mlsanityData to 7 Oct 2026

Object Detection in Video with Spatiotemporal Sampling Networks

arXiv 1803.05549 ↗First posted 15 Mar 2018cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos. Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent frames. This naturally renders the approach robust to occlusion or motion blur in individual frames. Our framework does not require additional supervision, as it optimizes sampling locations directly with respect to object detection performance. Our STSN outperforms the state-of-the-art on the ImageNet VID dataset and compared to prior video object detection methods it uses a simpler design, and does not require optical flow data for training.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 19; 2023: 6; 2024: 4; 2025: 4; 2026: 2.

57 papers.

Sort:

By area:

  1. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  2. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  3. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 120
  4. 2021Crossover Learning for Fast Online Video Instance Segmentationcited by 83
  5. 2022TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformerscited by 78
  6. 2021Video Instance Segmentation with a Propose-Reduce Paradigmcited by 74
  7. 2021DG-Font: Deformable Generative Networks for Unsupervised Font Generationcited by 70
  8. 2022MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detectioncited by 65
  9. 2022Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Networkcited by 57
  10. 2021Temporal RoI Align for Video Object Recognitioncited by 44
  11. 2021Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentationcited by 42
  12. 2021End-to-End Video Object Detection with Spatial-Temporal Transformerscited by 40
38 more
  1. 2022Monocular 3D Object Detection with Depth from Motioncited by 38
  2. 2021TF-Blender: Temporal Feature Blender for Video Object Detectioncited by 37
  3. 2022TubeFormer-DeepLab: Video Mask Transformercited by 35
  4. 2021From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detectioncited by 24
  5. 2021D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videoscited by 20
  6. 2021FDAN: Flow-guided Deformable Alignment Network for Video Super-Resolutioncited by 19
  7. 2021Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmarkcited by 17
  8. 2023Real-Time Idling Vehicles Detection using Combined Audio-Visual Deep Learningcited by 17
  9. 2021Multi-frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial-Temporal Feature Transformationcited by 15
  10. 2024Color Shift Estimation-and-Correction for Image Enhancementcited by 14
  11. 2021Improving Video Instance Segmentation via Temporal Pyramid Routingcited by 13
  12. 2022STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentationcited by 13
  13. 2024MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detectioncited by 13
  14. 2022QueryProp: Object Query Propagation for High-Performance Video Object Detectioncited by 12
  15. 2022LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perceptioncited by 11
  16. 2021Boggart: Towards General-Purpose Acceleration of Retrospective Video Analyticscited by 10
  17. 2022A recurrent CNN for online object detection on raw radar framescited by 9
  18. 2022Recent Advances in Embedding Methods for Multi-Object Tracking: A Surveycited by 8
  19. 2022Instance As Identity: A Generic Online Paradigm for Video Instance Segmentationcited by 8
  20. 2021Few-Shot Video Object Detectioncited by 7
  21. 2023Objects do not disappear: Video object detection by single-frame object location anticipationcited by 7
  22. 2022BoxMask: Revisiting Bounding Box Supervision for Video Object Detectioncited by 6
  23. 2021Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregationcited by 5
  24. 2021Application of Ghost-DeblurGAN to Fiducial Marker Detectioncited by 4
  25. 2022Flow Guidance Deformable Compensation Network for Video Frame Interpolationcited by 4
  26. 2023Identity-Consistent Aggregation for Video Object Detectioncited by 3
  27. 2021Learning to Track Object Position through Occlusioncited by 2
  28. 2021FFAVOD: Feature Fusion Architecture for Video Object Detectioncited by 2
  29. 2022Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baselinecited by 2
  30. 2022DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generationcited by 2
  31. 2021When Few-Shot Learning Meets Video Object Detectioncited by 1
  32. 2023High Dynamic Range Imaging of Dynamic Scenes with Saturation Compensation but without Explicit Motion Compensationcited by 1
  33. 2023Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detectioncited by 1
  34. 2024Spb3DTracker: A Robust LiDAR-Based Person Tracker for Noisy Environmentcited by 1
  35. 2025Gaseous Object Detectioncited by 1
  36. 2025TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detectioncited by 1
  37. 2022Human Instance Segmentation and Tracking via Data Association and Single-stage Detectorcited by 0
  38. 2022Representation Recycling for Streaming Video Analysiscited by 0

50 most cited of 57 All 57 (JSON)