REVIEW 10 cited by
Object Detection in 20 Years: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years. Over the past two decades, we have seen a rapid technological evolution of object detection and its profound impact on the entire computer vision field. If we consider today's object detection technique as a revolution driven by deep learning, then back in the 1990s, we would see the ingenious thinking and long-term perspective design of early computer vision. This paper extensively reviews this fast-moving research field in the light of technical evolution, spanning over a quarter-century's time (from the 1990s to 2022). A number of topics have been covered in this paper, including the milestone detectors in history, detection datasets, metrics, fundamental building blocks of the detection system, speed-up techniques, and the recent state-of-the-art detection methods.
Forward citations
Cited by 10 Pith papers
-
Unsupervised Detection of Entry and Exit Regions from Vehicle Trajectories for Camera-Agnostic Turning Movement Counts
Clustering start and end points of vehicle trajectories yields persistent entry/exit polygons that classify turning movements at ~3% median error across 25 uncalibrated cameras.
-
OpenGuide: Assistive Object Retrieval in Indoor Spaces for Individuals with Visual Impairments
OpenGuide combines vision-language value maps, frontier exploration, and POMDP planning to locate multiple objects in unfamiliar indoor spaces, reaching about 55% success in simulation and 54% in real-world trials.
-
Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World
A blue bear-logo T-shirt used as a data-poisoning trigger can erase people from YOLO, CenterNet, and even Faster R-CNN detectors in real video with near-100% success and no drop in clean accuracy.
-
VISA: Retrieval Augmented Generation with Visual Source Attribution
VISA makes RAG output point to the exact bounding box in a document screenshot that supports the answer, and fine-tuned VLMs improve box accuracy from 1.5% to 54.2% on the new Wiki-VISA benchmark.
-
Imbalance Problems in Object Detection: A Review
A taxonomy and critical review organizing eight object-detection imbalance problems under class, scale, spatial, and objective imbalance.
-
Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides
A deep learning pipeline can grade hemosiderin-laden macrophages in equine lung cytology slides at human-expert-level concordance, with whole-slide scoring in under two minutes.
-
Deep Learning-based Multi Project InP Wafer Simulation for Unsupervised Surface Defect Detection
A U-Net trained on CAD layouts and flawed wafer photos can generate defect-free synthetic wafer images that serve as a template for automated defect detection in InP multi-project wafer manufacturing.
-
Sidewalk Hazard Detection Using Variational Autoencoder and One-Class SVM
A VAE plus one-class SVM pipeline detects hazardous sidewalk anomalies from RGB camera frames, reporting 91.4% accuracy on a new sidewalk dataset.
-
Object Recognition Datasets and Challenges: A Review
A review paper that compiles statistics and descriptions of over 160 object recognition datasets, their associated challenges, and evaluation metrics.
-
Adaptive Object Detection with ESRGAN-Enhanced Resolution & Faster R-CNN
The paper applies the known ESRGAN super-resolution step before Faster R-CNN detection and asserts, without supporting evidence, that this improves detection accuracy.
Discussion (0). Continue with ORCID to comment.