# Impression Network for Video Object Detection

arXiv: https://arxiv.org/abs/1712.05896 · HTML: https://mlsanity.com/paper/1712.05896/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2017.

## Built on by (most cited first, 13 of 13)

- [MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection](https://mlsanity.com/paper/2205.05979/) (2022)
- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [Segment Anything Model for Road Network Graph Extraction](https://mlsanity.com/paper/2403.16051/) (2024)
- [QueryProp: Object Query Propagation for High-Performance Video Object Detection](https://mlsanity.com/paper/2207.10959/) (2022)
- [ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation](https://mlsanity.com/paper/2102.13493/) (2021)
- [Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation](https://mlsanity.com/paper/2103.14529/) (2021)
- [Flying Bird Object Detection Algorithm in Surveillance Video Based on Motion Information](https://mlsanity.com/paper/2301.01917/) (2023)
- [Novel View Synthesis from a Single RGBD Image for Indoor Scenes](https://mlsanity.com/paper/2311.01065/) (2023)
- [A Flying Bird Object Detection Method for Surveillance Video](https://mlsanity.com/paper/2401.03749/) (2024)
- [SGE net: Video object detection with squeezed GRU and information entropy map](https://mlsanity.com/paper/2106.07224/) (2021)
- [EucliDreamer: Fast and High-Quality Texturing for 3D Models with Depth-Conditioned Stable Diffusion](https://mlsanity.com/paper/2404.10279/) (2024)
- [Multimodal Spatio-temporal Graph Learning for Alignment-free RGBT Video Object Detection](https://mlsanity.com/paper/2504.11779/) (2025)
- [A comprehensive overview of deep learning models for object detection from videos/images](https://mlsanity.com/paper/2601.14677/) (2026)

## Abstract (arXiv)

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, causing failure on corresponding frames. Multi-frame feature fusion methods proved effective in improving the accuracy, but they dramatically sacrifice the speed. Feature propagation based methods proved effective in improving the speed, but they sacrifice the accuracy. So is it possible to improve speed and performance simultaneously? Inspired by how human utilize impression to recognize objects from blurry frames, we propose Impression Network that embodies a natural and efficient feature aggregation mechanism. In our framework, an impression feature is established by iteratively absorbing sparsely extracted frame features. The impression feature is propagated all the way down the video, helping enhance features of low-quality frames. This impression mechanism makes it possible to perform long-range multi-frame feature fusion among sparse keyframes with minimal overhead. It significantly improves per-frame detection baseline on ImageNet VID while being 3 times faster (20 fps). We hope Impression Network can provide a new perspective on video feature enhancement. Code will be made available.