# Dual Semantic Fusion Network for Video Object Detection

arXiv: https://arxiv.org/abs/2009.07498 · HTML: https://mlsanity.com/paper/2009.07498/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [Crossover Learning for Fast Online Video Instance Segmentation](https://mlsanity.com/paper/2104.05970/) (2021)
- [TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2201.05047/) (2022)
- [End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2105.10920/) (2021)
- [DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving](https://mlsanity.com/paper/2303.17144/) (2023)
- [Tracking Instances as Queries](https://mlsanity.com/paper/2106.11963/) (2021)
- [Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network](https://mlsanity.com/paper/2111.04733/) (2021)
- [Identity-Consistent Aggregation for Video Object Detection](https://mlsanity.com/paper/2308.07737/) (2023)
- [Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection](https://mlsanity.com/paper/2308.11327/) (2023)
- [SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving](https://mlsanity.com/paper/2405.18857/) (2024)
- [TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection](https://mlsanity.com/paper/2503.13903/) (2025)
- [Unifying Tracking and Image-Video Object Detection](https://mlsanity.com/paper/2211.11077/) (2022)
- [Learn Temporal Consistency For Robust Satellite Video Detector](https://mlsanity.com/paper/2606.15112/) (2026)

## Abstract (arXiv)

Video object detection is a tough task due to the deteriorated quality of video sequences captured under complex environments. Currently, this area is dominated by a series of feature enhancement based methods, which distill beneficial semantic information from multiple frames and generate enhanced features through fusing the distilled information. However, the distillation and fusion operations are usually performed at either frame level or instance level with external guidance using additional information, such as optical flow and feature memory. In this work, we propose a dual semantic fusion network (abbreviated as DSFNet) to fully exploit both frame-level and instance-level semantics in a unified fusion framework without external guidance. Moreover, we introduce a geometric similarity measure into the fusion process to alleviate the influence of information distortion caused by noise. As a result, the proposed DSFNet can generate more robust features through the multi-granularity fusion and avoid being affected by the instability of external guidance. To evaluate the proposed DSFNet, we conduct extensive experiments on the ImageNet VID dataset. Notably, the proposed dual semantic fusion network achieves, to the best of our knowledge, the best performance of 84.1% mAP among the current state-of-the-art video object detectors with ResNet-101 and 85.4% mAP with ResNeXt-101 without using any post-processing steps.