Ziyuan Huang

Latest

• Temporally-Adaptive Models for Efficient Video Understanding
• Towards Real-World Visual Tracking with Temporal Contexts
• PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework
• MAR: Masked Autoencoders for Efficient Action Recognition
• Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency
• ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
• TAda! Temporally-Adaptive Convolutions for Video Understanding
• A Stronger Baseline for Ego-Centric Action Detection
• Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition
• Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation
• Self-supervised motion learning from static images
• Support-Set Based Cross-Supervision for Video Grounding
• AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization
• Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking