is inefficient in computation and…
In scene text detection, Transformer-based methods have addressed the global feature extraction limitations inherent in traditional convolution neural network-based methods. However, most directly rely on native Transformer attention layers…
In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…
Sequential recommendation systems aim to predict users' next preferences based on their interaction histories, but existing approaches face critical limitations in efficiency and multi-scale pattern recognition. While Transformer-based…
Scene flow estimation aims to predict 3D motion from consecutive point cloud frames, which is of great interest in autonomous driving field. Existing methods face challenges such as insufficient spatio-temporal modeling and inherent loss of…
Image style transfer aims to integrate the visual patterns of a specific artistic style into a content image while preserving its content structure. Existing methods mainly rely on the generative adversarial network (GAN) or stable…
A great number of deep learning based models have been recently proposed for automatic music composition. Among these models, the Transformer stands out as a prominent approach for generating expressive classical piano performance with a…
Recent advancements in imitation learning, particularly with the integration of LLM techniques, are set to significantly improve robots' dexterity and adaptability. This paper proposes using Mamba, a state-of-the-art architecture with…