ReLER-Baidu-Seminar
| Date | Speaker | Title |
|---|---|---|
| 7.12 | Zongxin | End-to-end Object Detection with Transformers |
| 7.12 | Yu | In Defense of Grid Features for Visual Question Answering |
| 7.19 | Xiaohan | UNITER: UNiversal Image-TExt Representation Learning End-to-End Learning of Visual Representations from Uncurated Instructional Videos Self-Supervised MultiModal Versatile Networks |
| 7.26 | Ruijie | Long-term Human Motion Prediction with Scene Context |
| 7.26 | Youjiang | Discovering Human Interactions with Novel Objects via Zero-Shot Learning Learning Human-Object Interaction Detection using Interaction Points |
| 8.02 | Guang | Exploring Self-attention for Image Recognition |
| 8.02 | Yuanzhi | Visual Commonsense R-CNN |
| 8.09 | Pingbo | Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One |
| 8.09 | Chao | corner proposal network for anchor-free two-stage object detection |
| 8.16 | Yunqiu | Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation |
| 8.16 | Chen | Self-training with Noisy Student improves ImageNet classification |
| 8.23 | Xuanmeng | |
| 8.23 | Yutian | |
| 8.30 | Yuhang | |
| 8.30 | Jiaxu |