Search Results for author:
Found 6 papers, 0 papers with code
How Image Generation Helps Visible-to-Infrared Person Re-Identification?
To this end, we propose Flow2Flow, a unified framework that could jointly achieve training sample expansion and cross-modality image generation for V2I person ReID.
Multi-Granularity Graph Pooling for Video-based Person Re-Identification
To downsample the graph, we propose a multi-head full attention graph pooling (MHFAPool) layer, which integrates the advantages of existing node clustering and node selection pooling methods.
Pose-Aided Video-based Person Re-Identification via Recurrent Graph Convolutional Network
Finally, we propose a dual-attention method consisting of node-attention and time-attention to obtain the temporal graph representation from the node embeddings, where the self-attention mechanism is employed to learn the importance of each node and each frame.
Towards Complete-View and High-Level Pose-based Gait Recognition
Extensive experiments on two large gait recognition datasets, i. e., CASIA-B and OUMVLP-Pose, demonstrate that our method outperforms the baseline model and existing pose-based methods by a large margin.
TCDesc: Learning Topology Consistent Descriptors for Image Matching
Our method has the following two advantages: (1) We are the first to consider neighborhood information of descriptors, while former works mainly focus on neighborhood consistency of feature points; (2) Our method can be applied in any former work of learning descriptors by triplet loss.
TCDesc: Learning Topology Consistent Descriptors
Then we define topology distance between descriptors as the difference of their topology vectors.
