English
Related papers

Related papers: MAMBA4D: Efficient Long-Sequence Point Cloud Video…

200 papers

Transformers have significantly advanced the field of 3D human pose estimation (HPE). However, existing transformer-based methods primarily use self-attention mechanisms for spatio-temporal modeling, leading to a quadratic complexity,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Yunlong Huang , Junshuo Liu , Ke Xian , Robert Caiming Qiu

High-definition (HD) maps are essential for autonomous driving, as they provide precise road information for downstream tasks. Recent advances highlight the potential of temporal modeling in addressing challenges like occlusions and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Ruizi Yang , Xiaolu Liu , Junbo Chen , Jianke Zhu

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…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Younghyun Cho , Changhun Lee , Seonggon Kim , Eunhyeok Park

Sequence modeling is a crucial area across various domains, including Natural Language Processing (NLP), speech recognition, time series forecasting, music generation, and bioinformatics. Recurrent Neural Networks (RNNs) and Long Short Term…

Machine Learning · Computer Science 2024-04-26 Badri Narayana Patro , Vijay Srinivas Agneeswaran

In recent years, range-view-based LiDAR point cloud super-resolution techniques attract significant attention as a low-cost method for generating higher-resolution point cloud data. However, due to the sparsity and irregular structure of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Chuang Chen , Wenyi Ge

Accurate 3D object detection in autonomous driving relies on Bird's Eye View (BEV) perception and effective temporal fusion. However, existing fusion strategies based on convolutional layers or deformable self-attention struggle to model…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Zihan You , Ni Wang , Hao Wang , Qichao Zhao , Jinxiang Wang

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Machine Learning · Computer Science 2024-06-03 Albert Gu , Tri Dao

Robust feature representations are essential for learning-based Multi-View Stereo (MVS), which relies on accurate feature matching. Recent MVS methods leverage Transformers to capture long-range dependencies based on local features…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Jianfei Jiang , Qiankun Liu , Hongyuan Liu , Haochen Yu , Liyong Wang , Jiansheng Chen , Huimin Ma

Understanding 4D point cloud sequences online is of significant practical value in various scenarios such as VR/AR, robotics, and autonomous driving. The key goal is to continuously analyze the geometry and dynamics of a 3D scene as…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 Yuhao Dong , Zhuoyang Zhang , Yunze Liu , Li Yi

Point cloud analysis has seen substantial advancements due to deep learning, although previous Transformer-based methods excel at modeling long-range dependencies on this task, their computational demands are substantial. Conversely, the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Zicheng Wang , Zhenghao Chen , Yiming Wu , Zhen Zhao , Luping Zhou , Dong Xu

The rapid growth of long-duration, high-definition videos has made efficient video quality assessment (VQA) a critical challenge. Existing research typically tackles this problem through two main strategies: reducing model parameters and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-23 Yachun Mi , Yu Li , Weicheng Meng , Chaofeng Chen , Chen Hui , Shaohui Liu

Dynamic outdoor environments with high temporal variation (HTV) pose significant challenges for 3D single object tracking in LiDAR point clouds. Existing memory-based trackers often suffer from quadratic computational complexity, temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Shengjing Tian , Yinan Han , Xiantong Zhao , Xuehu Liu , Qi Lang

Video fusion is a fundamental technique in various video processing tasks. However, existing video fusion methods heavily rely on optical flow estimation and feature warping, resulting in severe computational overhead and limited…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Zixiang Zhao , Yukun Cui , Lilun Deng , Haowen Bai , Haotong Qin , Tao Feng , Konrad Schindler

Achieving both high accuracy and topological continuity in road segmentation from satellite imagery is a critical goal for applications ranging from urban planning to disaster response. State-of-the-art methods often rely on Vision…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Jules Decaestecker , Nicolas Vigne

The essence of audio-visual segmentation (AVS) lies in locating and delineating sound-emitting objects within a video stream. While Transformer-based methods have shown promise, their handling of long-range dependencies struggles due to…

Computer Vision and Pattern Recognition · Computer Science 2025-01-15 Sitong Gong , Yunzhi Zhuge , Lu Zhang , Yifan Wang , Pingping Zhang , Lijun Wang , Huchuan Lu

Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Xinyu Wang , Jinghua Hou , Zhe Liu , Yingying Zhu

State-space models (SSMs), exemplified by S4, have introduced a novel context modeling method by integrating state-space techniques into deep learning. However, they struggle with global context modeling due to their data-independent…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Hamid Suleman , Syed Talal Wasim , Muzammal Naseer , Juergen Gall

Existing video camouflaged object detection (VCOD) methods primarily rely on spatial appearances for motion perception. However, the high foreground-background similarity in VCOD limits the discriminability of such features (e.g. color and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Xin Li , Keren Fu , Qijun Zhao

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…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Jiehao Luo , Jintao Cheng , Xiaoyu Tang , Qingwen Zhang , Bohuan Xue , Rui Fan

Sequential recommendation aims to estimate the dynamic user preferences and sequential dependencies among historical user behaviors. Although Transformer-based models have proven to be effective for sequential recommendation, they suffer…

Information Retrieval · Computer Science 2024-07-02 Chengkai Liu , Jianghao Lin , Jianling Wang , Hanzhou Liu , James Caverlee