Related papers: FAQ: Feature Aggregated Queries for Transformer-ba…
Video object detection is a fundamental yet challenging task in computer vision. One practical solution is to take advantage of temporal information from the video and apply feature aggregation to enhance the object features in each frame.…
Compared with still image object detection, video object detection (VOD) needs to particularly concern the high across-frame variation in object appearance, and the diverse deterioration in some frames. In principle, the detection in a…
Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to…
Recent cutting-edge feature aggregation paradigms for video object detection rely on inferring feature correspondence. The feature correspondence estimation problem is fundamentally difficult due to poor image quality, motion blur, etc, and…
We present an Object-aware Feature Aggregation (OFA) module for video object detection (VID). Our approach is motivated by the intriguing property that video-level object-aware knowledge can be employed as a powerful semantic prior to help…
Video objection detection is a challenging task because isolated video frames may encounter appearance deterioration, which introduces great confusion for detection. One of the popular solutions is to exploit the temporal information and…
Video object detection is a fundamental problem in computer vision and has a wide spectrum of applications. Based on deep networks, video object detection is actively studied for pushing the limits of detection speed and accuracy. To reduce…
Video object detection has made significant progress in recent years thanks to convolutional neural networks (CNNs) and vision transformers (ViTs). Typically, CNNs excel at capturing local features but struggle to model global…
Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame. This results in suboptimal performance and increased…
Video objection detection (VID) has been a rising research direction in recent years. A central issue of VID is the appearance degradation of video frames caused by fast motion. This problem is essentially ill-posed for a single frame.…
Video deblurring methods, aiming at recovering consecutive sharp frames from a given blurry video, usually assume that the input video suffers from consecutively blurry frames. However, in real-world scenarios captured by modern imaging…
Video object detection is more challenging compared to image object detection. Previous works proved that applying object detector frame by frame is not only slow but also inaccurate. Visual clues get weakened by defocus and motion blur,…
Input aggregation is a simple technique used by state-of-the-art LiDAR 3D object detectors to improve detection. However, increasing aggregation is known to have diminishing returns and even performance degradation, due to objects…
The primary challenge in Video Object Detection (VOD) is effectively exploiting temporal information to enhance object representations. Traditional strategies, such as aggregating region proposals, often suffer from feature variance due to…
This paper aims to learn a compact representation of a video for video face recognition task. We make the following contributions: first, we propose a meta attention-based aggregation scheme which adaptively and fine-grained weighs the…
A significant amount of redundancy exists between consecutive frames of a video. Object detectors typically produce detections for one image at a time, without any capabilities for taking advantage of this redundancy. Meanwhile, many…
Single shot detectors that are potentially faster and simpler than two-stage detectors tend to be more applicable to object detection in videos. Nevertheless, the extension of such object detectors from image to video is not trivial…
Video periocular recognition is the task of recognizing an individual's identity based on the region around an individual's eyes. The periocular area is one of the most discriminative regions of the human face, making it suitable for…
Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature degradation caused by fast motion or multiple poses. Current…
Video object detection has been an important yet challenging topic in computer vision. Traditional methods mainly focus on designing the image-level or box-level feature propagation strategies to exploit temporal information. This paper…