Search Results for author:
Found 5 papers, 0 papers with code
HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation
To this end, we propose Multimodal LLMs on a Scene HyperGraph (HyperGLM), promoting reasoning about multi-way interactions and higher-order relationships.
CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos
In this paper, we introduce the new AeroEye dataset that focuses on multi-object relationship modeling in aerial videos.
HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding
In this paper, we delve into interactivities understanding within visual content by deriving scene graph representations from dense interactivities among humans and objects.
TextANIMAR: Text-based 3D Animal Fine-Grained Retrieval
Unlike previous SHREC challenge tracks, the proposed task is considerably more challenging, requiring participants to develop innovative approaches to tackle the problem of text-based retrieval.
SketchANIMAR: Sketch-based 3D Animal Fine-Grained Retrieval
To this end, we introduce a novel SHREC challenge track that focuses on retrieving relevant 3D animal models from a dataset using sketch queries and expedites accessing 3D models through available sketches.
