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 create a family of powerful video models which are able to: (i) learn interactions between semantic object information and raw appearance and motion features, and (ii) deploy attention in order to better learn the importance of features at each convolutional block of the network. A new network component named peer-attention is introduced, which dynamically learns the attention weights using another block or input modality. Even without pre-training, our models outperform the previous work on standard public activity recognition datasets with continuous videos, establishing new state-of-the-art. We also confirm that our findings of having neural connections from the object modality and the use of peer-attention is generally applicable for different existing architectures, improving their performances. We name our model explicitly as AssembleNet++. The code will be available at: https://sites.google.com/corp/view/assemblenet/
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2008.08072")
get_code_for_paper("2008.08072")
have("2008.08072")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2008.08072.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2008.08072)
Connect an agent — have() is free.