mlsanityData to 14 Oct 2026

Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline

arXiv 2206.11459 ↗First posted 23 Jun 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

We endeavor on a rarely explored task named Insubstantial Object Detection (IOD), which aims to localize the object with following characteristics: (1) amorphous shape with indistinct boundary; (2) similarity to surroundings; (3) absence in color. Accordingly, it is far more challenging to distinguish insubstantial objects in a single static frame and the collaborative representation of spatial and temporal information is crucial. Thus, we construct an IOD-Video dataset comprised of 600 videos (141,017 frames) covering various distances, sizes, visibility, and scenes captured by different spectral ranges. In addition, we develop a spatio-temporal aggregation framework for IOD, in which different backbones are deployed and a spatio-temporal aggregation loss (STAloss) is elaborately designed to leverage the consistency along the time axis. Experiments conducted on IOD-Video dataset demonstrate that spatio-temporal aggregation can significantly improve the performance of IOD. We hope our work will attract further researches into this valuable yet challenging task. The code will be available at: urlhttps://github.com/CalayZhou/IOD-Video.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 64 of its 91 references that are in the map. First posted on arXiv 23 Jun 2022.

Builds on

64 of 91 references.

References · 64

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  7. 2015Fast R-CNNcited by 2,933
  8. 2019Objects as Pointscited by 1,175
  9. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,143
  10. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  11. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 902
  12. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 856
38 more
  1. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  2. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  3. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 459
  4. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  5. 2017Deep Layer Aggregationcited by 436
  6. 2017Learning Spatio-Temporal Representation with Pseudo-3D Residual Networkscited by 387
  7. 2018Long-Term Feature Banks for Detailed Video Understandingcited by 239
  8. 2016Deep Feature Flow for Video Recognitioncited by 186
  9. 2020TDN: Temporal Difference Networks for Efficient Action Recognitioncited by 183
  10. 2017Flow-Guided Feature Aggregation for Video Object Detectioncited by 177
  11. 2020TEA: Temporal Excitation and Aggregation for Action Recognitioncited by 165
  12. 2019STM: SpatioTemporal and Motion Encoding for Action Recognitioncited by 142
  13. 2017Detect to Track and Track to Detectcited by 131
  14. 2020Memory Enhanced Global-Local Aggregation for Video Object Detectioncited by 128
  15. 2019TEINet: Towards an Efficient Architecture for Video Recognitioncited by 92
  16. 2020Actor-Context-Actor Relation Network for Spatio-Temporal Action Localizationcited by 91
  17. 2020A Comprehensive Study of Deep Video Action Recognitioncited by 88
  18. 2018Actor-Centric Relation Networkcited by 87
  19. 2019Sequence Level Semantics Aggregation for Video Object Detectioncited by 87
  20. 2017Action Tubelet Detector for Spatio-Temporal Action Localizationcited by 77
  21. 2019Relation Distillation Networks for Video Object Detectioncited by 77
  22. 2020MotionSqueeze: Neural Motion Feature Learning for Video Understandingcited by 72
  23. 2016Seq-NMS for Video Object Detectioncited by 68
  24. 2016T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videoscited by 67
  25. 2019More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregationcited by 64
  26. 2017Towards High Performance Video Object Detectioncited by 60
  27. 2018D3D: Distilled 3D Networks for Video Action Recognitioncited by 60
  28. 2015P-CNN: Pose-based CNN Features for Action Recognitioncited by 58
  29. 2018Object Detection in Video with Spatiotemporal Sampling Networkscited by 57
  30. 2020Actions as Moving Pointscited by 55
  31. 2019STEP: Spatio-Temporal Progressive Learning for Video Action Detectioncited by 51
  32. 2017Tube Convolutional Neural Network (T-CNN) for Action Detection in Videoscited by 50
  33. 2020Temporal Interlacing Networkcited by 45
  34. 2020Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognitioncited by 45
  35. 2017Video Object Detection with an Aligned Spatial-Temporal Memorycited by 42
  36. 2021End-to-End Video Object Detection with Spatial-Temporal Transformerscited by 40
  37. 2018Spatio-Temporal Channel Correlation Networks for Action Classificationcited by 38
  38. 2021TF-Blender: Temporal Feature Blender for Video Object Detectioncited by 37

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025M-SpecGene: Generalized Foundation Model for RGBT Multispectral Visioncited by 8
  2. 2025Gaseous Object Detectioncited by 1