Taojiannan Yang

9

Papers

146

Total Citations

Papers (9)

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

VIGOR: Cross-View Image Geo-Localization Beyond One-to-One Retrieval

Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning

FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER

3D Human Pose Estimation With Spatial and Temporal Transformers

A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition

MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution

Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level

GradAug: A New Regularization Method for Deep Neural Networks