Update TIM.md

_publications/TIM.md

@@ -13,5 +13,5 @@ Diverse actions give rise to rich audio-visual signals in long videos. Recent wo
 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].
 
 [Project Webpage](https://jacobchalk.github.io/TIM-Project) |
-[Paper](https://arxiv.org/pdf/2302.00646.pdf) |
+[Paper](https://arxiv.org/pdf/2404.05559) |
 [Source Code](https://github.com/JacobChalk/TIM)