Spatio-temporal video grounding using transformers
Bibliographic record
Abstract
The realm of artificial intelligence has witnessed significant advancements, particularly in the fields of Computer Vision and Natural Language Processing. Among the myriad of tasks that have emerged, Spatio-Temporal Video Grounding (STVG) stands out, aiming to align video segments in both spatial and temporal dimensions with corresponding textual descriptions. This thesis delves into the intricacies of STVG, focusing on the challenges of aligning video content with textual descriptions, especially in the face of potential ambiguities present in natural language. Through a comprehensive exploration of the STCAT model, an encoder-decoder Transformer-based STVG architecture, this research investigates modifications to its architecture and evaluates the performance of its variants. The study is underpinned by three pivotal research questions that target the modifications to the Anchor Queries module, alterations to the Attention Unit, and the model's adaptability to varying object and human sizes within datasets. By leveraging state-of-the-art models and methodologies, this research contributes to the ongoing development in the field of video understanding, particularly in STVG. The findings, presented through rigorous quantitative and qualitative analyses, offer insights into the potential enhancements and future directions in the domain.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".