mlsanityData to 14 Oct 2026

Few-Shot Video Object Detection

arXiv 2104.14805 ↗First posted 30 Apr 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We introduce Few-Shot Video Object Detection (FSVOD) with three contributions to real-world visual learning challenge in our highly diverse and dynamic world: 1) a large-scale video dataset FSVOD-500 comprising of 500 classes with class-balanced videos in each category for few-shot learning; 2) a novel Tube Proposal Network (TPN) to generate high-quality video tube proposals for aggregating feature representation for the target video object which can be highly dynamic; 3) a strategically improved Temporal Matching Network (TMN+) for matching representative query tube features with better discriminative ability thus achieving higher diversity. Our TPN and TMN+ are jointly and end-to-end trained. Extensive experiments demonstrate that our method produces significantly better detection results on two few-shot video object detection datasets compared to image-based methods and other naive video-based extensions. Codes and datasets are released at urlhttps://github.com/fanq15/FewX.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 138 of its 179 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

138 of 179 references.

References · 138

  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. 2017Mask R-CNNcited by 7,277
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  10. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  11. 2015Fast R-CNNcited by 2,933
  12. 2016Matching Networks for One Shot Learningcited by 2,255
38 more
  1. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  3. 2017Deformable Convolutional Networkscited by 1,488
  4. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  5. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  6. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  8. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  9. 2019When Does Label Smoothing Help?cited by 988
  10. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  11. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  12. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  13. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  14. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 568
  15. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 552
  16. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  17. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 532
  18. 2020Tracking Objects as Pointscited by 483
  19. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  20. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 475
  21. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  22. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 446
  23. 2019Video Object Segmentation using Space-Time Memory Networkscited by 438
  24. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 429
  25. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  26. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  27. 2018Meta-learning with differentiable closed-form solverscited by 397
  28. 2019Video Instance Segmentationcited by 393
  29. 2019Tracking without bells and whistlescited by 382
  30. 2019Learning Discriminative Model Prediction for Trackingcited by 344
  31. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 343
  32. 2018How to train your MAMLcited by 309
  33. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 305
  34. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  35. 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
  36. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  37. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  38. 2016ECO: Efficient Convolution Operators for Trackingcited by 239

50 most cited of 138 All 138 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 0; 2025: 3.

7 papers.

  1. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  2. 2023Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentationcited by 8
  3. 2025Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detectioncited by 6
  4. 2025MOVE: Motion-Guided Few-Shot Video Object Segmentationcited by 6
  5. 2022Multi-Modal Few-Shot Temporal Action Detectioncited by 3
  6. 2025Few-Shot Learning in Video and 3D Object Detection: A Surveycited by 2
  7. 2023Holistic Prototype Attention Network for Few-Shot VOScited by 1