# Tri-modal Confluence with Temporal Dynamics for Scene Graph Generation in Operating Rooms

arXiv: https://arxiv.org/abs/2404.09231 · HTML: https://mlsanity.com/paper/2404.09231/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 14 Apr 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions](https://mlsanity.com/paper/2004.03967/) (2020)
- [PLA: Language-Driven Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2211.16312/) (2022)
- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection](https://mlsanity.com/paper/2203.13954/) (2022)
- [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022)
- [Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer](https://mlsanity.com/paper/2103.09712/) (2021)
- [Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning](https://mlsanity.com/paper/2208.08165/) (2022)
- [4D-OR: Semantic Scene Graphs for OR Domain Modeling](https://mlsanity.com/paper/2203.11937/) (2022)
- [VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud](https://mlsanity.com/paper/2303.14408/) (2023)
- [Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection](https://mlsanity.com/paper/2302.00268/) (2023)
- [LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms](https://mlsanity.com/paper/2303.13293/) (2023)
- [FUN-SIS: a Fully UNsupervised approach for Surgical Instrument Segmentation](https://mlsanity.com/paper/2202.08141/) (2022)

## Built on by (most cited first, 6 of 6)

- [Generalizable Operating Room Expert with Multimodal Enhancement](https://mlsanity.com/paper/2508.08199/) (2025)
- [Specialized Foundation Models for Intelligent Operating Rooms](https://mlsanity.com/paper/2505.12890/) (2025)
- [Decoding the Surgical Scene: A Scoping Review of Scene Graphs in Surgery](https://mlsanity.com/paper/2509.20941/) (2025)
- [PanORama: Multiview Consistent Panoptic Segmentation in Operating Rooms](https://mlsanity.com/paper/2603.19920/) (2026)
- [NoPA: Non-Parametric Online 3D Scene Graph Generation](https://mlsanity.com/paper/2607.00529/) (2026)
- [SAGE-OR: Semi-supervised Adaptive Scene Graph Generation for Operating Rooms](https://mlsanity.com/paper/2608.15336/) (2026)

## Abstract (arXiv)

A comprehensive understanding of surgical scenes allows for monitoring of the surgical process, reducing the occurrence of accidents and enhancing efficiency for medical professionals. Semantic modeling within operating rooms, as a scene graph generation (SGG) task, is challenging since it involves consecutive recognition of subtle surgical actions over prolonged periods. To address this challenge, we propose a Tri-modal (i.e., images, point clouds, and language) confluence with Temporal dynamics framework, termed TriTemp-OR. Diverging from previous approaches that integrated temporal information via memory graphs, our method embraces two advantages: 1) we directly exploit bi-modal temporal information from the video streaming for hierarchical feature interaction, and 2) the prior knowledge from Large Language Models (LLMs) is embedded to alleviate the class-imbalance problem in the operating theatre. Specifically, our model performs temporal interactions across 2D frames and 3D point clouds, including a scale-adaptive multi-view temporal interaction (ViewTemp) and a geometric-temporal point aggregation (PointTemp). Furthermore, we transfer knowledge from the biomedical LLM, LLaVA-Med, to deepen the comprehension of intraoperative relations. The proposed TriTemp-OR enables the aggregation of tri-modal features through relation-aware unification to predict relations so as to generate scene graphs. Experimental results on the 4D-OR benchmark demonstrate the superior performance of our model for long-term OR streaming.