{"id":18832949,"url":"https://github.com/declare-lab/misa","last_synced_at":"2025-10-04T08:25:44.451Z","repository":{"id":41496431,"uuid":"272608979","full_name":"declare-lab/MISA","owner":"declare-lab","description":"MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis","archived":false,"fork":false,"pushed_at":"2023-03-14T15:13:34.000Z","size":234,"stargazers_count":229,"open_issues_count":0,"forks_count":33,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-10T03:52:06.191Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/declare-lab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-06-16T04:25:34.000Z","updated_at":"2025-04-06T15:02:12.000Z","dependencies_parsed_at":"2022-07-20T05:00:23.381Z","dependency_job_id":"885ec2fd-947f-45b0-b196-3727d2414928","html_url":"https://github.com/declare-lab/MISA","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/declare-lab%2FMISA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/declare-lab%2FMISA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/declare-lab%2FMISA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/declare-lab%2FMISA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/declare-lab","download_url":"https://codeload.github.com/declare-lab/MISA/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248154998,"owners_count":21056542,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-08T01:59:38.285Z","updated_at":"2025-10-04T08:25:39.407Z","avatar_url":"https://github.com/declare-lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis\nCode for the [ACM MM 2020](https://2020.acmmm.org) paper [MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis](https://arxiv.org/pdf/2005.03545.pdf)\n\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"600\" src=\"misa-pic.png\"\u003e\n\u003c/p\u003e\n\n\n\n### Setup the environment\n\nWe work with a conda environment.\n\n```\nconda env create -f environment.yml\nconda activate misa-code\n```\n\n### Data Download\n\n- Install [CMU Multimodal SDK](https://github.com/A2Zadeh/CMU-MultimodalSDK). Ensure, you can perform ```from mmsdk import mmdatasdk```.    \n- Option 1: Download [pre-computed splits](https://drive.google.com/drive/folders/1IBwWNH0XjPnZWaAlP1U2tIJH6Rb3noMI?usp=sharing) and place the contents inside ```datasets``` folder.     \n- Option 2: Re-create splits by downloading data from MMSDK. For this, simply run the code as detailed next.\n\n### Running the code\n\n1. ```cd src```\n2. Set ```word_emb_path``` in ```config.py``` to [glove file](http://nlp.stanford.edu/data/glove.840B.300d.zip).\n3. Set ```sdk_dir``` to the path of CMU-MultimodalSDK.\n2. ```python train.py --data mosi```. Replace ```mosi``` with ```mosei``` or ```ur_funny``` for other datasets.\n\n### Citation\n\nIf this paper is useful for your research, please cite us at:\n\n```\n@article{hazarika2020misa,\n  title={MISA: Modality-Invariant and-Specific Representations for Multimodal Sentiment Analysis},\n  author={Hazarika, Devamanyu and Zimmermann, Roger and Poria, Soujanya},\n  journal={arXiv preprint arXiv:2005.03545},\n  year={2020}\n}\n```\n\n### Contact\n\nFor any questions, please email at [hazarika@comp.nus.edu.sg](mailto:hazarika@comp.nus.edu.sg)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeclare-lab%2Fmisa","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeclare-lab%2Fmisa","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeclare-lab%2Fmisa/lists"}