Visual Relationship Detection

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 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

5 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 37 papers with code (82 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.

• Exploring Long Tail Visual Relationship Recognition with Large Vocabulary
  25 Mar 2020 3 repositories listed Syntology ran 2 of 5 samples · 3 unverified
  We use these benchmarks to study the performance of several state-of-the-art long-tail models on the LTVRR setup.
• 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.
• Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
  20 Nov 2021 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  Furthermore, background knowledge represented by RWFNs can be used to alleviate the incompleteness of training sets even though the space complexity of RWFNs is much smaller than LTNs (1:27 ratio).
• 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…
• One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks
  21 Nov 2020 2 repositories listed
  Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) reflecting localisation quality, (ii) interpretability and (iii) robustness to the design choices…
• Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image Interpretation
  1 Oct 2019 2 repositories listed
  This requires the detection of visual relationships: triples (subject, relation, object) describing a semantic relation between a subject and an object.
• METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection
  10 May 2025 1 repository listed
  In this paper, we propose Mutual EnhancemenT of Objects and Relationships (METOR), a query-based unified framework to jointly model and mutually enhance object detection and relationship classification in…
• Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
  26 Mar 2024 1 repository listed Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
  Groupwise Query Specialization trains a specialized query by dividing queries and relations into disjoint groups and directing a query in a specific query group solely toward relations in the corresponding relation…
• Video Relationship Detection Using Mixture of Experts
  6 Mar 2024 1 repository listed
  Secondly, classifiers trained by a single, monolithic neural network often lack stability and generalization.
• Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction
  8 Nov 2023 1 repository listed
  We present a novel self-supervised approach for representation learning, particularly for the task of Visual Relationship Detection (VRD).
• STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning
  13 Sep 2023 1 repository listed
  In addition to spatial relations, we also propose 50K visual depictions across 10 temporal relations, consisting of videos depicting event/time-point interactions.
• Unified Visual Relationship Detection with Vision and Language Models
  16 Mar 2023 1 repository listed
  To address this challenge, we propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models (VLMs).
• Distance-Aware Occlusion Detection with Focused Attention
  23 Aug 2022 1 repository listed Syntology ran 0 of 4 samples · 4 unverified
  In this work, (1) we propose a novel three-decoder architecture as the infrastructure for focused attention; 2) we use the generalized intersection box prediction task to effectively guide our model to focus on…
• Neural Message Passing for Visual Relationship Detection
  8 Aug 2022 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 3 pointer-only (licence)
  Visual relationship detection aims to detect the interactions between objects in an image; however, this task suffers from combinatorial explosion due to the variety of objects and interactions.
• PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
  23 May 2022 1 repository listed Syntology ran 3 of 7 samples · 4 unverified
  We show that PEVL enables state-of-the-art performance of detector-free VLP models on position-sensitive tasks such as referring expression comprehension and phrase grounding, and also improves the performance on…
• Image Scene Graph Generation (SGG) Benchmark
  27 Jul 2021 1 repository listed
  There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection.
• Recovering the Unbiased Scene Graphs from the Biased Ones
  5 Jul 2021 1 repository listed
  Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects.
• 2.5D Visual Relationship Detection
  26 Apr 2021 1 repository listed
  To enable progress on this task, we create a new dataset consisting of 220k human-annotated 2.
• RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition
  24 Apr 2021 1 repository listed
  This paper shows that modeling an effective message-passing flow through an attention mechanism can be critical to tackling the compositionality and long-tail challenges in VRR.
• Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship Detection
  1 Jan 2021 1 repository listed
  Scene Graph Generators (SGGs) are models that, given an image, build a directed graph where each edge represents a predicted subject predicate object triplet.
• LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos
  17 Dec 2020 1 repository listed
  Analyzing the interactions between humans and objects from a video includes identification of the relationships between humans and the objects present in the video.
• Visualization of Contributions to Open-Source Projects
  17 Oct 2020 1 repository listed
  We want to analyze visually, to what extend team members and external developers contribute to open-source projects.
• Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations
  10 Sep 2020 1 repository listed
  Visual relationship detection aims to reason over relationships among salient objects in images, which has drawn increasing attention over the past few years.
• Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks
  16 Jun 2020 1 repository listed
  Visual relationship detection is fundamental for holistic image understanding.
• AVR: Attention based Salient Visual Relationship Detection
  16 Mar 2020 1 repository listed
  To address this problem, we propose an attention based model, namely AVR, to achieve salient visual relationships based on both local and global context of the relationships.
• NODIS: Neural Ordinary Differential Scene Understanding
  14 Jan 2020 1 repository listed
  Detected objects, their labels and the discovered relations can be used to construct a scene graph which provides an abstract semantic interpretation of an image.
• Visual Relationship Detection with Relative Location Mining
  2 Nov 2019 1 repository listed
  Visual relationship detection, as a challenging task used to find and distinguish the interactions between object pairs in one image, has received much attention recently.
• Improving Visual Relation Detection using Depth Maps
  2 May 2019 1 repository listed
  We argue that depth maps can additionally provide valuable information on object relations, e.
• Visual Relationship Detection with Language prior and Softmax
  16 Apr 2019 1 repository listed
  Visual relationship detection is an intermediate image understanding task that detects two objects and classifies a predicate that explains the relationship between two objects in an image.
• Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection
  15 Feb 2019 1 repository listed
  Detecting visual relationships, i.

Syntology lines on 8 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.