A Review of Deep Learning for Video Captioning
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
Video captioning (VC) is a fast-moving, cross-disciplinary area of research that comprises contributions from domains such as computer vision, natural language processing, linguistics, and human-computer interaction. VC aims to understand a video and describe it through natural language descriptors. It plays a crucial role in various applications, from improving accessibility features such as low-vision navigation to advancing video question answering, video retrieval, and content generation. In this survey paper, we present a comprehensive review of deep learning-based VC methods. First, we provide an overview of VC, including the problem formulation, evaluation metrics, training losses, and attention-based architectures. Then, we categorize VC methods into several categories, including attention-based architectures graph networks, reinforcement learning, adversarial networks, and dense video captioning, and discuss each category in detail. In addition, we review existing data sets for VC methods and provide a discussion of research gaps and future research directions. We hope that this survey serves as a guide for researchers in relevant fields.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 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