Deep learning

AVisT: A Benchmark for Visual Object Tracking in Adverse Visibility

Robust Visual Tracking by Segmentation

Transforming Model Prediction for Tracking

Learning Target Candidate Association to Keep Track of What Not to Track

Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models

Adversarial Feature Distribution Alignment for Semi-Supervised Learning

Efficient Video Semantic Segmentation with Labels Propagation and Refinement

Adversarial Sampling for Active Learning