中文
相关论文

相关论文: MVGD-Net: A Novel Motion-aware Video Glass Surface…

200 篇论文

This paper introduces DGNet, a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD). It decouples the task into two connected branches, i.e., a context and a texture encoder. The essential…

计算机视觉与模式识别 · 计算机科学 2023-06-06 Ge-Peng Ji , Deng-Ping Fan , Yu-Cheng Chou , Dengxin Dai , Alexander Liniger , Luc Van Gool

With the growing digitalization all over the globe, the relevance of network security becomes increasingly important. Machine learning-based intrusion detection constitutes a promising approach for improving security, but it bears several…

机器学习 · 计算机科学 2025-08-19 Aleksei Liuliakov , Alexander Schulz , Luca Hermes , Barbara Hammer

Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to…

计算机视觉与模式识别 · 计算机科学 2017-08-21 Xizhou Zhu , Yujie Wang , Jifeng Dai , Lu Yuan , Yichen Wei

The reliability of grasp detection for target objects in complex scenes is a challenging task and a critical problem that needs to be solved urgently in practical application. At present, the grasp detection location comes from searching…

机器人学 · 计算机科学 2021-01-21 Mingshuai Dong , Shimin Wei , Xiuli Yu , Jianqin Yin

Fusing Radar and Lidar sensor data can fully utilize their complementary advantages and provide more accurate reconstruction of the surrounding for autonomous driving systems. Surround Radar/Lidar can provide 360-degree view sampling with…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Wenjing Xie , Tao Hu , Neiwen Ling , Guoliang Xing , Chun Jason Xue , Nan Guan

Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view (BEV) from multi-view images. In MVPD, end-to-end trainable deep learning methods have progressed greatly. However, they often struggle to…

计算机视觉与模式识别 · 计算机科学 2025-08-29 Taiga Yamane , Satoshi Suzuki , Ryo Masumura , Shota Orihashi , Tomohiro Tanaka , Mana Ihori , Naoki Makishima , Naotaka Kawata

Single-Domain Generalized Object Detection~(S-DGOD) aims to train an object detector on a single source domain while generalizing well to diverse unseen target domains, making it suitable for multimedia applications that involve various…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Xiaoran Xu , Jiangang Yang , Wenyue Chong , Wenhui Shi , Shichu Sun , Jing Xing , Jian Liu

Salient object detection on RGB-D images is an active topic in computer vision. Although the existing methods have achieved appreciable performance, there are still some challenges. The locality of convolutional neural network requires that…

计算机视觉与模式识别 · 计算机科学 2022-03-22 Xian Fang , Jinshao Zhu , Xiuli Shao , Hongpeng Wang

Being data-driven is one of the most iconic properties of deep learning algorithms. The birth of ImageNet drives a remarkable trend of "learning from large-scale data" in computer vision. Pretraining on ImageNet to obtain rich universal…

Anomaly detection in video surveillance has recently gained interest from the research community. Temporal duration of anomalies vary within video streams, leading to complications in learning the temporal dynamics of specific events. This…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Erkut Akdag , Egor Bondarev , Peter H. N. De With

A significant amount of redundancy exists between consecutive frames of a video. Object detectors typically produce detections for one image at a time, without any capabilities for taking advantage of this redundancy. Meanwhile, many…

计算机视觉与模式识别 · 计算机科学 2021-09-16 Hughes Perreault , Guillaume-Alexandre Bilodeau , Nicolas Saunier , Maguelonne Héritier

Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…

计算机视觉与模式识别 · 计算机科学 2024-02-19 Noreen Anwar , Guillaume-Alexandre Bilodeau , Wassim Bouachir

For real-world driver drowsiness detection from videos, the variation of head pose is so large that the existing methods on global face is not capable of extracting effective features, such as looking aside and lowering head. Temporal…

计算机视觉与模式识别 · 计算机科学 2018-01-09 Jie Lyu , Zejian Yuan , Dapeng Chen

Deep neural networks based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite significant performance improvement, due to the deep structures, they still require prohibitive…

计算机视觉与模式识别 · 计算机科学 2020-01-08 Mohammad Farhadi , Yezhou Yang

Top-leading solutions for Video Scene Graph Generation (VSGG) typically adopt an offline pipeline. Though demonstrating promising performance, they remain unable to handle real-time video streams and consume large GPU memory. Moreover,…

计算机视觉与模式识别 · 计算机科学 2025-03-19 Mu Chen , Liulei Li , Wenguan Wang , Yi Yang

Recent advancements in multi-view action recognition have largely relied on Transformer-based models. While effective and adaptable, these models often require substantial computational resources, especially in scenarios with multiple views…

计算机视觉与模式识别 · 计算机科学 2025-01-24 Yuhui Lin , Jiaxuan Lu , Yue Yong , Jiahao Zhang

Moving Object Detection (MOD) is a fundamental step for many computer vision applications. MOD becomes very challenging when a video sequence captured from a static or moving camera suffers from the challenges: camouflage, shadow, dynamic…

计算机视觉与模式识别 · 计算机科学 2022-07-15 Jhony H. Giraldo , Sajid Javed , Naoufel Werghi , Thierry Bouwmans

The multi-modal salient object detection model based on RGB-D information has better robustness in the real world. However, it remains nontrivial to better adaptively balance effective multi-modal information in the feature fusion phase. In…

计算机视觉与模式识别 · 计算机科学 2022-02-09 Jinchao Zhu , Xiaoyu Zhang , Xian Fang , Feng Dong , Qiu Yu

Recent advances in the industrial inspection of textured surfaces-in the form of visual inspection-have made such inspections possible for efficient, flexible manufacturing systems. We propose an unsupervised feature memory rearrangement…

计算机视觉与模式识别 · 计算机科学 2022-06-23 Haiming Yao , Wenyong Yu , Xue Wang

We present SceneVGGT, a spatio-temporal 3D scene understanding framework that combines SLAM with semantic mapping for autonomous and assistive navigation. Built on VGGT, our method scales to long video streams via a sliding-window pipeline.…