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 …

Video object detection (VID) is challenging because of the high variation of object
appearance as well as the diverse deterioration in some frames. On the positive side, the …

Current video object detection (VOD) models often encounter issues with over-aggregation
due to redundant aggregation strategies, which perform feature aggregation on every frame …

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 …

Recently, one-stage detectors have achieved competitive accuracy and faster speed
compared with traditional two-stage detectors on image data. However, in the field of video …

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 …

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 …

We present a new, simple yet effective approach to uplift video object detection. We observe
that prior works operate on instance-level feature aggregation that imminently neglects the …

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 …

In this paper, we propose a new video object detection (VoD) method, referred to as
temporal feature aggregation and motion-aware VoD (TM-VoD), that produces a joint …