AI Paper Atlas

Research map / Benchmarks / VATEX text-to-video

VATEX text-to-video leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VATEX text-to-video. Best R@1: 68.4 (NarVid, CVPR 2025).

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.

VATEX text-to-video · R@1

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

#R@1 ↑MethodPaperTopic
168.4NarVid
CLIP ViT-B/16
Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions
CVPR 2025 · Table 2
Video-language understanding
267.5AVIGATE
CLIP ViT-B/16
Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval
CVPR 2025 · Table 2
Video-language understanding
366.6Cap4Video
CLIP ViT-B/16
Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?
CVPR 2023 · Table: VATEX results
Video-language understanding
466.5VidLA-B/32
CLIP ViT-B/32
VidLA: Video-Language Alignment at Scale
CVPR 2024 · Table 3
Video-language understanding
565.6T-MASS
CLIP-ViT-B/16
Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval
CVPR 2024 · Table 2
Video-language understanding
664ProST (ViT-B/16)
CLIP ViT-B/16
Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval
ICCV 2023 · Table 4
Video-language understanding
762.5VideoPrism-g
VideoPrism-g
VideoPrism: A Foundational Visual Encoder for Video Understanding
ICML 2024 · Table: zero-shot video-text re
Video-language understanding
861.1UCoFiA
CLIP ViT-B/32
Unified Coarse-to-Fine Alignment for Video-Text Retrieval
ICCV 2023 · Table 1
Video-language understanding
959.1TS2-Net
CLIP ViT-B/32
TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval
ECCV 2022 · Table 5
Video-language understanding
1057.5STOP
CLIP-ViT-B/32
STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding
CVPR 2025 · Table 3
Video-language understanding

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