Research map / Detection and segmentation / Open-set and few-shot detection
Visual relationship and scene graph detection
Detect object relations and generate scene graphs with context and reinforcement learning.
63 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Open-set and few-shot detection, keyword cluster “human · interaction · hoi”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
14 papers in 2023–24 and 5 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 2.4% to 0.9%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Do Computational Models Differ Systematically From Human Object Perception? (CVPR 2016 · 35 citations)
- 2017 · Visual Translation Embedding Network for Visual Relation Detection (CVPR 2017 · 584 citations)
- 2018 · Emotional Attention: A Study of Image Sentiment and Visual Attention (CVPR 2018 · 164 citations)
- 2019 · Learning Loss for Active Learning (CVPR 2019 · 723 citations)
- 2020 · Robust Learning Through Cross-Task Consistency (CVPR 2020 · 125 citations)
- 2021 · Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks (AAAI 2021 · 61 citations)
- 2022 · Deep Hierarchical Semantic Segmentation (CVPR 2022 · 184 citations)
- 2023 · UniHCP: A Unified Model for Human-Centric Perceptions (CVPR 2023 · 75 citations)
- 2024 · Improving Audio-Visual Segmentation with Bidirectional Generation (AAAI 2024 · 32 citations)
- 2025 · Perceptual Inductive Bias Is What You Need Before Contrastive Learning (CVPR 2025 · 2 citations)
- 2026 · Temporal Slowness in Central Vision Drives Semantic Object Learning (ICLR 2026 · 0 citations)
Earliest papers here
- Do Computational Models Differ Systematically From Human Object Perception? (CVPR 2016 · 35 citations)
- Visual Translation Embedding Network for Visual Relation Detection (CVPR 2017 · 584 citations)
- Deep Learning Human Mind for Automated Visual Classification (CVPR 2017 · 295 citations)
What has been tried
60 papers here report 635 measured changes (a component added, removed or swapped, compared with a baseline): helped 75%, no clear effect 7%, hurt 14%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add audio features and the audio-visual fused module | AVSBench S4, MS3 from scratch, and MS3 pretrained on Single-Source · mIoU | 80.16 -> 80.82; 51.85 -> 54.35; 55.63 -> 56.51 | Helped | Improving Audio-Visual Segmentation with Bidirectional Generation (AAAI 2024 · 32 citations) |
| Add positional adapter (PA) | IG ZeroIA · CC | 0.3652 -> 0.4013 | Helped | Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition (CVPR 2024 · 20 citations) |
| Add head keypoints to face-based soft gaze attention | GazeFollow test · Min. Dist. | 0.077 -> 0.068 | Helped | Gaze Target Detection by Merging Human Attention and Activity Cues (AAAI 2024 · 6 citations) |
| Average all 9 query representations instead of using only the last query | SIFR · SA-SOR | 0.5623 -> 0.5807 | Helped | Advancing Saliency Ranking with Human Fixations: Dataset Models and Benchmarks (CVPR 2024 · 5 citations) |
| Add translation estimation to distance estimation | Brain-Score public benchmarks · neural mean | 0.399 -> 0.407 | No clear effect | Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations (ICLR 2025 · 1 citation) |
| Combine Ours features with DINO features | KITTI Eigen split · SILog | 6.991 -> 6.796 | Helped | Object Concepts Emerge from Motion (NeurIPS 2025 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 8 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- ImageNet-1k · 2 of 8 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 19 papers; from OpenAlex and the papers' affiliations).
- The University of Sydney · 2 papers
- Massachusetts Institute of Technology · 2 papers
Use it
Download BibTeX of 30 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Unsupervised object and part discovery (114 papers)
- Human-object interaction detection (66 papers)
- Hand-object and articulated interaction (52 papers)
Elsewhere in the topic
- Object-level representation learning (219 papers)
- Interactive and referring segmentation (161 papers)
- Open-set and unknown object detection (160 papers)
- Amodal and open-world instance segmentation (137 papers)
- Industrial anomaly detection (117 papers)
- Domain-adaptive object detection (103 papers)
- Open-vocabulary object detection (96 papers)
- Open-vocabulary semantic segmentation (93 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).