ICCV 2021 accepted papers on Graph learning
36 of the 1,612 papers accepted at ICCV 2021 (2.2%) are on Graph learning, compared with 2.1% at ICCV 2019. They fall into 4 topics.
See ICCV 2021 in the interactive map
Submitting to ICCV? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Knowledge and temporal graphs · 19 papers
- Channel-Wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition (1,185 citations)
- Spatio-Temporal Dynamic Inference Network for Group Activity Recognition (133 citations)
- Graph-Based Asynchronous Event Processing for Rapid Object Recognition (117 citations)
- From General to Specific: Informative Scene Graph Generation via Balance Adjustment (98 citations)
- TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition (88 citations)
- Context-Aware Scene Graph Generation With Seq2Seq Transformers (87 citations)
- Learning To Generate Scene Graph From Natural Language Supervision (78 citations)
- In Defense of Scene Graphs for Image Captioning (77 citations)
- Segmentation-Grounded Scene Graph Generation (35 citations)
- Generative Compositional Augmentations for Scene Graph Prediction (32 citations)
- Unifying Nonlocal Blocks for Neural Networks (31 citations)
- A Simple Baseline for Weakly-Supervised Scene Graph Generation (27 citations)
and 7 more in the interactive map.
Graph algorithms and clustering · 10 papers
- Learning To Match Features With Seeded Graph Matching Network (176 citations)
- Learning Hierarchical Graph Neural Networks for Image Clustering (38 citations)
- Hypergraph Neural Networks for Hypergraph Matching (31 citations)
- Viewing Graph Solvability via Cycle Consistency (16 citations)
- Learn To Cluster Faces via Pairwise Classification (15 citations)
- Fusion Moves for Graph Matching (12 citations)
- Learning To Bundle-Adjust: A Graph Network Approach to Faster Optimization of Bundle Adjustment for Vehicular SLAM (12 citations)
- Learning Better Visual Data Similarities via New Grouplet Non-Euclidean Embedding (11 citations)
- Rotation Averaging in a Split Second: A Primal-Dual Method and a Closed-Form for Cycle Graphs (8 citations)
- Synchronization of Group-Labelled Multi-Graphs (5 citations)
Graph self-supervised learning · 5 papers
- Graph Contrastive Clustering (167 citations)
- Generative Layout Modeling Using Constraint Graphs (97 citations)
- Visual Distant Supervision for Scene Graph Generation (38 citations)
- BlockPlanner: City Block Generation With Vectorized Graph Representation (30 citations)
- SketchLattice: Latticed Representation for Sketch Manipulation (22 citations)
