Finding 「It」: Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos
這是CVPR2018 Oral的一片關於Weakly-Supervised Video Grounding的文章，paper連接http://ai.stanford.edu/~dahuang/papers/cvpr18-ramil.pdf，作者的homepage http://ai.stanford.edu/~dahuang/，code暫時沒有被released出來。 文章要做的事情： 輸入：se
相關文章
- 1. Dense-Captioning Events in Videos
- 2. Temporal Relational Reasoning in Videos
- 3. 論文閱讀：Tracking-assisted Weakly Supervised Online Visual Object Segmentation in Unconstrained Videos
- 4. Android + OpenCV - Finding extreme points in contours
- 5. Image Processing23（Finding contours in your image )
- 6. 閱讀筆記（Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding)
- 7. SpeedNet: Learning the Speediness in Videos
- 8. Finding Lane Lines on the Road
- 9. 譯：Two-stream convolutional networks for action recognition in videos
- 10. Finding Tiny Faces in the Wild with Generative Adversarial Network
- 更多相關文章...
- • SQL IN 操作符 - SQL 教程
- • Swift for-in 循環 - Swift 教程
- • Kotlin學習（一）基本語法
- • 委託模式
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Dense-Captioning Events in Videos
- 2. Temporal Relational Reasoning in Videos
- 3. 論文閱讀：Tracking-assisted Weakly Supervised Online Visual Object Segmentation in Unconstrained Videos
- 4. Android + OpenCV - Finding extreme points in contours
- 5. Image Processing23（Finding contours in your image )
- 6. 閱讀筆記（Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding)
- 7. SpeedNet: Learning the Speediness in Videos
- 8. Finding Lane Lines on the Road
- 9. 譯：Two-stream convolutional networks for action recognition in videos
- 10. Finding Tiny Faces in the Wild with Generative Adversarial Network