mlsanityData to 7 Oct 2026

1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking

arXiv 2101.08040 ↗First posted 20 Jan 2021cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

We extend the classical tracking-by-detection paradigm to this tracking-any-object task. Solid detection results are first extracted from TAO dataset. Some state-of-the-art techniques like BAlanced-Group Softmax (BAGSciteli2020overcoming) and DetectoRSciteqiao2020detectors are integrated during detection. Then we learned appearance features to represent any object by training feature learning networks. We ensemble several models for improving detection and feature representation. Simple linking strategies with most similar appearance features and tracklet-level post association module are finally applied to generate final tracking results. Our method is submitted as AOA on the challenge website. Code is available at https://github.com/feiaxyt/WinnerECCV20TAO.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 13 of its 15 references that are in the map. First posted on arXiv 20 Jan 2021.

Builds on

13 of 15 references.

References · 13

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  3. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  4. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 471
  5. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
  6. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 429
  7. 2019Tracking without bells and whistlescited by 382
  8. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  9. 2019A Strong Baseline and Batch Normalization Neck for Deep Person Re-identificationcited by 154
  10. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  11. 2020TAO: A Large-Scale Benchmark for Tracking Any Objectcited by 146
  12. 2017YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Videocited by 109
1 more
  1. 2018Deep Cosine Metric Learning for Person Re-Identificationcited by 73

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 3; 2023: 3; 2024: 6; 2025: 1; 2026: 1.

17 papers.

Sort:

  1. 2022Global Tracking Transformerscited by 110
  2. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  3. 2023OVTrack: Open-Vocabulary Multiple Object Trackingcited by 53
  4. 2021Opening up Open-World Trackingcited by 50
  5. 2024Matching Anything by Segmenting Anythingcited by 49
  6. 2022Tracking Every Thing in the Wildcited by 44
  7. 2024NetTrack: Tracking Highly Dynamic Objects with a Netcited by 22
  8. 2021City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zonescited by 18
  9. 2023Video OWL-ViT: Temporally-consistent open-world localization in videocited by 13
  10. 2023TAO-Amodal: A Benchmark for Tracking Any Object Amodallycited by 7
  11. 2024SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Trackingcited by 7
  12. 2024VOVTrack: Exploring the Potentiality in Videos for Open-Vocabulary Object Trackingcited by 4
5 more
  1. 2024OCTrack: Benchmarking the Open-Corpus Multi-Object Trackingcited by 1
  2. 2021Reliable Multi-Object Tracking in the Presence of Unreliable Detectionscited by 0
  3. 2024The Progression of Transformers from Language to Vision to MOT: A Literature Review on Multi-Object Tracking with Transformerscited by 0
  4. 2025Lattice Boltzmann Model for Learning Real-World Pixel Dynamicitycited by 0
  5. 2026COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigmcited by 0