mlsanityData to 7 Oct 2026

What Can Help Pedestrian Detection?

arXiv 1705.02757 ↗First posted 8 May 2017cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods. However, there is still a lack of studies on whether and how CNN-based pedestrian detectors can benefit from these extra features. The first contribution of this paper is exploring this issue by aggregating extra features into CNN-based pedestrian detection framework. Through extensive experiments, we evaluate the effects of different kinds of extra features quantitatively. Moreover, we propose a novel network architecture, namely HyperLearner, to jointly learn pedestrian detection as well as the given extra feature. By multi-task training, HyperLearner is able to utilize the information of given features and improve detection performance without extra inputs in inference. The experimental results on multiple pedestrian benchmarks validate the effectiveness of the proposed HyperLearner.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 6; 2023: 6; 2024: 3; 2025: 3.

26 papers.

Sort:

By area:

  1. 2022Weakly Aligned Feature Fusion for Multimodal Object Detectioncited by 26
  2. 2021Multi-Source Domain Adaptation for Object Detectioncited by 21
  3. 2024LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restorationcited by 18
  4. 2023MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimizationcited by 14
  5. 2024Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenescited by 13
  6. 2023Cross-Modality Proposal-guided Feature Mining for Unregistered RGB-Thermal Pedestrian Detectioncited by 12
  7. 2022Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyondcited by 8
  8. 2023GeNIe: Generative Hard Negative Images Through Diffusioncited by 8
  9. 2021NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detectioncited by 7
  10. 2021Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoUcited by 7
  11. 2022Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimationcited by 5
  12. 2022Feature Calibration Network for Occluded Pedestrian Detectioncited by 4
14 more
  1. 2023HoughLaneNet: Lane Detection with Deep Hough Transform and Dynamic Convolutioncited by 4
  2. 2021A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasetscited by 3
  3. 2023End-to-end Rain Streak Removal with RAW Imagescited by 3
  4. 2025Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attentioncited by 3
  5. 2021Beyond Classification: Knowledge Distillation using Multi-Object Impressionscited by 2
  6. 2021Pedestrian Detection by Exemplar-Guided Contrastive Learningcited by 2
  7. 2022The Impact of Partial Occlusion on Pedestrian Detectabilitycited by 2
  8. 2024Data Augmentation in Human-Centric Visioncited by 2
  9. 2025Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detectioncited by 1
  10. 2021Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K Videos using a Joint Detection-and-Tracking Approachcited by 0
  11. 2021P2P-Loc: Point to Point Tiny Person Localizationcited by 0
  12. 2022CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detectioncited by 0
  13. 2023t-RAIN: Robust generalization under weather-aliasing label shift attackscited by 0
  14. 2025Learning 3D Texture-Aware Representations for Parsing Diverse Human Clothing and Body Partscited by 0