# Top-down Attention Recurrent VLAD Encoding for Action Recognition in Videos

Source: [Top-down Attention Recurrent VLAD Encoding for Action Recognition in Videos](<https://www.sota2.com/research/paper/68fa64c91e209131cea069df>)

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

Data updated: 2025-10-25T21:11:58.696Z

Authors: Swathikiran Sudhakaran, Oswald Lanz

Published: 2018-08-29T15:41:36.000Z

## Abstract

Most recent approaches for action recognition from video leverage deep architectures to encode the video clip into a fixed length representation vector that is then used for classification. For this to be successful, the network must be capable of suppressing irrelevant scene background and extract the representation from the most discriminative part of the video. Our contribution builds on the observation that spatio-temporal patterns characterizing actions in videos are highly correlated with objects and their location in the video. We propose Top-down Attention Action VLAD (TA-VLAD), a deep recurrent architecture with built-in spatial attention that performs temporally aggregated VLAD encoding for action recognition from videos. We adopt a top-down approach of attention, by using class specific activation maps obtained from a deep CNN pre-trained for image classification, to weight appearance features before encoding them into a fixed-length video descriptor using Gated Recurrent Units. Our method achieves state of the art recognition accuracy on HMDB51 and UCF101 benchmarks.

## 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.

- [Action Recognition on UCF101 (mean of 3 splits)](<https://www.sota2.com/research/sota/action-recognition-on-ucf101-mean-of-3-splits.md>): Action Recognition; UCF101 (mean of 3 splits); Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1808.09892>)

[PDF](<https://arxiv.org/pdf/1808.09892.pdf>)
