Search Results for author:
Found 5 papers, 2 papers with code
An Approach for Multi-Object Tracking with Two-Stage Min-Cost Flow
Specifically, we employ the minimum network flow algorithm with high-confidence detections as input in the first stage to obtain the candidate tracklets that need correction.
Reasonable Anomaly Detection in Long Sequences
In this paper, we propose to completely represent the motion patterns of objects by learning from long-term sequences.
Texture-Based Input Feature Selection for Action Recognition
To improve the model robustness, we propose a novel method to determine the task-irrelevant content in inputs which increases the domain discrepancy.
Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies
Second, to improve the robustness of binary models with contextual dependencies, we compute the contextual dynamic embeddings to determine the binarization thresholds in general binary convolutional blocks.
A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos
High-level graph representations encode the trajectories of people and the interactions among multiple identities while low-level graph representations encode the local body postures of each person.
