# Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection

arXiv: https://arxiv.org/abs/2210.02368 · HTML: https://mlsanity.com/paper/2210.02368/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 47 references that are in the map.
- First posted on arXiv 5 Oct 2022.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Deep Feature Flow for Video Recognition](https://mlsanity.com/paper/1611.07715/) (2016)
- [Flow-Guided Feature Aggregation for Video Object Detection](https://mlsanity.com/paper/1703.10025/) (2017)
- [Detect to Track and Track to Detect](https://mlsanity.com/paper/1710.03958/) (2017)
- [Memory Enhanced Global-Local Aggregation for Video Object Detection](https://mlsanity.com/paper/2003.12063/) (2020)
- [Sequence Level Semantics Aggregation for Video Object Detection](https://mlsanity.com/paper/1907.06390/) (2019)
- [TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2201.05047/) (2022)
- [Seq-NMS for Video Object Detection](https://mlsanity.com/paper/1602.08465/) (2016)
- [T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos](https://mlsanity.com/paper/1604.02532/) (2016)
- [Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution](https://mlsanity.com/paper/1909.06720/) (2019)
- [Object Detection from Video Tubelets with Convolutional Neural Networks](https://mlsanity.com/paper/1604.04053/) (2016)
- [TF-Blender: Temporal Feature Blender for Video Object Detection](https://mlsanity.com/paper/2108.05821/) (2021)
- [Progressive Sparse Local Attention for Video object detection](https://mlsanity.com/paper/1903.09126/) (2019)
- [Optimizing Video Object Detection via a Scale-Time Lattice](https://mlsanity.com/paper/1804.05472/) (2018)
- [Object Detection in Videos with Tubelet Proposal Networks](https://mlsanity.com/paper/1702.06355/) (2017)

## Built on by (most cited first, 8 of 8)

- [Object Detection with Transformers: A Review](https://mlsanity.com/paper/2306.04670/) (2023)
- [FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision](https://mlsanity.com/paper/2308.03594/) (2023)
- [Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art](https://mlsanity.com/paper/2309.04902/) (2023)
- [Objects do not disappear: Video object detection by single-frame object location anticipation](https://mlsanity.com/paper/2308.04770/) (2023)
- [Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection](https://mlsanity.com/paper/2308.11327/) (2023)
- [Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm](https://mlsanity.com/paper/2310.13019/) (2023)
- [Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection](https://mlsanity.com/paper/2412.04915/) (2024)
- [Improving Token-based Object Detection with Video](https://mlsanity.com/paper/2506.22562/) (2025)

## Abstract (arXiv)

This paper presents the novel idea of generating object proposals by leveraging temporal information for video object detection. The feature aggregation in modern region-based video object detectors heavily relies on learned proposals generated from a single-frame RPN. This imminently introduces additional components like NMS and produces unreliable proposals on low-quality frames. To tackle these restrictions, we present SparseVOD, a novel video object detection pipeline that employs Sparse R-CNN to exploit temporal information. In particular, we introduce two modules in the dynamic head of Sparse R-CNN. First, the Temporal Feature Extraction module based on the Temporal RoI Align operation is added to extract the RoI proposal features. Second, motivated by sequence-level semantic aggregation, we incorporate the attention-guided Semantic Proposal Feature Aggregation module to enhance object feature representation before detection. The proposed SparseVOD effectively alleviates the overhead of complicated post-processing methods and makes the overall pipeline end-to-end trainable. Extensive experiments show that our method significantly improves the single-frame Sparse RCNN by 8%-9% in mAP. Furthermore, besides achieving state-of-the-art 80.3% mAP on the ImageNet VID dataset with ResNet-50 backbone, our SparseVOD outperforms existing proposal-based methods by a significant margin on increasing IoU thresholds (IoU > 0.5).