mlsanityData to 7 Oct 2026

SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking

arXiv 2409.11235 ↗First posted 17 Sep 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. Currently, the best-performing methods are mainly based on pure appearance matching. Due to the complexity of motion patterns in the large-vocabulary scenarios and unstable classification of the novel objects, the motion and semantics cues are either ignored or applied based on heuristics in the final matching steps by existing methods. In this paper, we present a unified framework SLAck that jointly considers semantics, location, and appearance priors in the early steps of association and learns how to integrate all valuable information through a lightweight spatial and temporal object graph. Our method eliminates complex post-processing heuristics for fusing different cues and boosts the association performance significantly for large-scale open-vocabulary tracking. Without bells and whistles, we outperform previous state-of-the-art methods for novel classes tracking on the open-vocabulary MOT and TAO TETA benchmarks. Our code is available at hrefhttps://github.com/siyuanliii/SLAckgithub.com/siyuanliii/SLAck.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 42 of its 45 references that are in the map. First posted on arXiv 17 Sep 2024.

Builds on

42 of 45 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  9. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  10. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  11. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  12. 2016Simple Online and Realtime Trackingcited by 862
30 more
  1. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  2. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  3. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  4. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
  5. 2019Tracking without bells and whistlescited by 382
  6. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  7. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  8. 2020MOT20: A benchmark for multi object tracking in crowded scenescited by 355
  9. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  10. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  11. 2019Towards Real-Time Multi-Object Trackingcited by 311
  12. 2017Relation Networks for Object Detectioncited by 305
  13. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  14. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  15. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  16. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  17. 2020TAO: A Large-Scale Benchmark for Tracking Any Objectcited by 146
  18. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  19. 2023General Object Foundation Model for Images and Videos at Scalecited by 71
  20. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  21. 2023OVTrack: Open-Vocabulary Multiple Object Trackingcited by 53
  22. 2021Opening up Open-World Trackingcited by 50
  23. 2024Matching Anything by Segmenting Anythingcited by 49
  24. 2022Tracking Every Thing in the Wildcited by 44
  25. 2024NetTrack: Tracking Highly Dynamic Objects with a Netcited by 22
  26. 2023Cascade-DETR: Delving into High-Quality Universal Object Detectioncited by 19
  27. 20211st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Trackingcited by 17
  28. 2023DARTH: Holistic Test-time Adaptation for Multiple Object Trackingcited by 15
  29. 2023COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Trackingcited by 4
  30. 2024AM-SORT: Adaptable Motion Predictor with Historical Trajectory Embedding for Multi-Object Trackingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 1.

7 papers.

  1. 2024Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Trackingcited by 20
  2. 2025OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformercited by 11
  3. 2025Open-World Object Counting in Videoscited by 11
  4. 2024Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphscited by 4
  5. 2025Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Surveycited by 2
  6. 2025Attention to Trajectory: Trajectory-Aware Open-Vocabulary Trackingcited by 1
  7. 2026COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigmcited by 0