Research map / Video / Video-language understanding
Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding
Yang Jin, yongzhi li, Zehuan Yuan, Yadong MU
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add global template (content query) (ablation) | STCAT · VidSTG declarative | m_vIoU: 29.59 -> 30.54 | Improved |
| add local template (position query) (ablation) | STCAT · VidSTG declarative | m_vIoU: 29.59 -> 31.23 | Improved |
| add both local and global templates (ablation) | STCAT · VidSTG declarative | m_vIoU: 29.59 -> 33.14 | Improved |
| add temporal interaction layer (ablation) | STCAT · VidSTG declarative | m_vIoU: 31.12 -> 33.14 | Improved |
| add both templates (ablation) | STCAT · HC-STVG | m_vIoU: 32.12 -> 35.09 | Improved |
| add temporal interaction layer (ablation) | STCAT · HC-STVG | m_vIoU: 33.64 -> 35.09 | Improved |
| increase input resolution 320 to 448 (ablation) | STCAT · VidSTG declarative | m_vIoU: 31.85 -> 33.14 | Improved |
| increase input resolution from 448 to 480 (ablation) | STCAT · HC-STVG | m_vIoU: 35.09 -> 34.12 | Hurt |
| increase input resolution from 448 to 480 (ablation) | STCAT · VidSTG declarative | m_vIoU: 33.14 -> 32.86 | Hurt |
| replace TubeDETR with STCAT | STCAT · HC-STVG | vIoU@0.5: 23.50 -> 30.09 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- TubeDETR — TubeDETR: Spatio-Temporal Video Grounding With Transformers (CVPR 2022) · better on 7 of 7 shared results
- STVGBert — STVGBert: A Visual-Linguistic Transformer Based Framework for Spatio-Temporal Video Grounding (ICCV 2021) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Context-Guided Spatio-Temporal Video Grounding (CVPR 2024 · similarity 0.92)
- STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding (CVPR 2025 · similarity 0.91)
- Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding (NeurIPS 2025 · similarity 0.91)
- Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding (ICLR 2025 · similarity 0.91)
- VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding (CVPR 2024 · similarity 0.90)
- Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding (ICLR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
