# Low-Resolution Action Recognition for Tiny Actions Challenge

arXiv: https://arxiv.org/abs/2209.14711 · HTML: https://mlsanity.com/paper/2209.14711/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 6 references that are in the map.
- First posted on arXiv 28 Sep 2022.

## Builds on (most cited first, 6 of 6)

- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)
- [UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning](https://mlsanity.com/paper/2201.04676/) (2022)
- [Investigating Tradeoffs in Real-World Video Super-Resolution](https://mlsanity.com/paper/2111.12704/) (2021)
- [TinyVIRAT: Low-resolution Video Action Recognition](https://mlsanity.com/paper/2007.07355/) (2020)
- [TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videos](https://mlsanity.com/paper/2107.11494/) (2021)

## Built on by (most cited first, 5 of 5)

- [LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents](https://mlsanity.com/paper/2503.10200/) (2025)
- [VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning](https://mlsanity.com/paper/2506.06097/) (2025)
- [Percept, Chat, and then Adapt: Multimodal Knowledge Transfer of Foundation Models for Open-World Video Recognition](https://mlsanity.com/paper/2402.18951/) (2024)
- [VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2511.19524/) (2025)
- [Super Encoding Network: Recursive Association of Multi-Modal Encoders for Video Understanding](https://mlsanity.com/paper/2506.07576/) (2025)

## Abstract (arXiv)

Tiny Actions Challenge focuses on understanding human activities in real-world surveillance. Basically, there are two main difficulties for activity recognition in this scenario. First, human activities are often recorded at a distance, and appear in a small resolution without much discriminative clue. Second, these activities are naturally distributed in a long-tailed way. It is hard to alleviate data bias for such heavy category imbalance. To tackle these problems, we propose a comprehensive recognition solution in this paper. First, we train video backbones with data balance, in order to alleviate overfitting in the challenge benchmark. Second, we design a dual-resolution distillation framework, which can effectively guide low-resolution action recognition by super-resolution knowledge. Finally, we apply model en-semble with post-processing, which can further boost per-formance on the long-tailed categories. Our solution ranks Top-1 on the leaderboard.