mlsanityData to 7 Oct 2026

BoxMask: Revisiting Bounding Box Supervision for Video Object Detection

arXiv 2210.06008 ↗First posted 12 Oct 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We present a new, simple yet effective approach to uplift video object detection. We observe that prior works operate on instance-level feature aggregation that imminently neglects the refined pixel-level representation, resulting in confusion among objects sharing similar appearance or motion characteristics. To address this limitation, we propose BoxMask, which effectively learns discriminative representations by incorporating class-aware pixel-level information. We simply consider bounding box-level annotations as a coarse mask for each object to supervise our method. The proposed module can be effortlessly integrated into any region-based detector to boost detection. Extensive experiments on ImageNet VID and EPIC KITCHENS datasets demonstrate consistent and significant improvement when we plug our BoxMask module into numerous recent state-of-the-art methods.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 53 of its 68 references that are in the map. First posted on arXiv 12 Oct 2022.

Builds on

53 of 68 references.

References · 53

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2017Mask R-CNNcited by 7,259
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  10. 2015Fast R-CNNcited by 2,930
  11. 2018YOLOv3: An Incremental Improvementcited by 2,652
  12. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
38 more
  1. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  5. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  6. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  7. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  8. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  9. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  10. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  11. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  12. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  13. 2016Deep Feature Flow for Video Recognitioncited by 186
  14. 2017Flow-Guided Feature Aggregation for Video Object Detectioncited by 177
  15. 2018Acquisition of Localization Confidence for Accurate Object Detectioncited by 174
  16. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 150
  17. 2017Detect to Track and Track to Detectcited by 131
  18. 2020Memory Enhanced Global-Local Aggregation for Video Object Detectioncited by 128
  19. 2021You Only Look One-level Featurecited by 116
  20. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
  21. 2019Rethinking Classification and Localization for Object Detectioncited by 98
  22. 2019Sequence Level Semantics Aggregation for Video Object Detectioncited by 87
  23. 2020Revisiting the Sibling Head in Object Detectorcited by 82
  24. 2022TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformerscited by 78
  25. 2019Relation Distillation Networks for Video Object Detectioncited by 77
  26. 2016Seq-NMS for Video Object Detectioncited by 68
  27. 2016T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videoscited by 67
  28. 2017Towards High Performance Video Object Detectioncited by 60
  29. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  30. 2018Object Detection in Video with Spatiotemporal Sampling Networkscited by 57
  31. 2019AugFPN: Improving Multi-scale Feature Learning for Object Detectioncited by 54
  32. 2021Temporal RoI Align for Video Object Recognitioncited by 44
  33. 2017Video Object Detection with an Aligned Spatial-Temporal Memorycited by 41
  34. 2016Object Detection from Video Tubelets with Convolutional Neural Networkscited by 40
  35. 2021TF-Blender: Temporal Feature Blender for Video Object Detectioncited by 37
  36. 2019Progressive Sparse Local Attention for Video object detectioncited by 30
  37. 2018Revisiting RCNN: On Awakening the Classification Power of Faster RCNNcited by 28
  38. 2018Optimizing Video Object Detection via a Scale-Time Latticecited by 25

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 1; 2025: 1.

6 papers.

  1. 2023Object Detection with Transformers: A Reviewcited by 22
  2. 2023Objects do not disappear: Video object detection by single-frame object location anticipationcited by 7
  3. 2023Erasure-based Interaction Network for RGBT Video Object Detection and A Unified Benchmarkcited by 3
  4. 2023Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detectioncited by 1
  5. 2024Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detectioncited by 1
  6. 2025Contrastive Learning through Auxiliary Branch for Video Object Detectioncited by 0