Projects per year
Our proposed Temporal-Relational CrossTransformers (TRX) achieve state-of-the-art results on few-shot splits of Kinetics, Something-Something V2 (SSv2), HMDB51 and UCF101. Importantly, our method outperforms prior work on SSv2 by a wide margin (12%) due to the its ability to model temporal relations. A detailed ablation showcases the importance of matching to multiple support set videos and learning higher-order relational CrossTransformers.
|Number of pages||8|
|Publication status||Published - 25 Jun 2021|
|Event||Computer Vision and Pattern Recognition 2021 - Online|
Duration: 19 Jun 2021 → 25 Jun 2021
|Conference||Computer Vision and Pattern Recognition 2021|
|Period||19/06/21 → 25/06/21|
FingerprintDive into the research topics of 'Temporal-Relational CrossTransformers for Few-Shot Action Recognition'. Together they form a unique fingerprint.
- 1 Active
1/02/20 → 31/01/25
Susan L Pywell (Manager), Simon A Burbidge (Other), Polly E Eccleston (Other) & Simon H Atack (Other)