mlsanityData to 7 Oct 2026

Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation

arXiv 2006.07585 ↗First posted 13 Jun 2020cs.CV cs.LG eess.IVcited by 22

Not on the map. Why?

Abstract (arXiv)

Despite the huge progress in scene graph generation in recent years, its long-tail distribution in object relationships remains a challenging and pestering issue. Existing methods largely rely on either external knowledge or statistical bias information to alleviate this problem. In this paper, we tackle this issue from another two aspects: (1) scene-object interaction aiming at learning specific knowledge from a scene via an additive attention mechanism; and (2) long-tail knowledge transfer which tries to transfer the rich knowledge learned from the head into the tail. Extensive experiments on the benchmark dataset Visual Genome on three tasks demonstrate that our method outperforms current state-of-the-art competitors.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 3; 2024: 3; 2025: 1; 2026: 8.

22 papers.

Sort:

By area:

  1. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  2. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  3. 2021Recovering the Unbiased Scene Graphs from the Biased Onescited by 71
  4. 2022Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuningcited by 54
  5. 2021Exploiting Scene Graphs for Human-Object Interaction Detectioncited by 22
  6. 2023Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detectioncited by 15
  7. 2024HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generationcited by 14
  8. 2021Semantic Compositional Learning for Low-shot Scene Graph Generationcited by 12
  9. 2025VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural Heritagecited by 7
  10. 2023Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolboxcited by 6
  11. 2024Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learningcited by 6
  12. 2024ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagerycited by 3
10 more
  1. 2023RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generationcited by 2
  2. 2022Unbiased Scene Graph Generation using Predicate Similaritiescited by 1
  3. 2026HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilitiescited by 1
  4. 2026Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matchingcited by 0
  5. 2026CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generationcited by 0
  6. 2026ReLIC-SGG: Relation Lattice Completion for Open-Vocabulary Scene Graph Generationcited by 0
  7. 2026ScriptHOI: Learning Scripted State Transitions for Open-Vocabulary Human-Object Interaction Detectioncited by 0
  8. 2026RelWitness: Open-Vocabulary 3D Scene Graph Generation with Visual-Geometric Relation Witnessescited by 0
  9. 2026Resolving Ambiguity in Composed Image Retrieval via Calibrated Interactioncited by 0
  10. 2026Show, Don't Ask: Generative Visual Disambiguation for Composed Image Retrieval with Turn-Valid Coveragecited by 0