# From images in the wild to video-informed image classification

Source: [From images in the wild to video-informed image classification](<https://www.sota2.com/research/paper/68fa6ade1e209131cea2af17>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:49.999Z

Authors: Marc B\\"ohlen, Varun Chandola, Wawan Sujarwo, Raunaq Jain

Published: 2021-09-24T15:53:37.000Z

## Abstract

Image classifiers work effectively when applied on structured images, yet they often fail when applied on images with very high visual complexity. This paper describes experiments applying state-of-the-art object classifiers toward a unique set of images in the wild with high visual complexity collected on the island of Bali. The text describes differences between actual images in the wild and images from Imagenet, and then discusses a novel approach combining informational cues particular to video with an ensemble of imperfect classifiers in order to improve classification results on video sourced images of plants in the wild.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.12040>)

[PDF](<https://arxiv.org/pdf/2109.12040.pdf>)