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.
Multiview detection incorporates multiple camera views to deal with occlusions, and its central problem is multiview aggregation. Given feature map projections from multiple views onto a common ground plane, the state-of-the-art method addresses this problem via convolution, which applies the same calculation regardless of object locations. However, such translation-invariant behaviors might not be the best choice, as object features undergo various projection distortions according to their positions and cameras. In this paper, we propose a novel multiview detector, MVDeTr, that adopts a newly introduced shadow transformer to aggregate multiview information. Unlike convolutions, shadow transformer attends differently at different positions and cameras to deal with various shadow-like distortions. We propose an effective training scheme that includes a new view-coherent data augmentation method, which applies random augmentations while maintaining multiview consistency. On two multiview detection benchmarks, we report new state-of-the-art accuracy with the proposed system. Code is available at https://github.com/hou-yz/MVDeTr.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.05888")
get_code_for_paper("2108.05888")
have("2108.05888")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.05888.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.05888)
Connect an agent — have() is free.