# Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images

arXiv: https://arxiv.org/abs/1504.00983 · HTML: https://mlsanity.com/paper/1504.00983/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2015.

## Built on by (most cited first, 19 of 19)

- [Learning Audio-Video Modalities from Image Captions](https://mlsanity.com/paper/2204.00679/) (2022)
- [Zero-shot Natural Language Video Localization](https://mlsanity.com/paper/2110.00428/) (2021)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [Action Unit Memory Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2104.14135/) (2021)
- [Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2108.06524/) (2021)
- [Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation](https://mlsanity.com/paper/2103.16024/) (2021)
- [ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2103.15088/) (2021)
- [UnweaveNet: Unweaving Activity Stories](https://mlsanity.com/paper/2112.10194/) (2021)
- [Anchor-Constrained Viterbi for Set-Supervised Action Segmentation](https://mlsanity.com/paper/2104.02113/) (2021)
- [Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions](https://mlsanity.com/paper/2207.11805/) (2022)
- [CycDA: Unsupervised Cycle Domain Adaptation from Image to Video](https://mlsanity.com/paper/2203.16244/) (2022)
- [Weakly-guided Self-supervised Pretraining for Temporal Activity Detection](https://mlsanity.com/paper/2111.13675/) (2021)
- [Action-Agnostic Point-Level Supervision for Temporal Action Detection](https://mlsanity.com/paper/2412.21205/) (2024)
- [Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2407.08971/) (2024)
- [Unsupervised Discovery of Actions in Instructional Videos](https://mlsanity.com/paper/2106.14733/) (2021)
- [Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts](https://mlsanity.com/paper/2101.03713/) (2021)
- [CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition](https://mlsanity.com/paper/2103.10567/) (2021)
- [Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos](https://mlsanity.com/paper/2204.13548/) (2022)
- [Progression-Guided Temporal Action Detection in Videos](https://mlsanity.com/paper/2308.09268/) (2023)

## Abstract (arXiv)

We address the problem of fine-grained action localization from temporally untrimmed web videos. We assume that only weak video-level annotations are available for training. The goal is to use these weak labels to identify temporal segments corresponding to the actions, and learn models that generalize to unconstrained web videos. We find that web images queried by action names serve as well-localized highlights for many actions, but are noisily labeled. To solve this problem, we propose a simple yet effective method that takes weak video labels and noisy image labels as input, and generates localized action frames as output. This is achieved by cross-domain transfer between video frames and web images, using pre-trained deep convolutional neural networks. We then use the localized action frames to train action recognition models with long short-term memory networks. We collect a fine-grained sports action data set FGA-240 of more than 130,000 YouTube videos. It has 240 fine-grained actions under 85 sports activities. Convincing results are shown on the FGA-240 data set, as well as the THUMOS 2014 localization data set with untrimmed training videos.