Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/LanguageBind

LanguageBind

Reported on 8 benchmarks across 3 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing6 results

Relation ExtractiononVinoground
Video Score· 2023-10-03
5
best: 51 (GPT-4o (CoT))
SOTA
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment arXiv:2310.01852
Temporal Relation ExtractiononVinoground
Video Score· 2023-10-03
5
best: 51 (GPT-4o (CoT))
SOTA
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment arXiv:2310.01852
Relation ExtractiononVinoground
Group Score· 2023-10-03
1.2
best: 35 (GPT-4o (CoT))
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment arXiv:2310.01852
Relation ExtractiononVinoground
Text Score· 2023-10-03
10.6
best: 59.2 (GPT-4o (CoT))
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment arXiv:2310.01852
Temporal Relation ExtractiononVinoground
Group Score· 2023-10-03
1.2
best: 35 (GPT-4o (CoT))
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment arXiv:2310.01852
Temporal Relation ExtractiononVinoground
Text Score· 2023-10-03
10.6
best: 59.2 (GPT-4o (CoT))
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment arXiv:2310.01852

Computer Vision2 results

Zero-Shot Action RecognitiononKinetics
Top-1 Accuracy· uses extra data· 2023-10-03
64.1
best: 78.1 (TC-CLIP)
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment arXiv:2310.01852
Zero-Shot Action RecognitiononKinetics
Top-5 Accuracy· uses extra data· 2023-10-03
85.7
best: 95.7 (TC-CLIP)
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment arXiv:2310.01852