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

Jacob I Chalk, Jaesung Huh, Evangelos Kazakos, Andrew Zisserman, Dima Damen

Research output: Contribution to conferenceConference Paperpeer-review


Diverse actions give rise to rich audio-visual signals in long videos. Recent works showcase that the two modali- ties 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, report- ing 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 recog- nition accuracy. Additionally, we show that TIM can be adapted for action detection, using dense multi-scale inter- val 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 in- tegrating the two modalities and modelling their time inter- vals in achieving this performance.
Original languageEnglish
Publication statusPublished - 21 Jun 2024
EventIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): CVPR - Seattle, United States
Duration: 17 Jun 202421 Jun 2024


ConferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Country/TerritoryUnited States
Internet address


Dive into the research topics of 'TIM: A Time Interval Machine for Audio-Visual Action Recognition'. Together they form a unique fingerprint.

Cite this