self-critical sequence training for image captioning
Published 6 years ago • 1.6K plays • Length 13:45Download video MP4
Download video MP3
Similar videos
-
4:35
971 - self-distillation for few-shot image captioning
-
4:56
improve image captioning by estimating the gazing patterns from the caption
-
1:01
more grounded image captioning by distilling image-text matching model
-
1:01
meshed-memory transformer for image captioning
-
11:34
deep reinforcement learning-based image captioning with embedding reward
-
3:53:50
cvpr #18542 - new frontiers for zero-shot image captioning evaluation
-
4:40
wacv18: fine-grained and semantic-guided visual attention for image captioning
-
0:57
better captioning with sequence-level exploration
-
5:27
automatic image captions with microsoft azure computer vision api
-
3:41
improved image captioning via policy gradient optimization of spider
-
11:40
imagebert
-
8:57
self-training with noisy student (87.4% imagenet top-1 accuracy!)
-
4:58
masked autoencoders are scalable vision learners | cvpr 2022
-
3:38
image captioning with semantic attention
-
3:56
an unified framework for language guided image completion