Instructional Temporal Answer Grounding in Video on TutorialVQA (test)
60.31R@0.3CACR
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| CACRFamily=LVLM, Training Setting=supervised2026.06 | 60.31 | 43.65 | 28.72 | 43.65 | |
| MutualSLFamily=VLP, Training Setting=supervised2026.06 | 60.14 | 43.59 | 28.28 | 43.48 | |
| VTPSLFamily=VLP, Training Setting=supervised2026.06 | 50.07 | 40.01 | 25.79 | 40.2 | |
| TimescopeFamily=LVLM, Training Setting=supervised2026.06 | 26.01 | 12.9 | 5.24 | 18.59 | |
| MoRSFamily=VLP, Training Setting=supervised2026.06 | 23.45 | 15.01 | 8.55 | 19.48 | |
| TimeZeroFamily=LVLM, Training Setting=zero-shot2026.06 | 22.9 | 10.01 | 4.35 | 18.44 | |
| Time-R1Family=LVLM, Training Setting=supervised2026.06 | 22.15 | 13.98 | 7.97 | 19.95 | |
| TFVTGFamily=LVLM, Training Setting=zero-shot2026.06 | 19.34 | 9.16 | 4.58 | 13.58 | |
| VTG-R1Family=LVLM, Training Setting=supervised2026.06 | 18.28 | 9.89 | 3.79 | 14.38 | |
| ACRMFamily=VLP, Training Setting=supervised2026.06 | 12.61 | 11.37 | 1.26 | 11.12 | |
| VSLNetFamily=VLP, Training Setting=supervised2026.06 | 11.03 | 9.93 | 0.66 | 9.58 | |
| VSLBaseFamily=VLP, Training Setting=supervised2026.06 | 10.84 | 9.58 | 0.37 | 8.71 | |
| TMLGAFamily=VLP, Training Setting=supervised2026.06 | 10.39 | 9.24 | 0.34 | 8.65 | |
| Qwen2.5-VL-7B-InstructFamily=LVLM, Training Setting=zero-shot2026.06 | 7.9 | 3.85 | 2.12 | 5.39 | |
| Random Mode2026.06 | 6.53 | 2.46 | 0 | 5.26 | |
| GPT-3.5Family=LLM, Training Setting=zero-shot2026.06 | 2.33 | 0 | 0 | 1.18 | |
| GPT-3.5 (CoT)Family=LLM-CoT, Training Setting=zero-shot2026.06 | 0.33 | — | 0 | 1.13 |