Scene Graph Generation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

7 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

11 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 151 papers with code (318 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Unbiased Scene Graph Generation from Biased Training
  27 Feb 2020 6 repositories listed Syntology ran 3 of 6 samples · 3 unverified · 6 pointer-only (licence)
  Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e.
• Learning to Compose Dynamic Tree Structures for Visual Contexts
  5 Dec 2018 6 repositories listed Syntology ran 4 of 14 samples · 10 unverified
  We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A.
• Scene Graph Generation by Iterative Message Passing
  10 Jan 2017 5 repositories listed Syntology ran 3 of 5 samples · 2 unverified · 3 pointer-only (licence)
  In this work, we explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image.
• Structured Sparse R-CNN for Direct Scene Graph Generation
  21 Jun 2021 4 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  The key to our method is a set of learnable triplet queries and a structured triplet detector which could be jointly optimized from the training set in an end-to-end manner.
• Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
  1 Apr 2021 4 repositories listed
  Scene graph generation is an important visual understanding task with a broad range of vision applications.
• STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery
  13 Jun 2024 3 repositories listed
  This paper constructs a large-scale dataset for SGG in large-size VHR SAI with image sizes ranging from 512 x 768 to 27, 860 x 31, 096 pixels, named STAR (Scene graph generaTion in lArge-size satellite imageRy),…
• 4D Panoptic Scene Graph Generation
  16 May 2024 3 repositories listed Syntology ran 13 of 14 samples · 1 unverified · 10 pointer-only (licence)
  To facilitate research in this new area, we build a richly annotated PSG-4D dataset consisting of 3K RGB-D videos with a total of 1M frames, each of which is labeled with 4D panoptic segmentation masks as well as…
• Panoptic Video Scene Graph Generation
  28 Nov 2023 3 repositories listed Syntology ran 11 of 11 samples · 0 unverified · 3 pointer-only (licence)
  PVSG relates to the existing video scene graph generation (VidSGG) problem, which focuses on temporal interactions between humans and objects grounded with bounding boxes in videos.
• RLIPv2: Fast Scaling of Relational Language-Image Pre-training
  18 Aug 2023 3 repositories listed Syntology ran 22 of 30 samples · 8 unverified
  In this paper, we propose RLIPv2, a fast converging model that enables the scaling of relational pre-training to large-scale pseudo-labelled scene graph data.
• SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation
  30 Nov 2022 3 repositories listed
  However, it is difficult to draw a proper scene graph for image retrieval, image generation, and multi-modal applications.
• Knowledge-Embedded Routing Network for Scene Graph Generation
  8 Mar 2019 3 repositories listed Syntology ran 3 of 8 samples · 5 unverified
  More specifically, we show that the statistical correlations between objects appearing in images and their relationships, can be explicitly represented by a structured knowledge graph, and a routing mechanism is learned…
• Graphical Contrastive Losses for Scene Graph Parsing
  7 Mar 2019 3 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  The first, Entity Instance Confusion, occurs when the model confuses multiple instances of the same type of entity (e.
• LinkNet: Relational Embedding for Scene Graph
  15 Nov 2018 3 repositories listed
  In this paper, we present a method that improves scene graph generation by explicitly modeling inter-dependency among the entire object instances.
• Graph R-CNN for Scene Graph Generation
  1 Aug 2018 3 repositories listed
  We propose a novel scene graph generation model called Graph R-CNN, that is both effective and efficient at detecting objects and their relations in images.
• Pixels to Graphs by Associative Embedding
  22 Jun 2017 3 repositories listed
  Graphs are a useful abstraction of image content.
• Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection
  30 Jun 2023 2 repositories listed
  For further understanding of comics, an automated approach is needed to link text in comics to characters speaking the words.
• Fine-Grained Scene Graph Generation with Data Transfer
  22 Mar 2022 2 repositories listed
  Scene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images.
• Spatial-Temporal Transformer for Dynamic Scene Graph Generation
  26 Jul 2021 2 repositories listed Syntology ran 7 of 14 samples · 7 unverified · 5 pointer-only (licence)
  Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic…
• SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
  27 Mar 2021 2 repositories listed
  Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks.
• Learning and Reasoning with the Graph Structure Representation in Robotic Surgery
  7 Jul 2020 2 repositories listed Syntology ran 1 of 8 samples · 7 unverified · 8 pointer-only (licence)
  Learning to infer graph representations and performing spatial reasoning in a complex surgical environment can play a vital role in surgical scene understanding in robotic surgery.
• Learning Visual Commonsense for Robust Scene Graph Generation
  17 Jun 2020 2 repositories listed Syntology ran 3 of 11 samples · 8 unverified
  Scene graph generation models understand the scene through object and predicate recognition, but are prone to mistakes due to the challenges of perception in the wild.
• Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoning
  16 Jul 2018 2 repositories listed
  Recent approaches on visual scene understanding attempt to build a scene graph -- a computational representation of objects and their pairwise relationships.
• Open World Scene Graph Generation using Vision Language Models
  9 Jun 2025 1 repository listed
  Scene-Graph Generation (SGG) seeks to recognize objects in an image and distill their salient pairwise relationships.
• EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding
  30 May 2025 1 repository listed
  This new dataset and benchmark set a new foundation for OR perception, offering a rich, multimodal resource for next-generation clinical perception.
• LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study
  26 May 2025 1 repository listed
  In this work, we introduce Text-Scene Graph (TSG) Bench, a benchmark designed to systematically assess LLMs' ability to (1) understand scene graphs and (2) generate them from textual narratives.
• SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval
  21 May 2025 1 repository listed
  Despite the dominance of convolutional and transformer-based architectures in image-to-image retrieval, these models are prone to biases arising from low-level visual features, such as color.
• DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation
  18 Mar 2025 1 repository listed
  This embedding then serves as the input to task-specific heads for object classification, scene graph generation, etc.
• MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments
  4 Mar 2025 1 repository listed
  Operating rooms (ORs) are complex, high-stakes environments requiring precise understanding of interactions among medical staff, tools, and equipment for enhancing surgical assistance, situational awareness, and patient…
• KnowZRel: Common Sense Knowledge-based Zero-Shot Relationship Retrieval for Generalised Scene Graph Generation
  21 Feb 2025 1 repository listed
  The generalisability of Scene Graph Generation (SGG) methods is crucial for reliable reasoning and real-world applicability.
• Weakly Supervised Video Scene Graph Generation via Natural Language Supervision
  21 Feb 2025 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Existing Video Scene Graph Generation (VidSGG) studies are trained in a fully supervised manner, which requires all frames in a video to be annotated, thereby incurring high annotation cost compared to Image Scene Graph…

Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.