# Single Shot Video Object Detector

arXiv: https://arxiv.org/abs/2007.03560 · HTML: https://mlsanity.com/paper/2007.03560/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2020.

## Built on by (most cited first, 7 of 7)

- [Track to Detect and Segment: An Online Multi-Object Tracker](https://mlsanity.com/paper/2103.08808/) (2021)
- [Implicit Temporal Modeling with Learnable Alignment for Video Recognition](https://mlsanity.com/paper/2304.10465/) (2023)
- [CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation](https://mlsanity.com/paper/2208.12448/) (2022)
- [3D Cascade RCNN: High Quality Object Detection in Point Clouds](https://mlsanity.com/paper/2211.08248/) (2022)
- [Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey](https://mlsanity.com/paper/2105.12694/) (2021)
- [Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection](https://mlsanity.com/paper/2108.13775/) (2021)
- [TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection](https://mlsanity.com/paper/2503.13903/) (2025)

## Abstract (arXiv)

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 especially when appearance deterioration exists in videos, e.g., motion blur or occlusion. A valid question is how to explore temporal coherence across frames for boosting detection. In this paper, we propose to address the problem by enhancing per-frame features through aggregation of neighboring frames. Specifically, we present Single Shot Video Object Detector (SSVD) -- a new architecture that novelly integrates feature aggregation into a one-stage detector for object detection in videos. Technically, SSVD takes Feature Pyramid Network (FPN) as backbone network to produce multi-scale features. Unlike the existing feature aggregation methods, SSVD, on one hand, estimates the motion and aggregates the nearby features along the motion path, and on the other, hallucinates features by directly sampling features from the adjacent frames in a two-stream structure. Extensive experiments are conducted on ImageNet VID dataset, and competitive results are reported when comparing to state-of-the-art approaches. More remarkably, for 448 × 448 input, SSVD achieves 79.2% mAP on ImageNet VID, by processing one frame in 85 ms on an Nvidia Titan X Pascal GPU. The code is available at urlhttps://github.com/ddjiajun/SSVD.