# Beyond Semantic Image Segmentation : Exploring Efficient Inference in Video

Source: [Beyond Semantic Image Segmentation : Exploring Efficient Inference in Video](<https://www.sota2.com/research/paper/68fa62001e209131ce9f7102>)

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

Data updated: 2025-10-25T20:10:28.856Z

Authors: Subarna Tripathi, Serge Belongie, Truong Nguyen

Published: 2015-07-01T08:06:52.000Z

## Abstract

We explore the efficiency of the CRF inference module beyond image level semantic segmentation. The key idea is to combine the best of two worlds of semantic co-labeling and exploiting more expressive models. Similar to \[Alvarez14\] our formulation enables us perform inference over ten thousand images within seconds. On the other hand, it can handle higher-order clique potentials similar to \[vineet2014\] in terms of region-level label consistency and context in terms of co-occurrences. We follow the mean-field updates for higher order potentials similar to \[vineet2014\] and extend the spatial smoothness and appearance kernels \[DenseCRF13\] to address video data inspired by \[Alvarez14\]; thus making the system amenable to perform video semantic segmentation most effectively.

## 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/1507.01578>)

[PDF](<https://arxiv.org/pdf/1507.01578.pdf>)