Search Results for author:
Found 7 papers, 2 papers with code
ESGCN: Edge Squeeze Attention Graph Convolutional Network for Traffic Flow Forecasting
The ES module models the spatio-temporal dynamics using Graph Convolutional Network (GCN) and generates an Adaptive Adjacency Matrix (AAM) with temporal features.
Decompose, Adjust, Compose: Effective Normalization by Playing with Frequency for Domain Generalization
With the normalization methods, we propose ResNet-variant models, DAC-P and DAC-SC, which are robust to the domain gap.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
SBNet: Segmentation-based Network for Natural Language-based Vehicle Search
Natural language-based vehicle retrieval is a task to find a target vehicle within a given image based on a natural language description as a query.
Multi-Attention-Based Soft Partition Network for Vehicle Re-Identification
Meanwhile, based on the researchers' insights, various handcrafted multi-attention architectures for specific viewpoints or vehicle parts have been proposed.
StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle Re-Identification
Vehicle re-identification aims to obtain the same vehicles from vehicle images.
An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task.
Ranked #64 on
Instance Segmentation
on COCO test-dev
