# Temporal Interlacing Network

arXiv: https://arxiv.org/abs/2001.06499 · HTML: https://mlsanity.com/paper/2001.06499/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2020.

## Built on by (most cited first, 30 of 45)

- [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023)
- [VidTr: Video Transformer Without Convolutions](https://mlsanity.com/paper/2104.11746/) (2021)
- [ReasonNet: End-to-End Driving with Temporal and Global Reasoning](https://mlsanity.com/paper/2305.10507/) (2023)
- [Benchmarking Micro-action Recognition: Dataset, Methods, and Applications](https://mlsanity.com/paper/2403.05234/) (2024)
- [MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge](https://mlsanity.com/paper/2303.08914/) (2023)
- [GenVidBench: A 6-Million Benchmark for AI-Generated Video Detection](https://mlsanity.com/paper/2501.11340/) (2025)
- [Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition](https://mlsanity.com/paper/2412.14719/) (2024)
- [Event-Guided Procedure Planning from Instructional Videos with Text Supervision](https://mlsanity.com/paper/2308.08885/) (2023)
- [Diversifying Spatial-Temporal Perception for Video Domain Generalization](https://mlsanity.com/paper/2310.17942/) (2023)
- [When Video Classification Meets Incremental Classes](https://mlsanity.com/paper/2106.15827/) (2021)
- [Group Contextualization for Video Recognition](https://mlsanity.com/paper/2203.09694/) (2022)
- [XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition](https://mlsanity.com/paper/2403.01560/) (2024)
- [Attention in Attention: Modeling Context Correlation for Efficient Video Classification](https://mlsanity.com/paper/2204.09303/) (2022)
- [Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition](https://mlsanity.com/paper/2507.21977/) (2025)
- [What Makes for Good Tokenizers in Vision Transformer?](https://mlsanity.com/paper/2212.11115/) (2022)
- [Human-Centric Transformer for Domain Adaptive Action Recognition](https://mlsanity.com/paper/2407.10860/) (2024)
- [An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2406.00639/) (2024)
- [Text-Enhanced Zero-Shot Action Recognition: A training-free approach](https://mlsanity.com/paper/2408.16412/) (2024)
- [Long-term Leap Attention, Short-term Periodic Shift for Video Classification](https://mlsanity.com/paper/2207.05526/) (2022)
- [VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2305.19688/) (2023)
- [CPR-Coach: Recognizing Composite Error Actions based on Single-class Training](https://mlsanity.com/paper/2309.11718/) (2023)
- [TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification](https://mlsanity.com/paper/2502.00426/) (2025)
- [Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline](https://mlsanity.com/paper/2206.11459/) (2022)
- [OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition](https://mlsanity.com/paper/2503.23266/) (2025)
- [TSI: Temporal Saliency Integration for Video Action Recognition](https://mlsanity.com/paper/2106.01088/) (2021)
- [Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021](https://mlsanity.com/paper/2107.12618/) (2021)
- [Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds](https://mlsanity.com/paper/2308.13866/) (2023)
- [No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding](https://mlsanity.com/paper/2405.08344/) (2024)
- [Gaseous Object Detection](https://mlsanity.com/paper/2502.12415/) (2025)
- [Every Subtlety Counts: Fine-grained Person Independence Micro-Action Recognition via Distributionally Robust Optimization](https://mlsanity.com/paper/2509.21261/) (2025)

## Abstract (arXiv)

For a long time, the vision community tries to learn the spatio-temporal representation by combining convolutional neural network together with various temporal models, such as the families of Markov chain, optical flow, RNN and temporal convolution. However, these pipelines consume enormous computing resources due to the alternately learning process for spatial and temporal information. One natural question is whether we can embed the temporal information into the spatial one so the information in the two domains can be jointly learned once-only. In this work, we answer this question by presenting a simple yet powerful operator -- temporal interlacing network (TIN). Instead of learning the temporal features, TIN fuses the two kinds of information by interlacing spatial representations from the past to the future, and vice versa. A differentiable interlacing target can be learned to control the interlacing process. In this way, a heavy temporal model is replaced by a simple interlacing operator. We theoretically prove that with a learnable interlacing target, TIN performs equivalently to the regularized temporal convolution network (r-TCN), but gains 4% more accuracy with 6x less latency on 6 challenging benchmarks. These results push the state-of-the-art performances of video understanding by a considerable margin. Not surprising, the ensemble model of the proposed TIN won the 1st place in the ICCV19 - Multi Moments in Time challenge. Code is made available to facilitate further research at https://github.com/deepcs233/TIN