# The complementarity of a diverse range of deep learning features extracted from video content for video recommendation

Source: [The complementarity of a diverse range of deep learning features extracted from video content for video recommendation](<https://www.sota2.com/research/paper/68fa6b871e209131cea2ee35>)

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

Data updated: 2026-01-04T03:23:05.408Z

Authors: Adolfo Almeida, Johan Pieter de Villiers, Allan De Freitas, Mergandran Velayudan

Published: 2020-11-21T18:00:28.000Z

## Abstract

Following the popularisation of media streaming, a number of video streaming services are continuously buying new video content to mine the potential profit from them. As such, the newly added content has to be handled well to be recommended to suitable users. In this paper, we address the new item cold-start problem by exploring the potential of various deep learning features to provide video recommendations. The deep learning features investigated include features that capture the visual-appearance, audio and motion information from video content. We also explore different fusion methods to evaluate how well these feature modalities can be combined to fully exploit the complementary information captured by them. Experiments on a real-world video dataset for movie recommendations show that deep learning features outperform hand-crafted features. In particular, recommendations generated with deep learning audio features and action-centric deep learning features are superior to MFCC and state-of-the-art iDT features. In addition, the combination of various deep learning features with hand-crafted features and textual metadata yields significant improvement in recommendations compared to combining only the former.

## 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.

- [Video Recommendation on MovieLens item warm-start 10M](<https://www.sota2.com/research/sota/video-recommendation-on-movielens-item-warm-start-10m.md>): Video Recommendation; MovieLens item warm-start 10M; MAP@5: 0.1536.

- [Video Recommendation on MovieLens 10M (item cold-start)](<https://www.sota2.com/research/sota/video-recommendation-on-movielens-10m-item-cold-start.md>): Video Recommendation; MovieLens 10M (item cold-start); MAP@5: 0.0178.

- [Recommender Systems on MovieLens item 10M (cold-start)](<https://www.sota2.com/research/sota/recommender-systems-on-movielens-item-10m-cold-start.md>): Recommender Systems; MovieLens item 10M (cold-start); Div. SE @5: 9.1571.

- [Video Recommendation on MovieLens-10M item warm-start scenario](<https://www.sota2.com/research/sota/video-recommendation-on-movielens-10m-item-warm-start-scenario.md>): Video Recommendation; MovieLens-10M item warm-start scenario; Shannon Entropy @5: 7.5366.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2011.10834>)

[PDF](<https://arxiv.org/pdf/2011.10834.pdf>)

[Implementation](<https://github.com/Adolfo-Almeida/scaled_CER>)