Related papers: Transfer Learning for Keypoint Detection in Low-Re…
The main challenges of 3D pose transfer are: 1) Lack of paired training data with different characters performing the same pose; 2) Disentangling pose and shape information from the target mesh; 3) Difficulty in applying to meshes with…
We introduce an approach for image segmentation based on sparse correspondences between keypoints in testing and training images. Keypoints represent automatically identified distinctive image locations, where each keypoint correspondence…
The typical bottom-up human pose estimation framework includes two stages, keypoint detection and grouping. Most existing works focus on developing grouping algorithms, e.g., associative embedding, and pixel-wise keypoint regression that we…
We introduce YOLO-pose, a novel heatmap-free approach for joint detection, and 2D multi-person pose estimation in an image based on the popular YOLO object detection framework. Existing heatmap based two-stage approaches are sub-optimal as…
Current works focus on addressing the remote sensing change detection task using bi-temporal images. Although good performance can be achieved, however, seldom of they consider the motion cues which may also be vital. In this work, we…
Structural system identification in the presence of thermal loads is challenging, as unmeasured or poorly modeled thermal effects can mask or mimic damage, leading to unreliable conclusions. This work presents an optimization-driven,…
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…
We introduce Temporal consistency for Test-time adaptation (TempT) a novel method for test-time adaptation on videos through the use of temporal coherence of predictions across sequential frames as a self-supervision signal. TempT is an…
Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial…
Transfer learning allows us to exploit knowledge gained from one task to assist in solving another but relevant task. In modern computer vision research, the question is which architecture performs better for a given dataset. In this paper,…
Lattice thermal conductivity (TC) of semiconductors is crucial for various applications, ranging from microelectronics to thermoelectrics. Data-driven approach can potentially establish the critical composition-property relationship needed…
Thermal cameras capture environmental data through heat emission, a fundamentally different mechanism compared to visible light cameras, which rely on pinhole imaging. As a result, traditional visual relocalization methods designed for…
In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and…
Accurate rotational odometry is crucial for autonomous robotic systems, particularly for small, power-constrained platforms such as drones and mobile robots. This study introduces thermal-gyro fusion, a novel sensor fusion approach that…
A significant challenge in the field of object detection lies in the system's performance under non-ideal imaging conditions, such as rain, fog, low illumination, or raw Bayer images that lack ISP processing. Our study introduces "Feature…
Most of the automatic fire alarm systems detect the fire presence through sensors like thermal, smoke, or flame. One of the new approaches to the problem is the use of images to perform the detection. The image approach is promising since…
Multiple Object Tracking (MOT) in thermal imaging presents unique challenges due to the lack of visual features and the complexity of motion patterns. This paper introduces an innovative approach to improve MOT in the thermal domain by…
Gait recognition, which refers to the recognition or identification of a person based on their body shape and walking styles, derived from video data captured from a distance, is widely used in crime prevention, forensic identification, and…
This study is focused on evaluating the real-time performance of thermal object detection for smart and safe vehicular systems by deploying the trained networks on GPU & single-board EDGE-GPU computing platforms for onboard automotive…
This study aims to enhance the accuracy of a six-axis force/torque sensor compared to existing approaches that utilize Multi-Layer Perceptron (MLP) and the Least Square Method. The sensor used in this study is based on a photo-coupler and…