Papers with Code 아카이브

Scene Graph Generation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 7
보존된 평가 기록: 31

A scene graph is a structured representation of an image, where nodes in a scene graph correspond to object bounding boxes with their object categories, and edges correspond to their pairwise relationships between objects. The task of Scene Graph Generation is to generate a visually-grounded scene graph that most accurately correlates with an image.

Source: Scene Graph Generation by Iterative Message Passing

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/maelic/sgg-benchmark

공식 코드

REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation

https://github.com/maelic/vg_curated

공식 코드

Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation

https://github.com/manga109/public-annotations

공식 코드

Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection

https://github.com/mcg-nju/sportshhi

공식 코드

SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos

https://github.com/mcg-nju/structured-sparse-rcnn

공식 코드

Structured Sparse R-CNN for Direct Scene Graph Generation

https://github.com/mcg-nju/trace

공식 코드

Target Adaptive Context Aggregation for Video Scene Graph Generation

https://github.com/microsoft/scene_graph_benchmark

공식 코드

Image Scene Graph Generation (SGG) Benchmark

https://github.com/milomilo0320/a-semi-automatic-annotation-software-for-scene-graph

공식 코드

GeneAnnotator: A Semi-automatic Annotation Tool for Visual Scene Graph

https://github.com/mlvlab/speaq

공식 코드

Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection

https://github.com/mobarakol/Surgical_SceneGraph_Generation

공식 코드

Learning and Reasoning with the Graph Structure Representation in Robotic Surgery

https://github.com/mods333/energy-based-scene-graph

공식 코드

Energy-Based Learning for Scene Graph Generation

https://github.com/muktilin/nice

공식 코드

The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

https://github.com/myukzzz/eicr

공식 코드

Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation

https://github.com/naver-ai/egtr

공식 코드

EGTR: Extracting Graph from Transformer for Scene Graph Generation

https://github.com/nickhaidos/scenir-icml2025

공식 코드

SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval

https://github.com/paulgay/VGfM

공식 코드

Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoning

https://github.com/pjlallen/s2former-or

공식 코드

S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR

https://github.com/qncsn2016/TR2

공식 코드

Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs

https://github.com/rafa-cxg/PySGG-cxg

공식 코드

Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generation

https://github.com/rajatkoner08/rtn

공식 코드

Relation Transformer Network

https://github.com/rlqja1107/NL-VSGG

공식 코드

Weakly Supervised Video Scene Graph Generation via Natural Language Supervision

https://github.com/rlqja1107/torch-LLM4SGG

공식 코드

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation

https://github.com/rlqja1107/torch-st-sgg

공식 코드

Adaptive Self-training Framework for Fine-grained Scene Graph Generation

https://github.com/robotics-upo/og-sgg

공식 코드

OG-SGG: Ontology-Guided Scene Graph Generation. A Case Study in Transfer Learning for Telepresence Robotics

https://github.com/rohithpeddi/scenesayer

공식 코드

Towards Scene Graph Anticipation

https://github.com/rowanz/neural-motifs

공식 코드

Neural Motifs: Scene Graph Parsing with Global Context

https://github.com/sangminwoo/Local-to-Global-Interaction-Networks-SGG

공식 코드

Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions

https://github.com/sayaknag/unbiasedsgg

공식 코드

Unbiased Scene Graph Generation in Videos

https://github.com/scarecrow0/sgtr

공식 코드

SGTR: End-to-end Scene Graph Generation with Transformer

https://github.com/seung-b/fl-psg

공식 코드

Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph Generation

https://github.com/shanshuo/ml-mwn

공식 코드

Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation

https://github.com/shengyu-feng/dsg-detr

공식 코드

Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs

https://github.com/shikorab/SceneGraph

공식 코드

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

https://github.com/shtuplus/pix2grp_cvpr2024

공식 코드

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

https://github.com/siml3/hl-net

공식 코드

HL-Net: Heterophily Learning Network for Scene Graph Generation

https://github.com/siml3/ru-net

공식 코드

RU-Net: Regularized Unrolling Network for Scene Graph Generation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.