pengfei-luo / MIMIC

[KDD 2023] Multi-Grained Multimodal Interaction Network for Entity Linking
18 stars 3 forks source link

Problem on the CLIP Method Baseline #6

Open DAISYzxy opened 2 months ago

DAISYzxy commented 2 months ago

Hi Pengfei,

I have noticed that the results of baseline CLIP in the paper Table 1 are very high compared to what I have realized. Specifically, I use the exactly same dataset in this repo. I cannot find the details of how you implement this CLIP method in your paper. Do you just concatenate multimodal CLIP features and calculates the similarity? Or add another small model like MLP after concatenation by CLIP and train the model to get such results? Could you provide more details of this? Thank you so much!