DMFLC: Short Video Classification Based on Deep Multimodal Feature Fusion and Low Rank Representation
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
<title>Abstract</title> With the rise of short videos on social media platforms, short video recommendation technology has become an important research area in artificial intelligence and big data analysis. The unique features of short videos, including textual, image, and speech information, make multimodal content analysis crucial for accurate recommendation results. In this paper, we propose a deep learning-based classification algorithm that incorporates audio, visual, and text modalities for short video classification. The proposed algorithm aims to overcome the limitations of existing feature fusion methods by considering both common and private parts between different modal features. In this paper, we propose a classification algorithm based on deep multimodal feature fusion for short videos, and build a network based on audio modality, visual modality and text modality using the consistency and low-rank representation of multi-view features. The similarity loss function is used to explore the similarity of features extracted from different modalities by the public domain network, and the difference loss function is used to explore the difference of features extracted from the same modal private domain network and public domain network, and the classification loss is used to guide the classification of global video features. We evaluate the performance of the proposed algorithm on a public dataset and compare it with state-of-the-art approaches. The experimental results demonstrate that our algorithm achieves superior classification accuracy and outperforms existing approaches.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it