# Directional Temporal Modeling for Action Recognition

arXiv: https://arxiv.org/abs/2007.11040 · HTML: https://mlsanity.com/paper/2007.11040/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2020.

## Built on by (most cited first, 14 of 14)

- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [VidTr: Video Transformer Without Convolutions](https://mlsanity.com/paper/2104.11746/) (2021)
- [VA-RED2: Video Adaptive Redundancy Reduction](https://mlsanity.com/paper/2102.07887/) (2021)
- [Gate-Shift-Fuse for Video Action Recognition](https://mlsanity.com/paper/2203.08897/) (2022)
- [X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing](https://mlsanity.com/paper/2410.10167/) (2024)
- [Motion-driven Visual Tempo Learning for Video-based Action Recognition](https://mlsanity.com/paper/2202.12116/) (2022)
- [Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis](https://mlsanity.com/paper/2304.10073/) (2023)
- [Selective Feature Compression for Efficient Activity Recognition Inference](https://mlsanity.com/paper/2104.00179/) (2021)
- [Teacher Agent: A Knowledge Distillation-Free Framework for Rehearsal-based Video Incremental Learning](https://mlsanity.com/paper/2306.00393/) (2023)
- [Long-Short Temporal Modeling for Efficient Action Recognition](https://mlsanity.com/paper/2106.15787/) (2021)
- [Precondition and Effect Reasoning for Action Recognition](https://mlsanity.com/paper/2112.10057/) (2021)
- [SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition](https://mlsanity.com/paper/2305.12437/) (2023)
- [Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition](https://mlsanity.com/paper/2412.14833/) (2024)
- [Context-Aware Network Based on Multi-scale Spatio-temporal Attention for Action Recognition in Videos](https://mlsanity.com/paper/2512.18750/) (2025)

## Abstract (arXiv)

Many current activity recognition models use 3D convolutional neural networks (e.g. I3D, I3D-NL) to generate local spatial-temporal features. However, such features do not encode clip-level ordered temporal information. In this paper, we introduce a channel independent directional convolution (CIDC) operation, which learns to model the temporal evolution among local features. By applying multiple CIDC units we construct a light-weight network that models the clip-level temporal evolution across multiple spatial scales. Our CIDC network can be attached to any activity recognition backbone network. We evaluate our method on four popular activity recognition datasets and consistently improve upon state-of-the-art techniques. We further visualize the activation map of our CIDC network and show that it is able to focus on more meaningful, action related parts of the frame.