SOTAVerified

Text to Video Retrieval

She's gone I can't find her anywhere I'm looking everywhere for her Everywhere is dark

Papers

Showing 1120 of 75 papers

TitleStatusHype
Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video RetrievalCode1
VindLU: A Recipe for Effective Video-and-Language PretrainingCode1
An Empirical Study of End-to-End Video-Language Transformers with Masked Visual ModelingCode1
Partially Relevant Video RetrievalCode1
Clover: Towards A Unified Video-Language Alignment and Fusion ModelCode1
LAVENDER: Unifying Video-Language Understanding as Masked Language ModelingCode1
Revisiting the "Video" in Video-Language UnderstandingCode1
MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text RetrievalCode1
ECLIPSE: Efficient Long-range Video Retrieval using Sight and SoundCode1
GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and RetrievalCode1
Show:102550
← PrevPage 2 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FROZEN-revisedmAP23.39Unverified
2FROZEN-revised (two-stream)text-to-video R@112.8Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP4Cliptext-to-video R@144.5Unverified
#ModelMetricClaimedVerifiedStatus
1X-CLIP (Cross-Lingual)R@132.3Unverified