Related papers: Alpha-Refine: Boosting Tracking Performance by Pre…
Bird's-Eye-View (BEV) semantic segmentation provides comprehensive environmental perception for autonomous driving but suffers multi-modal misalignment and sensor noise. We propose RESAR-BEV, a progressive refinement framework that advances…
Large-scale object detection datasets (e.g., MS-COCO) try to define the ground truth bounding boxes as clear as possible. However, we observe that ambiguities are still introduced when labeling the bounding boxes. In this paper, we propose…
This paper proposes an eye tracking module for the XR Space Framework aimed at enhancing human performance in XR-based applications, specifically in training, screening, and teleoperation. This framework provides a methodology and…
Alpha matting aims to estimate the translucency of an object in a given image. The resulting alpha matte describes pixel-wise to what amount foreground and background colors contribute to the color of the composite image. While most methods…
Most tracking-by-detection methods employ a local search window around the predicted object location in the current frame assuming the previous location is accurate, the trajectory is smooth, and the computational capacity permits a search…
Most existing trackers are based on using a classifier and multi-scale estimation to estimate the target state. Consequently, and as expected, trackers have become more stable while tracking accuracy has stagnated. While trackers adopt a…
The one-shot multi-object tracking, which integrates object detection and ID embedding extraction into a unified network, has achieved groundbreaking results in recent years. However, current one-shot trackers solely rely on single-frame…
Visual-based target tracking is easily influenced by multiple factors, such as background clutter, targets fast-moving, illumination variation, object shape change, occlusion, etc. These factors influence the tracking accuracy of a target…
We introduce region-specific image refinement as a dedicated problem setting: given an input image and a user-specified region (e.g., a scribble mask or a bounding box), the goal is to restore fine-grained details while keeping all…
Efficient compression of 360-degree video content requires the application of advanced motion models for interframe prediction. The Motion Plane Adaptive (MPA) motion model projects the frames on multiple perspective planes in the 3D space.…
Discriminative correlation filters show excellent performance in object tracking. However, in complex scenes, the apparent characteristics of the tracked target are variable, which makes it easy to pollute the model and cause the model…
Much recent progress has been made in reconstructing the 3D shape of an object from an image of it, i.e. single view 3D reconstruction. However, it has been suggested that current methods simply adopt a "nearest-neighbor" strategy, instead…
In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper…
Convolution Neural Networks (CNN) have been extremely successful in solving intensive computer vision tasks. The convolutional filters used in CNNs have played a major role in this success, by extracting useful features from the inputs.…
Bayesian optimization is popular for optimizing time-consuming black-box objectives. Nonetheless, for hyperparameter tuning in deep neural networks, the time required to evaluate the validation error for even a few hyperparameter settings…
Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…
Coarsely-labeled semantic segmentation annotations are easy to obtain, but therefore bear the risk of losing edge details and introducing background pixels. Impeded by the inherent noise, existing coarse annotations are only taken as a…
Although deep models have greatly improved the accuracy and robustness of image segmentation, obtaining segmentation results with highly accurate boundaries and fine structures is still a challenging problem. In this paper, we propose a…
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in…
We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. MixTraining enhances data augmentation by utilizing augmentations of different strengths while excluding…