{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:31Z","timestamp":1778051551330,"version":"3.51.4"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00741","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7679-7688","source":"Crossref","is-referenced-by-count":0,"title":["MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction"],"prefix":"10.1109","author":[{"given":"Akshit","family":"Sharma","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Guwahati"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prashant W","family":"Patil","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Guwahati"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The llama 3 herd of models","volume-title":"Technical report","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00303"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.avb.2021.101608"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"ref6","author":"Dosovitskiy","year":"2021","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-025-01475-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref9","article-title":"Gemini: A family of highly capable multimodal models","volume-title":"Technical Report","year":"2023"},{"key":"ref10","article-title":"Gemma Team","author":"Kamath","year":"2025","journal-title":"Gemma 3 technical report"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3641249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2022.06.010"},{"key":"ref13","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Advances in neural information processing systems","volume":"33","author":"Kiela"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592254"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlp4pi-1.20"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.63317\/4jaa3afu4u68"},{"key":"ref17","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Li"},{"key":"ref18","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref19","author":"Li","year":"2019","journal-title":"Visualbert: A simple and performant baseline for vision and language"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","first-page":"6397","article-title":"Prompt-enhanced network for hateful meme classification","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-2024","author":"Liu"},{"key":"ref22","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Advances in neural information processing systems","volume":"32","author":"Lu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17745"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714778"},{"key":"ref25","author":"Meng","year":"2025","journal-title":"Mm-eureka: Exploring visual aha moment with rule-based large-scale reinforcement learning"},{"key":"ref26","article-title":"Gpt-4 technical report","volume-title":"Technical Report","year":"2023"},{"key":"ref27","article-title":"Lmm-r1: Empowering 3b lmms with strong reasoning abilities through two-stage rule-based rl","author":"Peng","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/mti5070034"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","volume":"139","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref33","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","volume-title":"NeurIPS 2021 Workshop on Datasets and Benchmarks","author":"Schuhmann"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.959"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.289"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.157"},{"key":"ref37","first-page":"4567","article-title":"Hateful content detection using visualbert and roberta for antisemitic and sexist memes","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Sudarshan"},{"key":"ref38","first-page":"32","article-title":"Multimodal meme dataset (multi-off) for identifying offensive content in image and text","volume-title":"Proceedings of the 2nd Workshop on Trolling, Aggression and Cyberbullying","author":"Suryawanshi"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s42001-020-00087-4"},{"key":"ref40","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref43","article-title":"Mm-rlhf: The next step forward in multimodal llm alignment","author":"Zhang","year":"2025"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492499.pdf?arnumber=11492499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:17:33Z","timestamp":1778048253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00741","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}