# Progressive Sparse Local Attention for Video object detection

arXiv: https://arxiv.org/abs/1903.09126 · HTML: https://mlsanity.com/paper/1903.09126/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2019.

## Built on by (most cited first, 30 of 30)

- [TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2201.05047/) (2022)
- [Temporal RoI Align for Video Object Recognition](https://mlsanity.com/paper/2109.03495/) (2021)
- [End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2105.10920/) (2021)
- [From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection](https://mlsanity.com/paper/2107.14391/) (2021)
- [PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection](https://mlsanity.com/paper/2209.02242/) (2022)
- [MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection](https://mlsanity.com/paper/2212.00442/) (2022)
- [MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection](https://mlsanity.com/paper/2401.09923/) (2024)
- [QueryProp: Object Query Propagation for High-Performance Video Object Detection](https://mlsanity.com/paper/2207.10959/) (2022)
- [Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning](https://mlsanity.com/paper/2303.00404/) (2023)
- [Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics](https://mlsanity.com/paper/2106.15315/) (2021)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection](https://mlsanity.com/paper/2210.02368/) (2022)
- [Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition](https://mlsanity.com/paper/2404.11903/) (2024)
- [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)
- [DSLA: Dynamic smooth label assignment for efficient anchor-free object detection](https://mlsanity.com/paper/2208.00817/) (2022)
- [Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization](https://mlsanity.com/paper/2208.01587/) (2022)
- [Temporal Early Exits for Efficient Video Object Detection](https://mlsanity.com/paper/2106.11208/) (2021)
- [Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks](https://mlsanity.com/paper/2208.09195/) (2022)
- [Identity-Consistent Aggregation for Video Object Detection](https://mlsanity.com/paper/2308.07737/) (2023)
- [HoughNet: Integrating near and long-range evidence for visual detection](https://mlsanity.com/paper/2104.06773/) (2021)
- [Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline](https://mlsanity.com/paper/2206.11459/) (2022)
- [Efficient Multi-Purpose Cross-Attention Based Image Alignment Block for Edge Devices](https://mlsanity.com/paper/2206.00291/) (2022)
- [Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection](https://mlsanity.com/paper/2308.11327/) (2023)
- [Context Enhanced Transformer for Single Image Object Detection](https://mlsanity.com/paper/2312.14492/) (2023)
- [Unifying Tracking and Image-Video Object Detection](https://mlsanity.com/paper/2211.11077/) (2022)
- [TDViT: Temporal Dilated Video Transformer for Dense Video Tasks](https://mlsanity.com/paper/2402.09257/) (2024)
- [A Survey on Efficiency Optimization Techniques for DNN-based Video Analytics: Process Systems, Algorithms, and Applications](https://mlsanity.com/paper/2507.15628/) (2025)
- [Learn Temporal Consistency For Robust Satellite Video Detector](https://mlsanity.com/paper/2606.15112/) (2026)
- [Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection](https://mlsanity.com/paper/2609.34142/) (2026)

## Abstract (arXiv)

Transferring image-based object detectors to the domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between accuracy and efficiency. However, introducing an extra model to estimate optical flow can significantly increase the overall model size. The gap between optical flow and high-level features can also hinder it from establishing spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense Feature Transforming (DenseFT) are proposed to model temporal appearance and enrich feature representation respectively in a novel video object detection framework. Experiments on ImageNet VID show that our method achieves the best accuracy compared to existing methods with smaller model size and acceptable runtime speed.