View-Association-Guided Dynamic Multi-View Classification
Authors: Xinyan Liang, Li Lv, Qian Guo, Bingbing Jiang, Feijiang Li, Liang Du, Lu Chen
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 4 Experiments 4.1 Datasets Our experiments are conducted on six challenging multi-view classification datasets which include image, text, audio, depth and video datasets. ... 4.2 Experimental Results with Other Methods ... 4.3 Further Analysis Ablation Experiments. ... Parameter Sensitive Analysis. ... Different Weight Strategies. |
| Researcher Affiliation | Academia | Xinyan Liang1 , Li Lv1 , Qian Guo2 , Bingbing Jiang3 , Feijiang Li1 , Liang Du1 and Lu Chen1 1Institute of Big Data Science and Industry, Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, Shanxi University, Taiyuan 030006, China 2 Shanxi Key Laboratory of Big Data Analysis and Parallel Computing, School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China 3 School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes the proposed method using figures (Figure 1, Figure 2) and mathematical formulations (Equations 1-13) but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code or links to code repositories. |
| Open Datasets | Yes | 4.1 Datasets Our experiments are conducted on six challenging multi-view classification datasets which include image, text, audio, depth and video datasets. (1) Animals with Attributes (AWA)[Lampert et al., 2013] dataset... (2) NUS-WIDE128 (NUS)[Tang et al., 2016] dataset... (3) Reuters [Amini et al., 2009] dataset... (4) Vox Celeb [Nagrani et al., 2020] dataset... (5) Youtube Face dataset, which includes 3,425 videos from 1,595 different people with five view features. According to [Wang et al., 2022b], we use a subset of 31 categories from this dataset, with a total of 101,499 frames. |
| Dataset Splits | Yes | The results in Tables 1, are presented through the mean metric value and the standard deviation obtained from 5-fold cross-validation. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x). |
| Experiment Setup | Yes | For the proposed Asso DMVC, in order to make the model elegant and lightweight, we set each module to contain one or two fully connected layer, and the number of neurons in the fully connected layer is selected from [128, 256]. We initialize the learnable parameters ϵ in GIN by 0. ... f (t+1) represents a neural network consisting of two fully connected layers, followed by Batch Normalization and a Leaky Re LU activation function. ... a two-layer fully connected network is used to transform the view association embeddings into guiding vectors: ... L = Lce + λLle, where Lle is the view association embedding loss, λ is a trade-off parameter... |