Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior

Pseudo-RIS; Distinctive Pseudo-supervision Generation for Referring Image Segmentation

​​Rank-N-Contrast; Learning Continuous Representations for Regression

​​Unsupervised Object Localization with Representer Point Selection

Zero-shot Referring Image Segmentation with Global-Local Context Features

Contrastive Learning for Space-Time Correspondences via Self-cycle Consistency

Weakly Supervised Instance Segmentation by Deep Community Learning

Forget & Diversify; Regularized Refinement for Weakly Supervised Object Detection

Real-Time MDNet

Multi-Object Tracking with Quadruplet Convolutional Neural Network