# Video Temporal Grounding on ActivityNet g43\_s12 (test) Source: [Video Temporal Grounding on ActivityNet g43\_s12 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-10T08:20:54.007Z Evaluation of Video Temporal Grounding performance on the specific ActivityNet subset g43\_s12 (test split), measured using Recall thresholds (R@0.3, R@0.5, R@0.7) and mean IoU (mIoU). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Video Temporal Grounding | | Dataset (including any stated split) | ActivityNet g43\_s12 (test) | | Metric | Recall@0.5 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Recall@0.5](): Higher is better; unit: PERCENT. - [Recall@0.3](): Higher is better; unit: PERCENT. - [Recall@0.7](): Higher is better; unit: PERCENT. - [mIoU](): Higher is better; unit: PERCENT. ## Recorded results | Method | Recall@0.5 | Result date | Report paper | | --- | --- | --- | --- | | Qwen2-VL-7B + T2SGrid-FT | 48.4 | Not recorded | 69afa5642d603e6de3e43841 | | TRACE | 37.7 | Not recorded | 69afa5642d603e6de3e43841 | | NumPro | 37.5 | Not recorded | 69afa5642d603e6de3e43841 | | GPT-4o + T2SGrid | 32.1 | Not recorded | 69afa5642d603e6de3e43841 | | HawkEye | 29.3 | Not recorded | 69afa5642d603e6de3e43841 | | VTimeLLM | 27.8 | Not recorded | 69afa5642d603e6de3e43841 | | Qwen2-VL-7B + T2SGrid | 27.2 | Not recorded | 69afa5642d603e6de3e43841 | | Qwen3-VL-8B + T2SGrid | 26.8 | Not recorded | 69afa5642d603e6de3e43841 | | Momentor | 26.6 | Not recorded | 69afa5642d603e6de3e43841 | | Qwen3-VL-8B | 26.2 | Not recorded | 69afa5642d603e6de3e43841 | | LITA | 25.9 | Not recorded | 69afa5642d603e6de3e43841 | | GPT-4o | 21.2 | Not recorded | 69afa5642d603e6de3e43841 | | LLaVA-OneVision-1.5-8B + T2SGrid | 17.4 | Not recorded | 69afa5642d603e6de3e43841 | | TimeChat | 16.9 | Not recorded | 69afa5642d603e6de3e43841 | | Qwen2-VL-7B | 9.4 | Not recorded | 69afa5642d603e6de3e43841 | | LLaVA-OneVision-1.5-8B | 4.9 | Not recorded | 69afa5642d603e6de3e43841 | ### Qwen2-VL-7B + T2SGrid-FT Recall@0.5: 48.4. Result ID: 69afd4636dbb7075b9581dd2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid-FT"}. This record does not assert independent reproduction. ### TRACE Recall@0.5: 37.7. Result ID: 69afd4636dbb7075b9581dc8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### NumPro Recall@0.5: 37.5. Result ID: 69afd4636dbb7075b9581dc9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### GPT-4o + T2SGrid Recall@0.5: 32.1. Result ID: 69afd4636dbb7075b9581dcb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid"}. This record does not assert independent reproduction. ### HawkEye Recall@0.5: 29.3. Result ID: 69afd4636dbb7075b9581dc7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### VTimeLLM Recall@0.5: 27.8. Result ID: 69afd4636dbb7075b9581dc5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### Qwen2-VL-7B + T2SGrid Recall@0.5: 27.2. Result ID: 69afd4636dbb7075b9581dd1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid"}. This record does not assert independent reproduction. ### Qwen3-VL-8B + T2SGrid Recall@0.5: 26.8. Result ID: 69afd4636dbb7075b9581dcd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid"}. This record does not assert independent reproduction. ### Momentor Recall@0.5: 26.6. Result ID: 69afd4636dbb7075b9581dc6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Recall@0.5: 26.2. Result ID: 69afd4636dbb7075b9581dcc. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs"}. This record does not assert independent reproduction. ### LITA Recall@0.5: 25.9. Result ID: 69afd4636dbb7075b9581dc3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### GPT-4o Recall@0.5: 21.2. Result ID: 69afd4636dbb7075b9581dca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs"}. This record does not assert independent reproduction. ### LLaVA-OneVision-1.5-8B + T2SGrid Recall@0.5: 17.4. Result ID: 69afd4636dbb7075b9581dcf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs","Framework":"T2SGrid"}. This record does not assert independent reproduction. ### TimeChat Recall@0.5: 16.9. Result ID: 69afd4636dbb7075b9581dc4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"VTG-Tuned Vision-LLMs"}. This record does not assert independent reproduction. ### Qwen2-VL-7B Recall@0.5: 9.4. Result ID: 69afd4636dbb7075b9581dd0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs"}. This record does not assert independent reproduction. ### LLaVA-OneVision-1.5-8B Recall@0.5: 4.9. Result ID: 69afd4636dbb7075b9581dce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"General Vision-LLMs"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.