Springer Science and Business Media LLC

Công bố khoa học tiêu biểu

* Dữ liệu chỉ mang tính chất tham khảo

Sắp xếp:  
Ma trận cơ bản: Lý thuyết, thuật toán và phân tích độ ổn định Dịch bởi AI
Springer Science and Business Media LLC - Tập 17 - Trang 43-75 - 1996
Quan-Tuan Luong, Olivier D. Faugeras
Trong bài báo này, chúng tôi phân tích chi tiết hình học của một cặp camera, tức là một thiết lập stereo. Trái ngược với những gì đã được thực hiện trong quá khứ và vẫn đang được sử dụng hiện nay, chẳng hạn như trong phân tích stereo hoặc chuyển động, chúng tôi không giả định rằng các tham số nội tại của các camera là đã biết (tọa độ của các điểm chính, tỷ lệ pixel và tiêu cự). Điều này quan trọng...... hiện toàn bộ
#ma trận cơ bản #hình học stereo #ước lượng #thị giác máy tính ba chiều #ổn định
Improving Bag-of-Features for Large Scale Image Search
Springer Science and Business Media LLC - Tập 87 - Trang 316-336 - 2009
Hervé Jégou, Matthijs Douze, Cordelia Schmid
This article improves recent methods for large scale image search. We first analyze the bag-of-features approach in the framework of approximate nearest neighbor search. This leads us to derive a more precise representation based on Hamming embedding (HE) and weak geometric consistency constraints (WGC). HE provides binary signatures that refine the matching based on visual words. WGC filters matc...... hiện toàn bộ
Real-Time 3D Head Pose Tracking Through 2.5D Constrained Local Models with Local Neural Fields
Springer Science and Business Media LLC - - 2019
Stephen Ackland, Francisco Chiclana, Howell Istance, Simon Coupland
Are Vision Transformers Robust to Spurious Correlations?
Springer Science and Business Media LLC - - Trang 1-21 - 2023
Soumya Suvra Ghosal, Yixuan Li
Deep neural networks may be susceptible to learning spurious correlations that hold on average but not in atypical test samples. As with the recent emergence of vision transformer (ViT) models, it remains unexplored how spurious correlations are manifested in such architectures. In this paper, we systematically investigate the robustness of different transformer architectures to spurious correlati...... hiện toàn bộ
Bounding Multiple Gaussians Uncertainty with Application to Object Tracking
Springer Science and Business Media LLC - Tập 118 - Trang 364-379 - 2016
Baochang Zhang, Alessandro Perina, Zhigang Li, Vittorio Murino, Jianzhuang Liu, Rongrong Ji
This paper proves the uncertainty bound for the multiple Gaussian functions, termed multiple Gaussians Uncertainty (MGU), which significantly generalizes the uncertainty principle for the single Gaussian function. First, as a theoretical contribution, we prove that the momentum (velocity) and position for the sum of multiple Gaussians wave function are theoretically bounded. Second, as for a pract...... hiện toàn bộ
Temporal Multi-Scale Models for Flow and Acceleration
Springer Science and Business Media LLC - Tập 32 - Trang 147-163 - 1999
Yaser Yacoob, Larry S. Davis
A model for computing image flow in image sequences containing a very wide range of instantaneous flows is proposed. This model integrates the spatio-temporal image derivatives from multiple temporal scales to provide both reliable and accurate instantaneous flow estimates. The integration employs robust regression and automatic scale weighting in a generalized brightness constancy framework. In a...... hiện toàn bộ
Self-Calibration of Stationary Cameras
Springer Science and Business Media LLC - Tập 22 - Trang 5-23 - 1997
Richard I. Hartley
A new practical method is given for the self-calibration of a camera. In this method, at least three images are taken from the same point in space with different orientations of the camera and calibration is computed from an analysis of point matches between the images. The method requires no knowledge of the orientations of the camera. Calibration is based on the image correspondences only. This ...... hiện toàn bộ
Video Behaviour Mining Using a Dynamic Topic Model
Springer Science and Business Media LLC - Tập 98 - Trang 303-323 - 2011
Timothy Hospedales, Shaogang Gong, Tao Xiang
This paper addresses the problem of fully automated mining of public space video data, a highly desirable capability under contemporary commercial and security considerations. This task is especially challenging due to the complexity of the object behaviors to be profiled, the difficulty of analysis under the visual occlusions and ambiguities common in public space video, and the computational cha...... hiện toàn bộ
Context-Based Path Prediction for Targets with Switching Dynamics
Springer Science and Business Media LLC - Tập 127 - Trang 239-262 - 2018
Julian F. P. Kooij, Fabian Flohr, Ewoud A. I. Pool, Dariu M. Gavrila
Anticipating future situations from streaming sensor data is a key perception challenge for mobile robotics and automated vehicles. We address the problem of predicting the path of objects with multiple dynamic modes. The dynamics of such targets can be described by a Switching Linear Dynamical System (SLDS). However, predictions from this probabilistic model cannot anticipate when a change in dyn...... hiện toàn bộ
Classifier and Exemplar Synthesis for Zero-Shot Learning
Springer Science and Business Media LLC - - 2019
Soravit Changpinyo, Wei-Lun Chao, Boqing Gong, Fei Sha
Zero-shot learning (ZSL) enables solving a task without the need to see its examples. In this paper, we propose two ZSL frameworks that learn to synthesize parameters for novel unseen classes. First, we propose to cast the problem of ZSL as learning manifold embeddings from graphs composed of object classes, leading to a flexible approach that synthesizes “classifiers” for the unseen classes. Then...... hiện toàn bộ
Tổng số: 2,006   
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 10