| HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling | ✓ Link | 59.59 | 48.99 | | | 83.75 | 74.28 | | HieraMamba (extra data) | 2025-10-27 |
| CVA: Context-aware Video-text Alignment for Video Temporal Grounding | | 58.80 | 43.21 | 27.73 | | | | 41.07 | CVA (extra data) | 2026-03-26 |
| Saliency-Guided DETR for Moment Retrieval and Highlight Detection | ✓ Link | 58.10 | 46.40 | 33.90 | | | | 42.40 | SG-DETR (w/ PT) | 2024-10-02 |
| LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection | ✓ Link | 57.61 | 44.31 | 26.24 | | | | 40.30 | LD-DETR | 2025-01-18 |
| DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos | ✓ Link | 57.36 | 46.79 | | 81.05 | 71.13 | | | DeCafNet | 2025-05-22 |
| Saliency-Guided DETR for Moment Retrieval and Highlight Detection | ✓ Link | 56.71 | 44.70 | 29.90 | | | | 40.90 | SG-DETR | 2024-10-02 |
| BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos | ✓ Link | 56.69 | 41.54 | 26.77 | | | | 39.31 | BAM-DETR | 2023-11-30 |
| SnAG: Scalable and Accurate Video Grounding | ✓ Link | 56.44 | 44.86 | | | 81.15 | 70.66 | | SnAG | 2024-04-02 |
| FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding | ✓ Link | 53.71 | 41.76 | 24.74 | | | | 37.61 | FlashVTG | 2024-12-18 |
| Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval | ✓ Link | 52.73 | 40.12 | 22.78 | | | | 36.55 | LLMEPET | 2024-07-21 |
| Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding | ✓ Link | 52.23 | 39.61 | 22.23 | | | | 36.48 | CG-DETR | 2023-11-15 |
| UniVTG: Towards Unified Video-Language Temporal Grounding | ✓ Link | 51.44 | 34.97 | 21.07 | | | | 35.76 | UniVTG | 2023-07-31 |
| SE-DETR: Explicit Semantic Exploration for Generalizability and Distinguishability in Video Temporal Grounding | ✓ Link | 50.6 | 39.2 | 22.6 | | | | 36.2 | SE-DETR+ | 2026-09-08 |
| Background-aware Moment Detection for Video Moment Retrieval | ✓ Link | 50.46 | 35.87 | | | | | | BM-DETR (C3D + BERT) (extra data) | 2023-06-05 |
| Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding | ✓ Link | 50.2 | 37.3 | 19.4 | | | | 33.9 | SRAM-Base | 2024-08-29 |
| VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning | ✓ Link | 49.5 | 36.2 | 21.4 | | | | 34.4 | VideoMind 7B (extra data) | 2025-03-17 |
| Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos | ✓ Link | 48.29 | 36.07 | | | | | | GVL (paragraph-level) | 2023-03-11 |
| Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos | ✓ Link | 45.92 | 34.57 | | | | | | GVL | 2023-03-11 |
| VLG-Net: Video-Language Graph Matching Network for Video Grounding | ✓ Link | 45.46 | 34.19 | | 81.80 | 70.38 | 56.56 | | VLG-Net | 2020-11-19 |
| Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection | ✓ Link | | 36.39 | 23.32 | | | | | UVCOM | 2023-11-28 |