paper-with-me

Video scene graph generation

1개 벤치마크 · 논문 23편 · 이 태스크의 논문 보기 →

Benchmarks

ImageNet-VidVRD

결과 1개

Most implemented

Panoptic Video Scene Graph Generation

2023-11-28 · 구현 3개

Papers

SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models

2026-05-13 · Vladislav Makarov, Mark Gizetdinov, Dmitry Yudin arxiv

Scene graph generation provides a compact structured representation for visual perception, but accurate and fast graph prediction from images and videos remains challenging. Recent VLM-based methods can generate scene gr…

Video scene graph generationReinforcement Learning

Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video

2026-04-19 · Chenxing Li, Yiping Duan, Xiaoming Tao arxiv

Video Scene Graph Generation aims to obtain structured semantic representations of objects and their relationships in videos for high-level understanding. However, existing methods still have limitations in handling long…

Video scene graph generationRelation Classification

Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning

2026-03-23 · Minseok Kang, Minhyeok Lee, Minjung Kim, Jungho Lee 외 arxiv

Weakly-supervised video scene graph generation (WS-VSGG) aims to parse video content into structured relational triplets without bounding box annotations and with only sparse temporal labeling, significantly reducing ann…

Video scene graph generation

Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos

2026-02-26 · Ziqi Gao, Jieyu Zhang, Wisdom Oluchi Ikezogwo, Jae Sung Park 외 arxiv

We introduce Synthetic Visual Genome 2 (SVG2), a large-scale panoptic video scene graph dataset. SVG2 contains over 636K videos with 6.6M objects, 52.0M attributes, and 6.7M relations, providing an order-of-magnitude inc…

Video scene graph generationVideo Question AnsweringPanoptic SegmentationSemantic Parsing

Click2Graph: Interactive Panoptic Video Scene Graphs from a Single Click

2025-11-20 · Raphael Ruschel, Hardikkumar Prajapati, Awsafur Rahman, B. S. Manjunath arxiv

State-of-the-art Video Scene Graph Generation (VSGG) systems provide structured visual understanding but operate as closed, feed-forward pipelines with no ability to incorporate human guidance. In contrast, promptable se…

Video scene graph generationRelational ReasoningScene Understanding

UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning

2025-09-07 · Huy Le, Nhat Chung, Tung Kieu, Jingkang Yang 외 arxiv

Video Scene Graph Generation (VidSGG) aims to represent dynamic visual content by detecting objects and modeling their temporal interactions as structured graphs. Prior studies typically target either coarse-grained box-…

Video scene graph generationRepresentation Learning

전체 23편 보기 →