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].
Counterfactual Thinking Driven Emotion Regulation for Image Sentiment Recognition
Authors: Xinyue Zhang, Zhaoxia Wang, Hailing Wang, Guitao Cao
IJCAI 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 4 Experiments 4.1 Datasets and the Evaluation Metric The experiments were conducted on datasets of various scales, including Flickr and Instagram (FI) [You et al., 2016], Emotion6 [Peng et al., 2016], Art Photo [Machajdik and Hanbury, 2010; Yang et al., 2018b], and Twitter II [Borth et al., 2013; Zhang et al., 2024]. Like all other ISR works, we utilize classification accuracy for evaluation. 4.2 Implementation Details 4.3 Comparisons on Multi-class Datasets 4.4 Comparisons on Binary-class Datasets 4.5 Ablation Studies |
| Researcher Affiliation | Academia | 1Shanghai Institute of Artificial Intelligence for Education, East China Normal University 2Mo E Engineering Research Center of SW/HW Co-design Technology and Application, East China Normal University 3Shanghai Key Laboratory of Trustworthy Computing, East China Normal University 4School of Computing and Information Systems, Singapore Management University EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes the methodology using textual explanations and mathematical equations, such as Equation (1) for multi-scale convolutional filters and Equation (2) for attentional deployment, but it does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper describes the proposed CTERNet and mentions implementing it using the PyTorch framework, but it does not provide any explicit statement about releasing the code or a link to a code repository for the described methodology. |
| Open Datasets | Yes | The experiments were conducted on datasets of various scales, including Flickr and Instagram (FI) [You et al., 2016], Emotion6 [Peng et al., 2016], Art Photo [Machajdik and Hanbury, 2010; Yang et al., 2018b], and Twitter II [Borth et al., 2013; Zhang et al., 2024]. |
| Dataset Splits | No | For dataset processing, we set the input image size to 448 × 448. Data augmentation on the training set included random cropping, random horizontal flipping, and image normalization. For the test set, we applied center cropping and image normalization. The paper mentions |
| Hardware Specification | Yes | All experiments were implemented on NVIDIA Geforce RTX 2080 Ti GPUs. |
| Software Dependencies | No | In terms of model architecture, we utilized a Res2Net-101 [Gao et al., 2019] pre-trained on the Image Net dataset, implemented using the Py Torch framework, to parameterize the feature extraction network. While PyTorch is mentioned, a specific version number is not provided. |
| Experiment Setup | Yes | For dataset processing, we set the input image size to 448 × 448. Data augmentation on the training set included random cropping, random horizontal flipping, and image normalization. For the test set, we applied center cropping and image normalization. We used the SGD optimizer with a learning rate of 0.0001 and a momentum of 0.9. The learning rate was decayed by a factor of 0.1 every 10 epochs. |