# S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks

arXiv: https://arxiv.org/abs/1807.08069 · HTML: https://mlsanity.com/paper/1807.08069/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2018.

## Built on by (most cited first, 16 of 16)

- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [CLIP2Video: Mastering Video-Text Retrieval via Image CLIP](https://mlsanity.com/paper/2106.11097/) (2021)
- [TALLFormer: Temporal Action Localization with a Long-memory Transformer](https://mlsanity.com/paper/2204.01680/) (2022)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [SignCLIP: Connecting Text and Sign Language by Contrastive Learning](https://mlsanity.com/paper/2407.01264/) (2024)
- [RGB Stream Is Enough for Temporal Action Detection](https://mlsanity.com/paper/2107.04362/) (2021)
- [FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks](https://mlsanity.com/paper/2203.13371/) (2022)
- [An Efficient Spatio-Temporal Pyramid Transformer for Action Detection](https://mlsanity.com/paper/2207.10448/) (2022)
- [Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition](https://mlsanity.com/paper/2204.00452/) (2022)
- [Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition](https://mlsanity.com/paper/2204.07270/) (2022)
- [Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2406.02831/) (2024)
- [Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2212.11187/) (2022)
- [POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization](https://mlsanity.com/paper/2310.13585/) (2023)
- [A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval](https://mlsanity.com/paper/2312.00115/) (2023)
- [Facial Tic Detection in Untrimmed Videos of Tourette Syndrome Patients](https://mlsanity.com/paper/2211.03895/) (2022)
- [ADM-Loc: Actionness Distribution Modeling for Point-supervised Temporal Action Localization](https://mlsanity.com/paper/2311.15916/) (2023)

## Abstract (arXiv)

In this paper, we present a novel Single Shot multi-Span Detector for temporal activity detection in long, untrimmed videos using a simple end-to-end fully three-dimensional convolutional (Conv3D) network. Our architecture, named S3D, encodes the entire video stream and discretizes the output space of temporal activity spans into a set of default spans over different temporal locations and scales. At prediction time, S3D predicts scores for the presence of activity categories in each default span and produces temporal adjustments relative to the span location to predict the precise activity duration. Unlike many state-of-the-art systems that require a separate proposal and classification stage, our S3D is intrinsically simple and dedicatedly designed for single-shot, end-to-end temporal activity detection. When evaluating on THUMOS'14 detection benchmark, S3D achieves state-of-the-art performance and is very efficient and can operate at 1271 FPS.