Related papers: Triple-stream Deep Metric Learning of Great Ape Be…

This paper addresses the problem of estimating the 3-DoF camera pose for a ground-level image with respect to a satellite image that encompasses the local surroundings. We propose a novel end-to-end approach that leverages the learning of…

We propose a novel point cloud based 3D organ segmentation pipeline utilizing deep Q-learning. In order to preserve shape properties, the learning process is guided using a statistical shape model. The trained agent directly predicts…

Given two consecutive RGB-D images, we propose a model that estimates a dense 3D motion field, also known as scene flow. We take advantage of the fact that in robot manipulation scenarios, scenes often consist of a set of rigidly moving…

Deep neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal importance and determining the activity relevance of…

This paper describes a scalable active learning pipeline prototype for large-scale brain mapping that leverages high performance computing power. It enables high-throughput evaluation of algorithm results, which, after human review, are…

Deep learning (DL) algorithms are the state of the art in automated classification of wildlife camera trap images. The challenge is that the ecologist cannot know in advance how many images per species they need to collect for model…

Recently significant progress has been made in human action recognition and behavior prediction using deep learning techniques, leading to improved vision-based semantic understanding. However, there is still a lack of high-quality motion…

Widely used traditional pipelines for subcortical brain segmentation are often inefficient and slow, particularly when processing large datasets. Furthermore, deep learning models face challenges due to the high resolution of MRI images and…

We present a method to combine markerless motion capture and dense pose feature estimation into a single framework. We demonstrate that dense pose information can help for multiview/single-view motion capture, and multiview motion capture…

Purpose: Surgical scene understanding plays a critical role in the technology stack of tomorrow's intervention-assisting systems in endoscopic surgeries. For this, tracking the endoscope pose is a key component, but remains challenging due…

Sensor-based human activity recognition (HAR) is now a research hotspot in multiple application areas. With the rise of smart wearable devices equipped with inertial measurement units (IMUs), researchers begin to utilize IMU data for HAR.…

Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image…

We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground…

Computer vision for animals holds great promise for wildlife research but often depends on large-scale data, while existing collection methods rely on controlled capture setups. Recent data-driven approaches show the potential of…

Matching two images while estimating their relative geometry is a key step in many computer vision applications. For decades, a well-established pipeline, consisting of SIFT, RANSAC, and 8-point algorithm, has been used for this task.…

We propose MFT -- Multi-Flow dense Tracker -- a novel method for dense, pixel-level, long-term tracking. The approach exploits optical flows estimated not only between consecutive frames, but also for pairs of frames at logarithmically…

In recent years, the advancement of AI technologies has accelerated the development of smart factories. In particular, the automatic monitoring of product assembly progress is crucial for improving operational efficiency, minimizing the…

Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convolutional neural networks (CNNs). Compared with optical flow…

Automotive Cyber-Physical Systems (ACPS) have attracted a significant amount of interest in the past few decades, while one of the most critical operations in these systems is the perception of the environment. Deep learning and,…

Metric learning aims to build a distance metric typically by learning an effective embedding function that maps similar objects into nearby points in its embedding space. Despite recent advances in deep metric learning, it remains…