10 papers
MaskMerge: Structure-aware Token Merging for Efficient Instance Segmentation
Bavesh Balaji, Letian Jiang, Alexander Wong +2
Token merging improves the efficiency of Vision Transformers by combining redundant tokens, but existing methods largely rely on feature similarity to determine which tokens to mer…
SPARC: SuperPixel-Aware Region Contrastive Learning for Self-Supervised Dense Prediction
David Szczecina, Yuanpei Xiang, Jitao Hu +4
Self-supervised learning (SSL) has become an effective approach for learning visual representations without manual annotations. Among SSL approaches, contrastive learning has been…
Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation
Kyle Gao, Joel Cumming, Jonathan Li +2
We present an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries. The system converts user intent into st…
Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization
Kyle Gao, Pranavi Kotta, Linlin Xu +2
Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex conversational and spatial analysis but introd…
Real-Scale Island Area and Coastline Estimation using Only its Place Name or Coordinates
Quanyun Wu, Kyle Gao, Wentao Sun +4
Accurate measurement of island area and coastline length is crucial for coastal zone monitoring and oceanographic analysis. However, traditional measurement and mapping methods usu…
Rapid Forest Fuel Load Estimation via Virtual Remote Sensing and Metric-Scale Feed-Forward 3D Reconstruction
Quanyun Wu, Kyle Gao, Wentao Sun +6
Accurate quantification of forest coverage and combustible biomass (fuel load) is critical for wildfire risk assessment and ecosystem management. However, traditional methods relyi…
KitchenTwin: Semantically and Geometrically Grounded 3D Kitchen Digital Twins
Quanyun Wu, Kyle Gao, Daniel Long +3
Embodied AI training and evaluation require object-centric digital twin environments with accurate metric geometry and semantic grounding. Recent transformer-based feedforward reco…
Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimation
Jerrin Bright, Zhibo Wang, Dmytro Klepachevskyi +4
We present Avatar4D, a real-world transferable pipeline for generating customizable synthetic human motion datasets tailored to domain-specific applications. Unlike prior works, wh…
Ice Hockey Puck Localization Using Contextual Cues
Liam Salass, Jerrin Bright, Amir Nazemi +3
Puck detection in ice hockey broadcast videos poses significant challenges due to the puck's small size, frequent occlusions, motion blur, broadcast artifacts, and scale inconsiste…
Gen4D: Synthesizing Humans and Scenes in the Wild
Jerrin Bright, Zhibo Wang, Yuhao Chen +3
Lack of input data for in-the-wild activities often results in low performance across various computer vision tasks. This challenge is particularly pronounced in uncommon human-cen…