ETH/UCY
PulseAugur coverage of ETH/UCY — every cluster mentioning ETH/UCY across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New research advances multi-person and single-person motion prediction
Two new research papers propose advanced methods for predicting human motion. FlowMoP utilizes a conditional flow matching framework to generate diverse future motions for multiple agents, outperforming deterministic mo…
-
New Bi-Mamba Model Enhances Robot Navigation with Real-Time Trajectory Prediction
Researchers have developed TrajMamba, a novel bidirectional state space model designed for real-time human trajectory prediction using RGB-D cameras. This model addresses the train-deploy pipeline gap by aligning pose e…
-
New MoRE framework enhances language-based trajectory prediction models
Researchers have developed MoRE, a novel framework designed to enhance language-based trajectory prediction models. MoRE integrates numerical forecasting priors into existing language models using reinforcement learning…
-
New GEAR model dynamically activates social context for improved trajectory prediction
Researchers have developed GEAR, a novel model for human trajectory prediction that addresses the limitations of existing methods by focusing on how social context is activated during future trajectory generation. Unlik…
-
New method forecasts trajectories using uncertainty from imperfect tracking
Researchers have developed a novel approach to trajectory forecasting that accounts for uncertainties inherent in real-world tracking data. This method models observed states as Gaussian distributions, incorporating bot…
-
New framework INTraJ models social influence in trajectory prediction
Researchers have introduced INTraJ, a novel framework for trajectory prediction that explicitly models social influence in two distinct stages. The first stage, planning, uses future social information to construct refe…
-
TSCA-Net improves pedestrian trajectory prediction with novel attention and adaptive modules
Researchers have developed TSCA-Net, a novel framework for pedestrian trajectory prediction in crowded environments. This system addresses limitations in existing models by incorporating learnable temporal gating, a dyn…
-
New diffusion model enhances multi-agent motion prediction
Researchers have developed a new diffusion-based framework to improve multi-agent motion prediction. This approach leverages contextual information from historical trajectories to enhance the diversity and expressivenes…
-
SceneSelect introduces selective learning for trajectory prediction, improving accuracy by 10.5%
Researchers have introduced SceneSelect, a novel scene-centric paradigm for trajectory prediction that addresses the limitations of traditional model-centric approaches. This new method analyzes scene characteristics to…