Related papers: Self-supervised ControlNet with Spatio-Temporal Ma…
Video super-resolution (VSR) aims to restore a sequence of high-resolution (HR) frames from their low-resolution (LR) counterparts. Although some progress has been made, there are grand challenges to effectively utilize temporal dependency…
Mamba-based models have drawn much attention in offline RL. However, their selective mechanism often detrimental when key steps in RL sequences are omitted. To address these issues, we propose a simple yet effective structure, called…
The outdoor vision systems are frequently contaminated by rain streaks and raindrops, which significantly degenerate the performance of visual tasks and multimedia applications. The nature of videos exhibits redundant temporal cues for rain…
Deep learning models like Convolutional Neural Networks and transformers have shown impressive capabilities in speech verification, gaining considerable attention in the research community. However, CNN-based approaches struggle with…
Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we…
Audio super-resolution aims to enhance low-resolution signals by creating high-frequency content. In this work, we modify the architecture of AERO (a state-of-the-art system for this task) for music super-resolution. SPecifically, we…
Image segmentation holds a vital position in the realms of diagnosis and treatment within the medical domain. Traditional convolutional neural networks (CNNs) and Transformer models have made significant advancements in this realm, but they…
Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very important that motion information among frames should be well…
Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture…
Designing computationally efficient network architectures remains an ongoing necessity in computer vision. In this paper, we adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity. At the core…
Text-driven video moment retrieval (VMR) remains challenging due to limited capture of hidden temporal dynamics in untrimmed videos, leading to imprecise grounding in long sequences. Traditional methods rely on natural language queries…
Visual Mamba is an approach that extends the selective space state model, Mamba, to vision tasks. It processes image tokens sequentially in a fixed order, accumulating information to generate outputs. Despite its growing popularity for…
Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…
Point cloud videos can faithfully capture real-world spatial geometries and temporal dynamics, which are essential for enabling intelligent agents to understand the dynamically changing world. However, designing an effective 4D backbone…
We present a joint learning scheme of video super-resolution and deblurring, called VSRDB, to restore clean high-resolution (HR) videos from blurry low-resolution (LR) ones. This joint restoration problem has drawn much less attention…
Restoration and enhancement are essential for improving the quality of videos captured under atmospheric turbulence conditions, aiding visualization, object detection, classification, and tracking in surveillance systems. In this paper, we…
The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting significant attention due to its efficient processing of long sequence tasks. Mamba's inherent causal mechanism renders it particularly…
Diffusion models have recently achieved outstanding results in the field of image super-resolution. These methods typically inject low-resolution (LR) images via ControlNet.In this paper, we first explore the temporal dynamics of…
The LiDAR 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many existing LiDAR detection models depend on complex feature transformations,…
Sequential recommendation systems have become a cornerstone of personalized services, adept at modeling the temporal evolution of user preferences by capturing dynamic interaction sequences. Existing approaches predominantly rely on…