Search Results for author:
Found 5 papers, 0 papers with code
IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Prediction
In the proposed module, the data-driven mechanism can effectively extract the feature representations of dynamic human-human interactions in the scene and calculate the corresponding weights to represent the importance of different interactions.
Learning Discriminative Features for Crowd Counting
Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations.
Tolerating Annotation Displacement in Dense Object Counting via Point Annotation Probability Map
To improve the robustness to annotation displacement, we design an effective transport cost function based on GGD.
Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation
Thus, CNN could locate and estimate crowds accurately in low-density regions, while it is hard to properly perceive the densities in high-density regions.
Region-Aware Network: Model Human's Top-Down Visual Perception Mechanism for Crowd Counting
More specifically, we scan the whole input images and its priority maps in the form of column vector to obtain a relevance matrix estimating their similarity.
