how to visualize the cross-attention map

jayleicn / moment_detr

[NeurIPS 2021] Moment-DETR code and QVHighlights dataset

https://arxiv.org/abs/2107.09609

MIT License

259 stars 44 forks source link

Open themingcha opened 1 year ago

themingcha commented 1 year ago

I would like to see where the model focuses attention on video features for text queries. How can I visualize the cross-attention heatmap?