YouCook2

Overview edit

Variants: YouCook2

Associated Benchmarks

This dataset is used in 5 benchmarks:

• Video Captioning - Metrics: BLEU-4, BLEU-3, CIDEr, ROUGE-L, METEOR
• Video Retrieval - Metrics: text-to-video R@1, text-to-video R@5, text-to-video R@10, text-to-video Median Rank, text-to-video Mean Rank
• Dense Video Captioning - Metrics: CIDEr, METEOR, SODA, BLEU4, ROUGE-L, F1, Precision, Recall
• Long Video Retrieval (Background Removed) - Metrics: Cap. Avg. R@1, Cap. Avg. R@5, Cap. Avg. R@10, DTW R@1, DTW R@5, DTW R@10, OTAM R@1, OTAM R@5, OTAM R@10
• Zero-Shot Video Retrieval - Metrics: text-to-video R@1, text-to-video R@5, text-to-video R@10, text-to-video Mean Rank, text-to-video Median Rank

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning (2024) -
• Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval (2024) -
• MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding (2024) -
• Multi-granularity Correspondence Learning from Long-term Noisy Videos (2024) -
• OmniVec: Learning robust representations with cross modal sharing (2023) -
• HowToCaption: Prompting LLMs to Transform Video Annotations at Scale (2023) -
• COSA: Concatenated Sample Pretrained Vision-Language Foundation Model (2023) -
• VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset (2023) -
• MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models (2023) -
• Text with Knowledge Graph Augmented Transformer for Video Captioning (2023) -
• Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos (2023) -
• Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning (2023) -
• TempCLR: Temporal Alignment Representation with Contrastive Learning (2022) -
• VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners (2022) -
• OmniVL:One Foundation Model for Image-Language and Video-Language Tasks (2022) -
• Semantic Role Aware Correlation Transformer for Text to Video Retrieval (2022) -
• RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval (2022) -
• MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization (2022) -
• VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding (2021) -
• TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment (2021) -