SOTAVerified

Video Captioning

Video Captioning is a task of automatic captioning a video by understanding the action and event in the video which can help in the retrieval of the video efficiently through text.

Source: NITS-VC System for VATEX Video Captioning Challenge 2020

Papers

Showing 251275 of 473 papers

TitleStatusHype
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations0
Crowd Video Captioning0
CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning0
Deep Reinforcement Learning for NLP0
Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols0
Dense Video Captioning using Graph-based Sentence Summarization0
Describe Anything: Detailed Localized Image and Video Captioning0
DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement0
Directed Domain Fine-Tuning: Tailoring Separate Modalities for Specific Training Tasks0
Discourse Analysis for Evaluating Coherence in Video Paragraph Captions0
Diverse Video Captioning Through Latent Variable Expansion0
Dual-Level Decoupled Transformer for Video Captioning0
DVCFlow: Modeling Information Flow Towards Human-like Video Captioning0
E-MMAD: Multimodal Advertising Caption Generation Based on Structured Information0
Empirical Autopsy of Deep Video Captioning Frameworks0
Encoder-Decoder Based Long Short-Term Memory (LSTM) Model for Video Captioning0
End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering0
End-to-end Dense Video Captioning as Sequence Generation0
End-to-end Dense Video Captioning as Sequence Generation0
End-to-end Generative Pretraining for Multimodal Video Captioning0
Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization0
Evaluation of Automatic Video Captioning Using Direct Assessment0
EVC-MF: End-to-end Video Captioning Network with Multi-scale Features0
Event-Equalized Dense Video Captioning0
EVLM: An Efficient Vision-Language Model for Visual Understanding0
Show:102550
← PrevPage 11 of 19Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1mPLUG-2CIDEr80Unverified
2VASTCIDEr78Unverified
3GIT2CIDEr75.9Unverified
4VLABCIDEr74.9Unverified
5COSACIDEr74.7Unverified
6VALORCIDEr74Unverified
7MaMMUT (ours)CIDEr73.6Unverified
8VideoCoCaCIDEr73.2Unverified
9RTQCIDEr69.3Unverified
10HowToCaptionCIDEr65.3Unverified
#ModelMetricClaimedVerifiedStatus
1MaMMUTCIDEr195.6Unverified
2VLABCIDEr179.8Unverified
3COSACIDEr178.5Unverified
4VALORCIDEr178.5Unverified
5mPLUG-2CIDEr165.8Unverified
6HowToCaptionCIDEr154.2Unverified
7HiTeACIDEr146.9Unverified
8Vid2SeqCIDEr146.2Unverified
9VIOLETv2CIDEr139.2Unverified
10RTQCIDEr123.4Unverified
#ModelMetricClaimedVerifiedStatus
1VASTBLEU-418.2Unverified
2UniVL + MELTRBLEU-417.92Unverified
3UniVLBLEU-417.35Unverified
4VideoCoCaBLEU-414.2Unverified
5VLMBLEU-412.27Unverified
6E2vidD6-MASSvid-BiDBLEU-412.04Unverified
7TextKGBLEU-411.7Unverified
8COOTBLEU-411.3Unverified
9COSABLEU-410.1Unverified
10HowToCaptionBLEU-48.8Unverified
#ModelMetricClaimedVerifiedStatus
1VALORBLEU-445.6Unverified
2VASTBLEU-445Unverified
3COSABLEU-443.7Unverified
4VideoCoCaBLEU-439.7Unverified
5IcoCap (ViT-B/16)BLEU-437.4Unverified
6IcoCap (ViT-B/32)BLEU-436.9Unverified
7VASTA (Kinetics-backbone)BLEU-436.25Unverified
8CoCap (ViT/L14)BLEU-435.8Unverified
9ORG-TRLBLEU-432.1Unverified
10NITS-VCBLEU-420Unverified
#ModelMetricClaimedVerifiedStatus
1VideoCoCaBLEU414.7Unverified
2VLTinT (ae-test split) C3D/LingBLEU414.5Unverified
3VLCap (ae-test split) - Appearance + LanguageBLEU413.38Unverified
4COOT (ae-test split) - Only Appearance featuresBLEU410.85Unverified
5MART (ae-test split) - Appearance + FlowBLEU410.33Unverified
#ModelMetricClaimedVerifiedStatus
1CENCIDEr49.87Unverified
2GITCIDEr32.43Unverified
3SEM-POSCIDEr26.01Unverified
4AKGNNCIDEr25.9Unverified
#ModelMetricClaimedVerifiedStatus
1CENCIDEr63.51Unverified
2GITCIDEr45.63Unverified
3SEM-POSCIDEr37.16Unverified
4AKGNNCIDEr35.08Unverified
#ModelMetricClaimedVerifiedStatus
1SBD_KeyframeBLEU441.01Unverified
2V+S-Att-basedBLEU436.2Unverified
#ModelMetricClaimedVerifiedStatus
1VASTBLEU-419.9Unverified
2COSABLEU-418.8Unverified
#ModelMetricClaimedVerifiedStatus
1GVTBLEU417.7Unverified
#ModelMetricClaimedVerifiedStatus
1VNS-GRU (Cross-Lingual)BLEU-458.68Unverified
#ModelMetricClaimedVerifiedStatus
1Shot2StoryCIDEr37.4Unverified
#ModelMetricClaimedVerifiedStatus
1Vid2SeqCIDEr120.5Unverified