# Deep Concept-wise Temporal Convolutional Networks for Action Localization

arXiv: https://arxiv.org/abs/1908.09442 · HTML: https://mlsanity.com/paper/1908.09442/

## Key facts

- Cited by 10 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 26 Aug 2019.

## Built on by (most cited first, 10 of 10)

- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [OadTR: Online Action Detection with Transformers](https://mlsanity.com/paper/2106.11149/) (2021)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection](https://mlsanity.com/paper/2205.02717/) (2022)
- [Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization](https://mlsanity.com/paper/2106.14118/) (2021)
- [RGB Stream Is Enough for Temporal Action Detection](https://mlsanity.com/paper/2107.04362/) (2021)
- [SVIP: Sequence VerIfication for Procedures in Videos](https://mlsanity.com/paper/2112.06447/) (2021)
- [Structured Attention Composition for Temporal Action Localization](https://mlsanity.com/paper/2205.09956/) (2022)
- [Semantic Video Moments Retrieval at Scale: A New Task and a Baseline](https://mlsanity.com/paper/2210.08389/) (2022)

## Abstract (arXiv)

Existing action localization approaches adopt shallow temporal convolutional networks (ie, TCN) on 1D feature map extracted from video frames. In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution. To address this issue, we introduce a novel concept-wise temporal convolution (CTC) layer as an alternative to conventional temporal convolution layer for training deeper action localization networks. Instead of recombining latent concepts, CTC layer deploys a number of temporal filters to each concept separately with shared filter parameters across concepts. Thus can capture common temporal patterns of different concepts and significantly enrich representation ability. Via stacking CTC layers, we proposed a deep concept-wise temporal convolutional network (C-TCN), which boosts the state-of-the-art action localization performance on THUMOS'14 from 42.8 to 52.1 in terms of mAP(%), achieving a relative improvement of 21.7%. Favorable result is also obtained on ActivityNet.