mlsanityData to 7 Oct 2026

CityFlow-NL: Tracking and Retrieval of Vehicles at City Scale by Natural Language Descriptions

arXiv 2101.04741 ↗First posted 12 Jan 2021cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Natural Language (NL) descriptions can be one of the most convenient or the only way to interact with systems built to understand and detect city scale traffic patterns and vehicle-related events. In this paper, we extend the widely adopted CityFlow Benchmark with NL descriptions for vehicle targets and introduce the CityFlow-NL Benchmark. The CityFlow-NL contains more than 5,000 unique and precise NL descriptions of vehicle targets, making it the first multi-target multi-camera tracking with NL descriptions dataset to our knowledge. Moreover, the dataset facilitates research at the intersection of multi-object tracking, retrieval by NL descriptions, and temporal localization of events. In this paper, we focus on two foundational tasks: the Vehicle Retrieval by NL task and the Vehicle Tracking by NL task, which take advantage of the proposed CityFlow-NL benchmark and provide a strong basis for future research on the multi-target multi-camera tracking by NL description task.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 18 of its 21 references that are in the map. First posted on arXiv 12 Jan 2021.

Builds on

18 of 21 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  4. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  5. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
  6. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 897
  7. 2014Show and Tell: A Neural Image Caption Generatorcited by 877
  8. 2017Localizing Moments in Video with Natural Languagecited by 660
  9. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 424
  10. 2019A Fast and Accurate One-Stage Approach to Visual Groundingcited by 194
  11. 2015DenseCap: Fully Convolutional Localization Networks for Dense Captioningcited by 176
  12. 2018MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustmentcited by 145
6 more
  1. 2015Natural Language Object Retrievalcited by 124
  2. 2019CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identificationcited by 119
  3. 2019Learning to Compose and Reason with Language Tree Structures for Visual Groundingcited by 98
  4. 2018Dialog-based Interactive Image Retrievalcited by 84
  5. 2019Real-time Visual Object Tracking with Natural Language Descriptioncited by 26
  6. 2019Siamese Natural Language Tracker: Tracking by Natural Language Descriptions with Siamese Trackerscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 4; 2023: 9; 2024: 2; 2025: 2; 2026: 3.

26 papers.

Sort:

By area:

  1. 2022Multi-View Transformer for 3D Visual Groundingcited by 138
  2. 2021SAT: 2D Semantics Assisted Training for 3D Visual Groundingcited by 124
  3. 2023Vision Language Models in Autonomous Driving: A Survey and Outlookcited by 124
  4. 2023Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Drivingcited by 122
  5. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 65
  6. 2023Visual Programming for Zero-shot Open-Vocabulary 3D Visual Groundingcited by 64
  7. 2021The 5th AI City Challengecited by 28
  8. 2022The 6th AI City Challengecited by 23
  9. 2023The 7th AI City Challengecited by 20
  10. 2023Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Groundingcited by 18
  11. 2024EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Drivingcited by 18
  12. 2023FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval systemcited by 15
14 more
  1. 2021Connecting Language and Vision for Natural Language-Based Vehicle Retrievalcited by 12
  2. 2025Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospectscited by 12
  3. 2023Prospective Role of Foundation Models in Advancing Autonomous Vehiclescited by 7
  4. 2025ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Groundingcited by 5
  5. 2021SBNet: Segmentation-based Network for Natural Language-based Vehicle Searchcited by 3
  6. 2021All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformerscited by 3
  7. 2022OMG: Observe Multiple Granularities for Natural Language-Based Vehicle Retrievalcited by 3
  8. 2023Weakly-Supervised 3D Visual Grounding based on Visual Language Alignmentcited by 3
  9. 2022Symmetric Network with Spatial Relationship Modeling for Natural Language-based Vehicle Retrievalcited by 2
  10. 2021Robust 2D/3D Vehicle Parsing in CVIScited by 1
  11. 2023VQPy: An Object-Oriented Approach to Modern Video Analyticscited by 1
  12. 2026T2I-VeRW: Part-level Fine-grained Perception for Text-to-Image Vehicle Retrievalcited by 0
  13. 2026Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessmentcited by 0
  14. 2026ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Trackingcited by 0