mlsanityData to 14 Oct 2026

Using Cross-Domain Detection Loss to Infer Multi-Scale Information for Improved Tiny Head Tracking

arXiv 2505.22677 ↗First posted 14 May 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Head detection and tracking are essential for downstream tasks, but current methods often require large computational budgets, which increase latencies and ties up resources (e.g., processors, memory, and bandwidth). To address this, we propose a framework to enhance tiny head detection and tracking by optimizing the balance between performance and efficiency. Our framework integrates (1) a cross-domain detection loss, (2) a multi-scale module, and (3) a small receptive field detection mechanism. These innovations enhance detection by bridging the gap between large and small detectors, capturing high-frequency details at multiple scales during training, and using filters with small receptive fields to detect tiny heads. Evaluations on the CroHD and CrowdHuman datasets show improved Multiple Object Tracking Accuracy (MOTA) and mean Average Precision (mAP), demonstrating the effectiveness of our approach in crowded scenes.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 50 references that are in the map. First posted on arXiv 14 May 2025.

Builds on

27 of 50 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  6. 2016Pyramid Scene Parsing Networkcited by 2,479
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  8. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  9. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  10. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  12. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
15 more
  1. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  2. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 910
  3. 2016Simple Online and Realtime Trackingcited by 868
  4. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  5. 2018Path Aggregation Network for Instance Segmentationcited by 798
  6. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  7. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 568
  8. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 459
  9. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 409
  10. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 346
  11. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 284
  12. 2019BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUscited by 74
  13. 2021Tracking Pedestrian Heads in Dense Crowdcited by 42
  14. 2018Unveiling the Power of Deep Trackingcited by 41
  15. 2020TinaFace: Strong but Simple Baseline for Face Detectioncited by 31

Built on by

Not cited yet.