# TIM: A Time Interval Machine for Audio-Visual Action Recognition

arXiv: https://arxiv.org/abs/2404.05559 · HTML: https://mlsanity.com/paper/2404.05559/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 67 references that are in the map.
- First posted on arXiv 8 Apr 2024.

## Builds on (most cited first, 30 of 56)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [Perception Test: A Diagnostic Benchmark for Multimodal Video Models](https://mlsanity.com/paper/2305.13786/) (2023)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [G-TAD: Sub-Graph Localization for Temporal Action Detection](https://mlsanity.com/paper/1911.11462/) (2019)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition](https://mlsanity.com/paper/1908.08498/) (2019)
- [Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers](https://mlsanity.com/paper/2106.05392/) (2021)
- [Omnivore: A Single Model for Many Visual Modalities](https://mlsanity.com/paper/2201.08377/) (2022)

## Built on by (most cited first, 15 of 15)

- [HD-EPIC: A Highly-Detailed Egocentric Video Dataset](https://mlsanity.com/paper/2502.04144/) (2025)
- [MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps](https://mlsanity.com/paper/2503.18223/) (2025)
- [Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation](https://mlsanity.com/paper/2507.22886/) (2025)
- [AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection](https://mlsanity.com/paper/2504.04495/) (2025)
- [Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context](https://mlsanity.com/paper/2410.21275/) (2024)
- [EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception](https://mlsanity.com/paper/2506.21080/) (2025)
- [LLaVAction: evaluating and training multi-modal large language models for action understanding](https://mlsanity.com/paper/2503.18712/) (2025)
- [Audio-visual Event Localization on Portrait Mode Short Videos](https://mlsanity.com/paper/2504.06884/) (2025)
- [Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation](https://mlsanity.com/paper/2506.12481/) (2025)
- [textttAVROBUSTBENCH: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time](https://mlsanity.com/paper/2506.00358/) (2025)
- [EgoBrain: Synergizing Minds and Eyes For Human Action Understanding](https://mlsanity.com/paper/2506.01353/) (2025)
- [Domain Generalization using Action Sequences for Egocentric Action Recognition](https://mlsanity.com/paper/2506.17685/) (2025)
- [CRAM: Large-scale Video Continual Learning with Bootstrapped Compression](https://mlsanity.com/paper/2508.05001/) (2025)
- [CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition](https://mlsanity.com/paper/2503.23447/) (2025)
- [AViS-Mamba: Adaptive Visual Steering of Audio State-Space Dynamics for Violence Detection](https://mlsanity.com/paper/2604.03329/) (2026)

## Abstract (arXiv)

Diverse actions give rise to rich audio-visual signals in long videos. Recent works showcase that the two modalities of audio and video exhibit different temporal extents of events and distinct labels. We address the interplay between the two modalities in long videos by explicitly modelling the temporal extents of audio and visual events. We propose the Time Interval Machine (TIM) where a modality-specific time interval poses as a query to a transformer encoder that ingests a long video input. The encoder then attends to the specified interval, as well as the surrounding context in both modalities, in order to recognise the ongoing action. We test TIM on three long audio-visual video datasets: EPIC-KITCHENS, Perception Test, and AVE, reporting state-of-the-art (SOTA) for recognition. On EPIC-KITCHENS, we beat previous SOTA that utilises LLMs and significantly larger pre-training by 2.9% top-1 action recognition accuracy. Additionally, we show that TIM can be adapted for action detection, using dense multi-scale interval queries, outperforming SOTA on EPIC-KITCHENS-100 for most metrics, and showing strong performance on the Perception Test. Our ablations show the critical role of integrating the two modalities and modelling their time intervals in achieving this performance. Code and models at: https://github.com/JacobChalk/TIM