# Less is More: Sparse Sampling for Dense Reaction Predictions

arXiv: https://arxiv.org/abs/2106.01764 · HTML: https://mlsanity.com/paper/2106.01764/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 3 Jun 2021.

## Builds on (most cited first, 9 of 9)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Dual-Path Convolutional Image-Text Embeddings with Instance Loss](https://mlsanity.com/paper/1711.05535/) (2017)
- [Transferring Cross-domain Knowledge for Video Sign Language Recognition](https://mlsanity.com/paper/2003.03703/) (2020)
- [Learnable pooling with Context Gating for video classification](https://mlsanity.com/paper/1706.06905/) (2017)
- [Evaluation of Error and Correlation-Based Loss Functions For Multitask Learning Dimensional Speech Emotion Recognition](https://mlsanity.com/paper/2003.10724/) (2020)

## Built on by (most cited first, 2 of 2)

- [Robust Low-Rank Sparse Framework for Video-Based Affective Computing](https://mlsanity.com/paper/2511.11406/) (2025)
- [Temporal Convolution Networks with Positional Encoding for Evoked Expression Estimation](https://mlsanity.com/paper/2106.08596/) (2021)

## Abstract (arXiv)

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.