Predicate Classification
10 papers with code • 3 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Predicate Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Visual Genome
ImageCLEF-DA
3RScan
Most implemented papers
SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks.
Fine-Grained Scene Graph Generation with Data Transfer
waxnkw/ietrans-sgg.pytorch
•
•
Scene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images.
1st Place Solution for PSG competition with ECCV'22 SenseHuman Workshop
wangqixun/mfpsg
•
•
Panoptic Scene Graph (PSG) generation aims to generate scene graph representations based on panoptic segmentation instead of rigid bounding boxes.
Visual Distant Supervision for Scene Graph Generation
In this work, we propose visual distant supervision, a novel paradigm of visual relation learning, which can train scene graph models without any human-labeled data.
Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions
sangminwoo/Local-to-Global-Interaction-Networks-SGG
•
•
To quantify how much LOGIN is aware of relational direction, a new diagnostic task called Bidirectional Relationship Classification (BRC) is also proposed.
Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs
Dawn-LX/VidSGG-BIG
•
•
CVPR 2022
To this end, we propose a new classification-then-grounding framework for VidSGG, which can avoid all the three overlooked drawbacks.
Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generation
Scene graph generation is a sophisticated task because there is no specific recognition pattern (e. g., "looking at" and "near" have no conspicuous difference concerning vision, whereas "near" could occur between entities with different morphology).
Fine-Grained Predicates Learning for Scene Graph Generation
The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e. g., "woman-on/standing on/walking on-beach" or "woman-near/looking at/in front of-child".
Hierarchical Relationships: A New Perspective to Enhance Scene Graph Generation
bowen-upenn/scene_graph_commonsense
•
•
This paper presents a finding that leveraging the hierarchical structures among labels for relationships and objects can substantially improve the performance of scene graph generation systems.
Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge
bowen-upenn/scene_graph_commonsense
•
•
This work introduces an enhanced approach to generating scene graphs by incorporating both a relationship hierarchy and commonsense knowledge.
