SOTAVerified

Text to Video Retrieval

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 75 papers

TitleStatusHype
X^2-VLM: All-In-One Pre-trained Model For Vision-Language TasksCode2
Revealing Single Frame Bias for Video-and-Language LearningCode2
Prototype-based Aleatoric Uncertainty Quantification for Cross-modal RetrievalCode1
Multimodal Clustering Networks for Self-supervised Learning from Unlabeled VideosCode1
MDMMT: Multidomain Multimodal Transformer for Video RetrievalCode1
Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video RetrievalCode1
GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and RetrievalCode1
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip RetrievalCode1
LAVENDER: Unifying Video-Language Understanding as Masked Language ModelingCode1
MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text RetrievalCode1
Less is More: ClipBERT for Video-and-Language Learning via Sparse SamplingCode1
Advancing High-Resolution Video-Language Representation with Large-Scale Video TranscriptionsCode1
DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy MinimizationCode1
Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and DataCode1
Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video RetrievalCode1
An Empirical Study of End-to-End Video-Language Transformers with Masked Visual ModelingCode1
ECLIPSE: Efficient Long-range Video Retrieval using Sight and SoundCode1
Clover: Towards A Unified Video-Language Alignment and Fusion ModelCode1
End-to-End Learning of Visual Representations from Uncurated Instructional VideosCode1
Condensed Movies: Story Based Retrieval with Contextual EmbeddingsCode1
HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video ClipsCode1
Holistic Features are almost Sufficient for Text-to-Video RetrievalCode1
Bridging Video-text Retrieval with Multiple Choice QuestionsCode1
Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalCode1
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation ModelsCode1
Show:102550
← PrevPage 1 of 3Next →
All datasetsKinetics-GEB+MSR-VTTMSVD-Indonesian

Benchmark Results

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