This paper presents the novel idea of generating object proposals by leveraging temporal
information for video object detection. The feature aggregation in modern region-based …

Transferring image-based object detectors to the domain of videos remains a challenging
problem. Previous efforts mostly exploit optical flow to propagate features across frames …

Recent cutting-edge feature aggregation paradigms for video object detection rely on
inferring feature correspondence. The feature correspondence estimation problem is …

Recent progress in video object detection (VOD) has shown that aggregating features from
other frames to capture long-range contextual information is very important to deal with the …

State-of-the-art video object detection methods maintain a memory structure, either a sliding
window or a memory queue, to enhance the current frame using attention mechanisms …

Recent studies have shown that, context aggregating information from proposals in different
frames can clearly enhance the performance of video object detection. However, these …

Transferring existing image-based detectors to the video is non-trivial since the quality of
frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous …

For efficient video object detection, our detector consists of a spatial module and a temporal
module. The spatial module aims to detect objects in static frames using convolutional …

Abstract In Video Object Detection (VID), a common practice is to leverage the rich temporal
contexts from the video to enhance the object representations in each frame. Existing …

Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the
need for many hand-designed components in object detection while demonstrating good …