Papers › NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene...

NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment

5 Nov 2023Semantic Web 2023 11archive 2025-07-28

M. Jaleed Khan, John Breslin, Edward Curry

Neuro-symbolic hybrid approaches are inevitable for seamless high-level understanding and reasoning about visual scenes. Scene Graph Generation (SGG) is a symbolic image representation approach based on deep neural networks (DNN) that involves predicting objects, their attributes, and pairwise visual relationships in images to create scene graphs, which are utilized in downstream visual reasoning. The crowdsourced training datasets used in SGG are highly imbalanced, which results in biased SGG results. The vast number of possible triplets makes it challenging to collect sufficient training samples for every visual concept or relationship. To address these challenges, we propose augmenting the typical data-driven SGG approach with common sense knowledge to enhance the expressiveness and autonomy of visual understanding and reasoning. We present a loosely-coupled neuro-symbolic visual understanding and reasoning framework that employs a DNN-based pipeline for object detection and multi-modal pairwise relationship prediction for scene graph generation and leverages common sense knowledge in heterogenous knowledge graphs to enrich scene graphs for improved downstream reasoning. A comprehensive evaluation is performed on multiple standard datasets, including Visual Genome and Microsoft COCO, in which the proposed approach outperformed the state-of-the-art SGG methods in terms of relationship recall scores, i.e. Recall@K and mean Recall@K, as well as the state-of-the-art scene graph-based image captioning methods in terms of SPICE and CIDEr scores with comparable BLEU, ROGUE and METEOR scores. As a result of enrichment, the qualitative results showed improved expressiveness of scene graphs, resulting in more intuitive and meaningful caption generation using scene graphs. Our results validate the effectiveness of enriching scene graphs with common sense knowledge using heterogeneous knowledge graphs. This work provides a baseline for future research in knowledge-enhanced visual understanding and reasoning.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Caption GenerationCommon Sense ReasoningGraph GenerationImage CaptioningKnowledge GraphsObject DetectionScene Graph DetectionScene Graph GenerationScene UnderstandingVisual Reasoningobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Captioning MS-COCO NeuSyRE BLEU-1 79.1 #1 of 1 Archive leaderboard report
Image Captioning MS-COCO NeuSyRE BLEU-4 37.6 #1 of 1 Archive leaderboard report
Image Captioning MS-COCO NeuSyRE CIDEr 131.4 #1 of 1 Archive leaderboard report
Image Captioning MS-COCO NeuSyRE METEOR 28.5 #1 of 1 Archive leaderboard report
Image Captioning MS-COCO NeuSyRE SPICE 23.8 #1 of 1 Archive leaderboard report
Image Captioning MS-COCO NeuSyRE Test ROGUE-L 57.7 #1 of 1 Archive leaderboard report
Scene Graph Generation MS-COCO NeuSyRE R@100 38.5 #1 of 1 Archive leaderboard report
Scene Graph Generation MS-COCO NeuSyRE R@20 27.9 #1 of 1 Archive leaderboard report
Scene Graph Generation MS-COCO NeuSyRE R@50 36.3 #1 of 1 Archive leaderboard report
Scene Graph Generation MS-COCO NeuSyRE mR@100 12.8 #1 of 1 Archive leaderboard report
Scene Graph Generation MS-COCO NeuSyRE mR@20 9.2 #1 of 1 Archive leaderboard report
Scene Graph Generation MS-COCO NeuSyRE mR@50 11.6 #1 of 1 Archive leaderboard report
Scene Graph Generation Visual Genome NeuSyRE R@100 39.1 #18 of 19 Archive leaderboard report
Scene Graph Generation Visual Genome NeuSyRE mR@100 12.6 #18 of 19 Archive leaderboard report
Scene Graph Generation Visual Genome NeuSyRE mR@50 10.9 #18 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections