AI Paper Atlas

Research map / Benchmarks / VidSTG declarative

VidSTG declarative leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VidSTG declarative. Best m_vIoU: 35.09 (CoSTA, AAAI 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

VidSTG declarative · m_vIoU

10 papers, each with its best reported number for its own method; higher is better.

#m_vIoU ↑MethodPaperTopic
135.09CoSTACoSTA: End-to-End Comprehensive Space-Time Entanglement for Spatio-Temporal Video Grounding
AAAI 2024 · Table 4
Video-language understanding
234CG-STVGContext-Guided Spatio-Temporal Video Grounding
CVPR 2024 · Table 3
Video-language understanding
333.7OursCollaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding
CVPR 2023 · Table 2
Video-language understanding
423.97STVGBertSTVGBert: A Visual-Linguistic Transformer Based Framework for Spatio-Temporal Video Grounding
ICCV 2021 · Table 1
Video-language understanding
519.75STGRNWhere Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences
CVPR 2020 · Table: Performance Evaluation
Video-language understanding
618Ours (LLaVA-OneVision-7B)
LLaVA-OneVision-7B
Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding
NeurIPS 2025 · Table 1
Video-language understanding
716.21E3M (zero-shot)
CLIP ViT-B/32
E3M: Zero-Shot Spatio-Temporal Video Grounding with Expectation-Maximization Multimodal Modulation
ECCV 2024 · Table 1
Video-language understanding
816CoSPaL
Grounding DINO
Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding
ICLR 2025 · Table: Comparison with existin
Video-language understanding
915.93TubeRMCTubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding
AAAI 2026 · Table 1
Video-language understanding
1015.52STPro
Grounding DINO
STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding
CVPR 2025 · Table 2
Video-language understanding

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.