Picture for Chris Buehler

Chris Buehler

Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

Add code
Mar 14, 2018
Figure 1 for Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Figure 2 for Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Figure 3 for Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Figure 4 for Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Viaarxiv icon

Semantic-driven Generation of Hyperlapse from $360^\circ$ Video

Add code
Oct 10, 2017
Figure 1 for Semantic-driven Generation of Hyperlapse from $360^\circ$ Video
Figure 2 for Semantic-driven Generation of Hyperlapse from $360^\circ$ Video
Figure 3 for Semantic-driven Generation of Hyperlapse from $360^\circ$ Video
Figure 4 for Semantic-driven Generation of Hyperlapse from $360^\circ$ Video
Viaarxiv icon

Rich Image Captioning in the Wild

Add code
Mar 31, 2016
Figure 1 for Rich Image Captioning in the Wild
Figure 2 for Rich Image Captioning in the Wild
Figure 3 for Rich Image Captioning in the Wild
Figure 4 for Rich Image Captioning in the Wild
Viaarxiv icon