Related papers: Motion Vector Extrapolation for Video Object Detec…
For the majority of the machine learning community, the expensive nature of collecting high-quality human-annotated data and the inability to efficiently finetune very large state-of-the-art pretrained models on limited compute are major…
The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization. In this paper, we present a conceptually simple, computationally…
The strong temporal consistency of surveillance video enables compelling compression performance with traditional methods, but downstream vision applications operate on decoded image frames with a high data rate. Since it is not…
Traffic videos inherently differ from generic videos in their stationary camera setup, thus providing a strong motion prior where objects often move in a specific direction over a short time interval. Existing works predominantly employ…
Video object segmentation aims at accurately segmenting the target object regions across consecutive frames. It is technically challenging for coping with complicated factors (e.g., shape deformations, occlusion and out of the lens). Recent…
Video action recognition, which is topical in computer vision and video analysis, aims to allocate a short video clip to a pre-defined category such as brushing hair or climbing stairs. Recent works focus on action recognition with deep…
As mobile computing technology rapidly evolves, deploying efficient object detection algorithms on mobile devices emerges as a pivotal research area in computer vision. This study zeroes in on optimizing the YOLOv7 algorithm to boost its…
State-of-the-art object detectors and trackers are developing fast. Trackers are in general more efficient than detectors but bear the risk of drifting. A question is hence raised -- how to improve the accuracy of video object…
Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associated. Although deep-learning based method can noticeably…
Object detection is a basic computer vision task to loccalize and categorize objects in a given image. Most state-of-the-art detection methods utilize a fixed number of proposals as an intermediate representation of object candidates, which…
In this paper we propose a novel approach for detecting and tracking objects in videos with variable background i.e. videos captured by moving cameras without any additional sensor. In a video captured by a moving camera, both the…
In moving camera videos, motion segmentation is commonly performed using the image plane motion of pixels, or optical flow. However, objects that are at different depths from the camera can exhibit different optical flows even if they share…
Occlusion is one of the most significant challenges encountered by object detectors and trackers. While both object detection and tracking has received a lot of attention in the past, most existing methods in this domain do not target…
Video object detection targets to simultaneously localize the bounding boxes of the objects and identify their classes in a given video. One challenge for video object detection is to consistently detect all objects across the whole video.…
This paper presents static object detection and segmentation method in videos from cluttered scenes. Robust static object detection is still challenging task due to presence of moving objects in many surveillance applications. The level of…
Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation. However, these approaches typically struggle on long videos due to increased GPU memory demands, as they frequently expand…
In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection. Built upon the sparse query design in the PETR series, we systematically develop an object-centric temporal mechanism. The…
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…
Detection of moving objects is an essential capability in dealing with dynamic environments. Most moving object detection algorithms have been designed for color images without depth. For robotic navigation where real-time RGB-D data is…
We consider the problem of providing dense segmentation masks for object discovery in videos. We formulate the object discovery problem as foreground motion clustering, where the goal is to cluster foreground pixels in videos into different…