1. Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding
2. Detector-Free Weakly Supervised Grounding by Separation
3. Point-Level Region Contrast for Object Detection Pre-Training
4. Emergence of object segmentation in perturbed generative models;Bielski;Advances in Neural Information Processing Systems,2019
5. Move: Unsupervised movable object segmentation and detection;Bielski,2022