Stochastic trajectory prediction via motion indeterminacy diffusion
Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory
prediction system to model the multi-modality of future motion states. Unlike existing …
prediction system to model the multi-modality of future motion states. Unlike existing …
Progressive spatio-temporal prototype matching for text-video retrieval
The performance of text-video retrieval has been significantly improved by vision-language
cross-modal learning schemes. The typical solution is to directly align the global video-level …
cross-modal learning schemes. The typical solution is to directly align the global video-level …
Adaptive trajectory prediction via transferable gnn
Pedestrian trajectory prediction is an essential component in a wide range of AI applications
such as autonomous driving and robotics. Existing methods usually assume the training and …
such as autonomous driving and robotics. Existing methods usually assume the training and …
Eigentrajectory: Low-rank descriptors for multi-modal trajectory forecasting
Capturing high-dimensional social interactions and feasible futures is essential for
predicting trajectories. To address this complex nature, several attempts have been devoted …
predicting trajectories. To address this complex nature, several attempts have been devoted …
Sparse instance conditioned multimodal trajectory prediction
Pedestrian trajectory prediction is critical in many vision tasks but challenging due to the
multimodality of the future trajectory. Most existing methods predict multimodal trajectories …
multimodality of the future trajectory. Most existing methods predict multimodal trajectories …
Multi-stream representation learning for pedestrian trajectory prediction
Forecasting the future trajectory of pedestrians is an important task in computer vision with a
range of applications, from security cameras to autonomous driving. It is very challenging …
range of applications, from security cameras to autonomous driving. It is very challenging …
Multi-person 3d motion prediction with multi-range transformers
We propose a novel framework for multi-person 3D motion trajectory prediction. Our key
observation is that a human's action and behaviors may highly depend on the other persons …
observation is that a human's action and behaviors may highly depend on the other persons …
Learning pedestrian group representations for multi-modal trajectory prediction
Modeling the dynamics of people walking is a problem of long-standing interest in computer
vision. Many previous works involving pedestrian trajectory prediction define a particular set …
vision. Many previous works involving pedestrian trajectory prediction define a particular set …
Combating representation learning disparity with geometric harmonization
Self-supervised learning (SSL) as an effective paradigm of representation learning has
achieved tremendous success on various curated datasets in diverse scenarios …
achieved tremendous success on various curated datasets in diverse scenarios …
[HTML][HTML] Gatraj: A graph-and attention-based multi-agent trajectory prediction model
Trajectory prediction has been a long-standing problem in intelligent systems like
autonomous driving and robot navigation. Models trained on large-scale benchmarks have …
autonomous driving and robot navigation. Models trained on large-scale benchmarks have …