Noah Snavely, Apoorv Khandelwal, Hadar Averbuch-Elor, Claire Cui, Yoav Artzi
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present a task and benchmark dataset for personcentric visual grounding, the problem of linking between people named in a caption and people pictured in an image. In contrast to prior work in visual grounding, which is predominantly object-based, our new task masks out the names of people in captions in order to encourage methods trained on such image-caption pairs to focus on contextual cues, such as the rich interactions between multiple people, rather than learning associations between names and appearances. To facilitate this task, we introduce a new dataset, Who's Waldo, mined automatically from image-caption data on Wikimedia Commons. We propose a Transformer-based method that outperforms several strong baselines on this task, and release our data to the research community to spur work on contextual models that consider both vision and language.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.07253")
get_code_for_paper("2108.07253")
have("2108.07253")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.07253.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.07253)
Connect an agent — have() is free.