Less is More: Sparse Sampling for Dense Reaction Predictions
arXiv:2106.01764
Abstract
Obtaining viewer responses from videos can be useful for creators and streaming platforms to analyze the video performance and improve the future user experience. In this report, we present our method for 2021 Evoked Expression from Videos Challenge. In particular, our model utilizes both audio and image modalities as inputs to predict emotion changes of viewers. To model long-range emotion changes, we use a GRU-based model to predict one sparse signal with 1Hz. We observe that the emotion changes are smooth. Therefore, the final dense prediction is obtained via linear interpolating the signal, which is robust to the prediction fluctuation. Albeit simple, the proposed method has achieved pearson's correlation score of 0.04430 on the final private test set.
arXiv commentCode is available at: https://github.com/HenryLittle/EEV-Challenge-2021
References in corpus (5)
- Learning Transferable Visual Models From Natural Language Supervision
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Rethinking the Inception Architecture for Computer Vision
- Learnable pooling with Context Gating for video classification
- EEV: A Large-Scale Dataset for Studying Evoked Expressions from Video