中文
相关论文

相关论文: Cross-Domain Visual Matching via Generalized Simil…

200 篇论文

Person re-identification (re-ID) is a task of matching pedestrians under disjoint camera views. To recognise paired snapshots, it has to cope with large cross-view variations caused by the camera view shift. Supervised deep neural networks…

计算机视觉与模式识别 · 计算机科学 2019-07-24 Lin Wu , Richang Hong , Yang Wang , Meng Wang

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric. Our pipeline's modular structure allows…

计算机视觉与模式识别 · 计算机科学 2021-02-12 Yuhe Jin , Dmytro Mishkin , Anastasiia Mishchuk , Jiri Matas , Pascal Fua , Kwang Moo Yi , Eduard Trulls

The ability to classify images is dependent on having access to large labeled datasets and testing on data from the same domain that the model can train on. Classification becomes more challenging when dealing with new data from a different…

计算机视觉与模式识别 · 计算机科学 2023-10-20 Firas Al-Hindawi , Md Mahfuzur Rahman Siddiquee , Teresa Wu , Han Hu , Ying Sun

Generalized gait recognition remains challenging due to significant domain shifts in viewpoints, appearances, and environments. Mixed-dataset training has recently become a practical route to improve cross-domain robustness, but it…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Qian Zhou , Xianda Guo , Jilong Wang , Chuanfu Shen , Zhongyuan Wang , Zhen Han , Qin Zou , Shiqi Yu

Longitudinal studies, where a series of images from the same set of individuals are acquired at different time-points, represent a popular technique for studying and characterizing temporal dynamics in biomedical applications. The classical…

图像与视频处理 · 电气工程与系统科学 2023-04-18 Heejong Kim , Mert R. Sabuncu

In many applications involving multi-media data, the definition of similarity between items is integral to several key tasks, e.g., nearest-neighbor retrieval, classification, and recommendation. Data in such regimes typically exhibits…

人工智能 · 计算机科学 2010-09-01 Brian McFee , Gert Lanckriet

Existing person re-identification (re-ID) research mainly focuses on pedestrian identity matching across cameras in adjacent areas. However, in reality, it is inevitable to face the problem of pedestrian identity matching across…

计算机视觉与模式识别 · 计算机科学 2023-07-18 Huafeng Li , Yanmei Mao , Yafei Zhang , Guanqiu Qi , Zhengtao Yu

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing…

计算机视觉与模式识别 · 计算机科学 2017-11-17 Tanmoy Mukherjee , Makoto Yamada , Timothy M. Hospedales

Image matching, which establishes correspondences between two-view images to recover 3D structure and camera geometry, serves as a cornerstone in computer vision and underpins a wide range of applications, including visual localization, 3D…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Shihua Zhang , Zizhuo Li , Kaining Zhang , Yifan Lu , Yuxin Deng , Linfeng Tang , Xingyu Jiang , Jiayi Ma

Person re-identification (Re-ID) is the task of matching humans across cameras with non-overlapping views that has important applications in visual surveillance. Like other computer vision tasks, this task has gained much with the…

计算机视觉与模式识别 · 计算机科学 2018-07-24 Sergey Rodionov , Alexey Potapov , Hugo Latapie , Enzo Fenoglio , Maxim Peterson

Person re-identification (Re-ID) aims to match person images across non-overlapping camera views. The majority of Re-ID methods focus on small-scale surveillance systems in which each pedestrian is captured in different camera views of…

计算机视觉与模式识别 · 计算机科学 2021-07-30 Wenhang Ge , Chunyan Pan , Ancong Wu , Hongwei Zheng , Wei-Shi Zheng

As one of the fundamental functions of autonomous driving system, freespace detection aims at classifying each pixel of the image captured by the camera as drivable or non-drivable. Current works of freespace detection heavily rely on large…

计算机视觉与模式识别 · 计算机科学 2022-10-07 Yuanbin Wang , Leyan Zhu , Shaofei Huang , Tianrui Hui , Xiaojie Li , Fei Wang , Si Liu

3D shape matching is a long-standing problem in computer vision and computer graphics. While deep neural networks were shown to lead to state-of-the-art results in shape matching, existing learning-based approaches are limited in the…

计算机视觉与模式识别 · 计算机科学 2022-07-21 Dongliang Cao , Florian Bernard

Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Jiaming Zhou , Teli Ma , Kun-Yu Lin , Zifan Wang , Ronghe Qiu , Junwei Liang

The rapid evolution of generative models has enabled the creation of hyper-realistic facial deepfakes, exposing a critical vulnerability in modern digital forensics: the inability of detectors to generalize to unseen manipulation…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Ibrahim Delibasoglu

Accurate spatial understanding is essential for image-guided surgery, augmented reality integration and context awareness. In minimally invasive procedures, where visual input is the sole intraoperative modality, establishing precise…

计算机视觉与模式识别 · 计算机科学 2025-12-12 Alberto Rota , Elena De Momi

Multi-modal medical image segmentation plays an essential role in clinical diagnosis. It remains challenging as the input modalities are often not well-aligned spatially. Existing learning-based methods mainly consider sharing trainable…

计算机视觉与模式识别 · 计算机科学 2021-01-06 Jingkun Chen , Wenqi Li , Hongwei Li , Jianguo Zhang

Person search is a challenging task which aims to achieve joint pedestrian detection and person re-identification (ReID). Previous works have made significant advances under fully and weakly supervised settings. However, existing methods…

计算机视觉与模式识别 · 计算机科学 2022-07-26 Junjie Li , Yichao Yan , Guanshuo Wang , Fufu Yu , Qiong Jia , Shouhong Ding

Multiple Object Tracking (MOT) plays an important role in solving many fundamental problems in video analysis in computer vision. Most MOT methods employ two steps: Object Detection and Data Association. The first step detects objects of…

计算机视觉与模式识别 · 计算机科学 2019-07-17 ShiJie Sun , Naveed Akhtar , HuanSheng Song , Ajmal Mian , Mubarak Shah

In object detection, data amount and cost are a trade-off, and collecting a large amount of data in a specific domain is labor intensive. Therefore, existing large-scale datasets are used for pre-training. However, conventional transfer…

计算机视觉与模式识别 · 计算机科学 2022-09-01 Yuzuru Nakamura , Yasunori Ishii , Yuki Maruyama , Takayoshi Yamashita