Abstract Objects in videos are typically characterized by continuous smooth motion. We
exploit continuous smooth motion in three ways. 1) Improved accuracy by using object …

Single-frame object detectors perform well on videos sometimes, even without temporal
context. However, challenges such as occlusion, motion blur, and rare poses of objects are …

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 …

While single-image object detectors can be naively applied to videos in a frame-by-frame
fashion, the prediction is often temporally inconsistent. Moreover, the computation can be …

Despite significant progress in semi-supervised learning for image object detection, several
key issues are yet to be addressed for video object detection:(1) Achieving good …

Deep convolutional neural networks have achieved great success on various image
recognition tasks. However, it is nontrivial to transfer the existing networks to video due to …

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 …

Extending state-of-the-art object detectors from image to video is challenging. The accuracy
of detection suffers from degenerated object appearances in videos, eg, motion blur, video …

Abstract We introduce Spatial-Temporal Memory Networks for video object detection. At its
core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent …

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 …