# Object Detection in Videos by High Quality Object Linking

arXiv: https://arxiv.org/abs/1801.09823 · HTML: https://mlsanity.com/paper/1801.09823/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2018.

## Built on by (most cited first, 11 of 11)

- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Crossover Learning for Fast Online Video Instance Segmentation](https://mlsanity.com/paper/2104.05970/) (2021)
- [LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception](https://mlsanity.com/paper/2210.15518/) (2022)
- [Few-Shot Video Object Detection](https://mlsanity.com/paper/2104.14805/) (2021)
- [BoxMask: Revisiting Bounding Box Supervision for Video Object Detection](https://mlsanity.com/paper/2210.06008/) (2022)
- [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)
- [GLRD: Global-Local Collaborative Reason and Debate with PSL for 3D Open-Vocabulary Detection](https://mlsanity.com/paper/2503.20682/) (2025)
- [VariabilityTrack:Multi-Object Tracking with Variable Speed Object Movement](https://mlsanity.com/paper/2203.06424/) (2022)
- [D^bf3: Duplicate Detection Decontaminator for Multi-Athlete Tracking in Sports Videos](https://mlsanity.com/paper/2209.12248/) (2022)
- [Non-parametric Contextual Relationship Learning for Semantic Video Object Segmentation](https://mlsanity.com/paper/2407.05916/) (2024)

## Abstract (arXiv)

Compared with object detection in static images, object detection in videos is more challenging due to degraded image qualities. An effective way to address this problem is to exploit temporal contexts by linking the same object across video to form tubelets and aggregating classification scores in the tubelets. In this paper, we focus on obtaining high quality object linking results for better classification. Unlike previous methods that link objects by checking boxes between neighboring frames, we propose to link in the same frame. To achieve this goal, we extend prior methods in following aspects: (1) a cuboid proposal network that extracts spatio-temporal candidate cuboids which bound the movement of objects; (2) a short tubelet detection network that detects short tubelets in short video segments; (3) a short tubelet linking algorithm that links temporally-overlapping short tubelets to form long tubelets. Experiments on the ImageNet VID dataset show that our method outperforms both the static image detector and the previous state of the art. In particular, our method improves results by 8.8% over the static image detector for fast moving objects.