SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.09393 · 2022

Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks

arXiv · PDF · Open in the Atlas

Code that ran

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We tackle this problem from two different angles: algorithm and dataset. From the perspective of algorithms, we propose Spatial-aware Multi-Aspect Debiasing (SMAD), which incorporates both explicit debiasing with multi-aspect adversarial training and implicit debiasing with the spatial actionness reweighting module, to learn a more generic representation invariant to non-action aspects. To neutralize the intrinsic dataset bias, we propose OmniDebias to leverage web data for joint training selectively, which can achieve higher performance with far fewer web data. To verify the effectiveness, we establish evaluation protocols and perform extensive experiments on both re-distributed splits of existing datasets and a new evaluation dataset focusing on the action with rare scenes. We also show that the debiased representation can generalize better when transferred to other datasets and tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2209.09393")
get_code_for_paper("2209.09393")
have("2209.09393")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2209.09393.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2209.09393.svg)](https://syntology.ai/paper/2209.09393)

Connect an agent — have() is free.