Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Multi-Granular Multimodal Clue Fusion for Meme Understanding

Authors: Li Zheng, Hao Fei, Ting Dai, Zuquan Peng, Fei Li, Huisheng Ma, Chong Teng, Donghong Ji

AAAI 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments conducted on the widely-used MET-MEME bilingual dataset demonstrate significant improvements over state-of-the-art baselines. Specifically, there is an 8.14% increase in precision for offensiveness detection task, and respective accuracy enhancements of 3.53%, 3.89%, and 3.52% for metaphor recognition, sentiment analysis, and intention detection tasks.
Researcher Affiliation Academia 1Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China 2National University of Singapore, Singapore, Singapore 3Laboratory for Advanced Computing and Intelligence Engineering, Wuxi, China 4North China Institute of Computing Technology, beijing, China EMAIL EMAIL, EMAIL
Pseudocode No The paper describes its methodology using mathematical formulations and textual explanations but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements about releasing code or provide links to a code repository for the described methodology.
Open Datasets Yes To verify the effectiveness of our model, we conduct experiments on the benchmark MET-MEME bilingual dataset (Xu et al. 2022), which contains both English and Chinese memes.
Dataset Splits No The paper mentions using the MET-MEME bilingual dataset and discusses training, but does not explicitly provide the train/validation/test splits used for their experiments (e.g., specific percentages or sample counts).
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running the experiments.
Software Dependencies No The paper mentions using Multilingual BERT and VGG16 models, but it does not specify any software dependencies with their version numbers (e.g., Python version, PyTorch/TensorFlow versions, or specific library versions).
Experiment Setup No The paper states that the model is trained using a standard gradient descent algorithm and cross-entropy loss, and mentions 'τ is the temperature to scale the logits' as a parameter in the loss function. However, it does not provide specific hyperparameters such as learning rate, batch size, number of epochs, or detailed optimizer settings.