ECCV 2024 accepted papers on Graph learning
23 of the 2,387 papers accepted at ECCV 2024 (1.0%) are on Graph learning, compared with 1.5% at ECCV 2022. They fall into 4 topics.
See ECCV 2024 in the interactive map
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 · 14 papers
- SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition (138 citations)
- Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction (60 citations)
- Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention (26 citations)
- Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation (14 citations)
- OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models (12 citations)
- Fine-Grained Scene Graph Generation via Sample-Level Bias Prediction (7 citations)
- Heterogeneous Graph Learning for Scene Graph Prediction in 3D Point Clouds (7 citations)
- A Fair Ranking and New Model for Panoptic Scene Graph Generation (5 citations)
- Continuity Preserving Online CenterLine Graph Learning (5 citations)
- Multi-Granularity Sparse Relationship Matrix Prediction Network for End-to-End Scene Graph Generation (5 citations)
- Multiscale Graph Texture Network (5 citations)
- Mew: Multiplexed Immunofluorescence Image Analysis through an Efficient Multiplex Network (3 citations)
and 2 more in the interactive map.
Graph algorithms and clustering · 4 papers
- Graph Neural Network Causal Explanation via Neural Causal Models (12 citations)
- A Direct Approach to Viewing Graph Solvability (2 citations)
- Synchronization of Projective Transformations (2 citations)
- Adaptive Annealing for Robust Averaging (1 citation)
