Research map

Detection and segmentation: research map

Object detection, segmentation and tracking in images.

4,827 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 5 topics. Within all five venues, its share shrank from 4.8% in 2023–24 to 2.7% in 2025–26 (1,256 → 1,205 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).

Explore Detection and segmentation in the interactive map

Topics

• Open-set and few-shot detection · 1,888 papers
  Object-level representation learning, Open-set and unknown object detection, Interactive and referring segmentation
• CNN features · 1,734 papers
  Context modeling for semantic segmentation, Local features and context in CNNs, Context for hard detection conditions
• 3D detection and driving · 458 papers
  Unified LiDAR 3D detection, Depth-based and label-free 3D detection, 3D objectness and scene segmentation
• Weakly supervised detection and segmentation · 436 papers
  Weakly supervised semantic segmentation, Weakly supervised detection, Weakly supervised object localization
• Tracking · 311 papers
  Foundation-model and correlation-filter tracking, Siamese network tracking, Transformer-based video object tracking

Most cited papers in Detection and segmentation

• Deep Residual Learning for Image Recognition (CVPR 2016 · 228,971 citations)
• You Only Look Once: Unified, Real-Time Object Detection (CVPR 2016 · 51,511 citations)
• Feature Pyramid Networks for Object Detection (CVPR 2017 · 29,987 citations)
• MobileNetV2: Inverted Residuals and Linear Bottlenecks (CVPR 2018 · 26,804 citations)
• Pyramid Scene Parsing Network (CVPR 2017 · 15,903 citations)
• The Cityscapes Dataset for Semantic Urban Scene Understanding (CVPR 2016 · 12,279 citations)
• Learning Deep Features for Discriminative Localization (CVPR 2016 · 11,042 citations)
• Path Aggregation Network for Instance Segmentation (CVPR 2018 · 9,292 citations)
• nuScenes: A Multimodal Dataset for Autonomous Driving (CVPR 2020 · 6,931 citations)
• Scene Parsing Through ADE20K Dataset (CVPR 2017 · 3,305 citations)
• Masked-Attention Mask Transformer for Universal Image Segmentation (CVPR 2022 · 3,259 citations)
• High Performance Visual Tracking With Siamese Region Proposal Network (CVPR 2018 · 3,032 citations)