Semantic-Guided Multimodal Sentiment Decoding with Adversarial Temporal-Invariant Learning

Code for Semantic-Guided Multimodal Sentiment Decoding with Adversarial Temporal-Invariant Learning (SATI).
Our checkpints can be download from here.

Data Download

• Install CMU Multimodal SDK. Ensure, you can perform from mmsdk import mmdatasdk.
• Option 1: Download pre-computed splits and place the contents inside datasets folder.
• Option 2: Re-create splits by downloading data from MMSDK. For this, simply run the code as detailed next.

Running the code

• cd src
• Set word_emb_path in config.py to glove file and roberta path.
• Set sdk_dir to the path of CMU-MultimodalSDK.
• python train.py --data mosi. Replace mosi with mosei or ur_funny for other datasets.