Related papers: A Detector-oblivious Multi-arm Network for Keypoin…
We propose a novel learned keypoint detection method to increase the number of correct matches for the task of non-rigid image correspondence. By leveraging true correspondences acquired by matching annotated image pairs with a specified…
Matching keypoint pairs of different images is a basic task of computer vision. Most methods require customized extremum point schemes to obtain the coordinates of feature points with high confidence, which often need complex algorithmic…
Establishing a sparse set of keypoint correspon dences between images is a fundamental task in many computer vision pipelines. Often, this translates into a computationally expensive nearest neighbor search, where every keypoint descriptor…
We present a novel learned keypoint detection method designed to maximize the number of correct matches for the task of non-rigid image correspondence. Our training framework uses true correspondences, obtained by matching annotated image…
Hyperspectral image denoising is unique for the highly similar and correlated spectral information that should be properly considered. However, existing methods show limitations in exploring the spectral correlations across different bands…
Local feature matching is an essential component in many visual applications. In this work, we propose OAMatcher, a Tranformer-based detector-free method that imitates humans behavior to generate dense and accurate matches. Firstly,…
In modern recommender systems, sequential recommendation leverages chronological user behaviors to make effective next-item suggestions, which suffers from data sparsity issues, especially for new users. One promising line of work is the…
3D object detection is an important module in autonomous driving and robotics. However, many existing methods focus on using single frames to perform 3D detection, and do not fully utilize information from multiple frames. In this paper, we…
The detection of anatomical landmarks is a vital step for medical image analysis and applications for diagnosis, interpretation and guidance. Manual annotation of landmarks is a tedious process that requires domain-specific expertise and…
We develop a robust multi-scale structure-aware neural network for human pose estimation. This method improves the recent deep conv-deconv hourglass models with four key improvements: (1) multi-scale supervision to strengthen contextual…
We propose augmenting deep neural networks with an attention mechanism for the visual object detection task. As perceiving a scene, humans have the capability of multiple fixation points, each attended to scene content at different…
Intelligent robots require object-level scene understanding to reason about possible tasks and interactions with the environment. Moreover, many perception tasks such as scene reconstruction, image retrieval, or place recognition can…
Person re-identification is the problem of recognizing people across different images or videos with non-overlapping views. Although there has been much progress in person re-identification over the last decade, it remains a challenging…
This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pairwise correspondences, the proposed method identifies and matches only a…
Person re-identification is the task of recognizing or identifying a person across multiple views in multi-camera networks. Although there has been much progress in person re-identification, person re-identification in large-scale…
In this thesis, we propose a pioneering work on sparse keypoints tracking across images using transformer networks. While deep learning-based keypoints matching have been widely investigated using graph neural networks - and more recently…
This paper proposes a DNN-based system that detects multiple people from a single depth image. Our neural network processes a depth image and outputs a likelihood map in image coordinates, where each detection corresponds to a…
Person re-identification in large-scale multi-camera networks is a challenging task because of the spatio-temporal uncertainty and high complexity due to large numbers of cameras and people. To handle these difficulties, additional…
The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using a single network.…
We present Manifold Alignment Determination (MAD), an algorithm for learning alignments between data points from multiple views or modalities. The approach is capable of learning correspondences between views as well as correspondences…