Writing study: TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Jiaming He, Guanyu Hou, Hongwei Li, Zhicong Huang, Kangjie Chen, Yi Yu, Wenbo Jiang, Guowen Xu, Tianwei Zhang · Official CVPR 2026 oral record

Observed writing choices, not acceptance rules. This study examines the inspected manuscript version. It does not establish why the paper was accepted or that its presentation choices should be copied unchanged.

Figure, table and section ledger

Editorial contribution type: Empirical analysis, diagnosis & auditing (primary).

Layout extraction, not a required paper template. Counts are distinct caption labels; a multi-panel figure counts once. Section spans are estimated from heading positions, including floats and whitespace. Method and limitations.

Canonical PDF

10 physical pages

Before references / appendix

≈ 8.13 page-equivalents

Main figures / tables

7 / 3

Attached appendix figures / tables

0 / 0

Attached appendix span

No boundary detected; not assumed zero

Before references / appendix: ≈ 81.3%References / intervening material: ≈ 18.7%Estimated layout envelopes, not text/artwork area. Unresolved appendix boundaries remain within the undivided post-body material.

Extraction notes: No attached appendix boundary detected. Zero means no recognized caption, not independently verified absence.

Section-by-section lengths and source pages

The title/abstract/front matter precede the first numbered heading. A span ends at the next detected top-level heading, not at the last sentence; end-page whitespace is included. References and statements are listed separately. These are not measurements of text-only or artwork area.

Top-level heading	Starts on PDF page	Estimated span	Share of entire PDF
1. Introduction	1	≈ 1.06 pp.	10.6%
2. Related-work	2	≈ 0.41 pp.	4.1%
3. Methodology	2	≈ 2.76 pp.	27.6%
4. Experiments	5	≈ 3.28 pp.	32.8%
5. Conclusion	8	≈ 0.27 pp.	2.7%
References	9	≈ 1.87 pp.	18.7%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 4
• Table 1 · p. 6
• Figure 3 · p. 6
• Table 2 · p. 7
• Figure 4 · p. 7
• Figure 5 · p. 7
• Figure 6 · p. 8
• Figure 7 · p. 8
• Table 3 · p. 8

Attached appendix

No recognized caption labels.

Argument and organization

1. Problem and contribution

   Uses temporal sequences to explain why innocuous text and isolated frames can be insufficient for video safety evaluation.

2. Argument sequence

   Defines the threat model, generator optimization and refinement before separately testing seeded and seed-free generation.

3. Evidence and verification

   Tables 1–2 report category-specific outcomes and prompt-filter pass measures rather than substituting filter bypass for video-level success.

Problem, claim and contribution

Uses temporal sequences to explain why innocuous text and isolated frames can be insufficient for video safety evaluation.

Introduction and Figure 1, p. 1 · Main paper

Argument and section order

Defines the threat model, generator optimization and refinement before separately testing seeded and seed-free generation.

Sections 3–4, pp. 2–7 · Main paper

Figures, captions and visual explanation

Figure 2 separates generator training from test generation, with distinct prompt and video judges and a feedback path.

Figure 2, p. 4 · Main paper

Tables, comparisons and evidence

Tables 1–2 report category-specific outcomes and prompt-filter pass measures rather than substituting filter bypass for video-level success.

Tables 1–2, pp. 6–7 · Main paper

Appendix and reproducibility

No separately listed supplementary file was available in the inventory; the main paper retains generation-setting and transfer analyses but refers to further appendix material.

Sections 4.2–4.3, pp. 6–8 · Main paper

Clarity and writing conventions

Seed-free generation and commercial-service effectiveness are named as distinct result claims rather than merged into one success rate.

Section 4.2, pp. 6–7 · Main paper

What to reuse—and what not to infer

Transferable lesson: Define success at every stage of a multistage evaluation; distinguish passed prompts, generated outputs and judged target outcomes.

Boundary: API-dependent outcomes are tied to the tested model versions, evaluators and query protocol; do not present them as timeless system properties.

Apply this lesson using the argument and evidence worksheet.

Inspection record and sources

Checked

2026-09-26

Reading status

Writing-focused manuscript scan + selected visuals inspected

Main text

Writing-oriented scan throughout Sections 1–5, PDF pp. 1–8; references pp. 9–10: abstract/framing, section sequence, figure/table captions, evaluation organization and conclusions; not an exhaustive technical verification.

Appendix / supplement

No separate supplement is listed in the official corpus inventory; appendix references in the text do not establish a retrieved appendix.

Visually inspected PDF pages

4, 6

This is a writing-focused scan of the manuscript and the stated supplementary scope: framing, organization, visual explanation, evidence presentation and wording. It is not a line-by-line proof audit, reproduction of results or exhaustive scientific review.

• Official CVF open-access CVPR 2026 accepted-paper PDF · 10 pages