Dense Video Captioning on ActivityNet Captions (val)
16.1METEORESG module
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| ESG moduleProposal source=GT events, Training set=Enlarged2020.06 | 16.1 | — | — | — | — | — | — | — | — | |
| Re-rankingProposal source=GT proposals2020.06 | 15 | 25.84 | 13.77 | 6.6 | 2.93 | 42.86 | — | — | — | |
| ESG moduleProposal source=GT events, Training set=Official2020.06 | 15 | — | — | — | — | — | — | — | — | |
| METEOR.SCProposal source=GT proposals2020.06 | 14.53 | 26.16 | 13.8 | 6.49 | 2.85 | 47.29 | — | — | — | |
| CIDEr.SCProposal source=GT proposals2020.06 | 13.75 | 26.94 | 14.29 | 6.75 | 2.94 | 53.58 | — | — | — | |
| SDVCProposal source=GT proposals2020.06 | 13.07 | 28.02 | 12.05 | 4.41 | 1.28 | 43.48 | — | — | — | |
| Cross-entropyProposal source=GT proposals2020.06 | 12.42 | 24.76 | 13.05 | 6.43 | 3.22 | 54.1 | — | — | — | |
| ESG moduleProposal source=Generated events, Training set=Enlarged2020.06 | 12.27 | — | — | — | — | — | — | — | — | |
| Re-rankingProposal source=generated proposals2020.06 | 11.28 | 16.59 | 9.65 | 5.32 | 2.91 | 14.03 | — | — | — | |
| ESG moduleProposal source=Generated events, Training set=Official2020.06 | 11.28 | — | — | — | — | — | — | — | — | |
| METEOR.SCProposal source=generated proposals2020.06 | 10.7 | 15.6 | 8.82 | 4.87 | 2.59 | 13.28 | — | — | — | |
| CIDEr.SCProposal source=generated proposals2020.06 | 10.38 | 17.91 | 10.18 | 5.57 | 2.88 | 20.44 | — | — | — | |
| Cross-entropyProposal source=generated proposals2020.06 | 9.39 | 16.65 | 9.4 | 5.35 | 3.05 | 20.91 | — | — | — | |
| PDVCLive=false, Features=TSP2024.06 | 9.03 | — | — | — | 2.17 | — | — | — | — | |
| Mun et al. (RL)Dataset visibility=Seen full dataset, Optimization strategy=Reinforcement Learning (RL), Proposal type=learned proposals2020.03 | 8.82 | — | — | — | — | — | — | — | — | |
| SDVCProposal source=generated proposals2020.06 | 8.82 | 17.92 | 7.99 | 2.94 | 0.93 | 30.68 | — | — | — | |
| Mun et al.RL optimization=true, Full Dataset available=true2020.05 | 8.82 | — | — | 2.94 | 0.93 | — | — | — | — | |
| JEDDi-Nettraining_strategy=joint training, context=with context2018.02 | 8.58 | 19.97 | 9.1 | 4.06 | 1.63 | 19.88 | 19.63 | — | — | |
| PDVC lightLive=false, Features=TSP2024.06 | 8.55 | — | — | — | 1.77 | — | — | — | — | |
| Vid2SeqLive=false, Features=CLIP2024.06 | 8.5 | — | — | — | — | — | — | — | — | |
| Vid2seqPre-training=YT-Temporal-1B2024.03 | 8.5 | — | — | — | — | 30.1 | 52.7 | 53.9 | 5.8 | |
| Bi-modal Transformer (BMT)RL optimization=false, Full Dataset available=false2020.05 | 8.44 | — | — | 3.84 | 1.88 | — | — | — | — | |
| JEDDi-Nettraining_strategy=joint training2018.02 | 8.3 | 19.27 | 8.69 | 3.78 | 1.54 | 19.81 | 18.86 | — | — | |
| PDVC lightLive=false, Features=TSN2024.06 | 7.97 | — | — | — | 1.66 | — | — | — | — | |
| PDVCLive=false, Features=TSN2024.06 | 7.96 | — | — | — | 1.78 | — | — | — | — | |
| OmniViD2024.03 | 7.54 | — | — | — | 1.73 | 26 | 45.08 | 60.43 | 5.6 | |
| PDVCLive=false, Features=C3D2024.06 | 7.5 | — | — | — | 1.65 | — | — | — | — | |
| PDVC2024.03 | 7.5 | — | — | — | 1.65 | 25.87 | 55.42 | 58.07 | 5.3 | |
| Iashin et al.RL optimization=false, Full Dataset available=false2020.05 | 7.46 | — | — | 2.53 | 1.01 | — | — | — | — | |
| JEDDi-Nettraining_strategy=separate training2018.02 | 7.37 | 16.72 | 6.65 | 2.65 | 1.07 | 14.65 | 16.47 | — | — | |
| MDVCDataset visibility=Seen part of the dataset, Data completeness=no missings, Proposal type=learned proposals2020.03 | 7.31 | — | — | — | — | — | — | — | — | |
| PDVC lightLive=false, Features=C3D2024.06 | 7.11 | — | — | — | 1.51 | — | — | — | — | |
| Xiong (RL)Dataset visibility=Seen full dataset, Optimization strategy=Reinforcement Learning (RL), Proposal type=learned proposals2020.03 | 7.08 | — | — | — | — | — | — | — | — | |
| Xiong et al.RL optimization=true, Full Dataset available=true2020.05 | 7.08 | — | — | 2.84 | 1.24 | — | — | — | — | |
| Li et al.RL optimization=true, Full Dataset available=true2020.05 | 6.93 | — | — | 2.27 | 0.73 | — | — | — | — | |
| DVC2024.03 | 6.93 | — | — | — | 0.73 | 12.61 | — | — | — | |
| Mun et al. (without RL)Dataset visibility=Seen full dataset, Optimization strategy=without RL, Proposal type=learned proposals2020.03 | 6.92 | — | — | — | — | — | — | — | — | |
| Mun et al.RL optimization=false, Full Dataset available=true2020.05 | 6.92 | — | — | — | — | — | — | — | — | |
| SDVC2024.03 | 6.92 | — | — | — | — | — | 55.58 | 57.57 | — | |
| Zhou et al.RL optimization=false, Full Dataset available=true2020.05 | 6.91 | — | — | 2.91 | 1.44 | — | — | — | — | |
| Li et al.RL optimization=false, Full Dataset available=true2020.05 | 6.14 | — | — | 2.05 | 0.74 | — | — | — | — | |
| Wang et al.RL optimization=false, Full Dataset available=true2020.05 | 6.1 | — | — | 2.27 | 1.13 | — | — | — | — | |
| TDA-CG2024.03 | 5.86 | — | — | — | 1.31 | 7.99 | — | — | — | |
| Krishna et al.RL optimization=false, Full Dataset available=true2020.05 | 5.69 | — | — | 1.9 | 0.71 | — | — | — | — | |
| DCE2024.03 | 5.69 | — | — | — | 0.17 | 12.43 | — | — | — | |
| Rahman et al.RL optimization=false, Full Dataset available=false2020.05 | 4.93 | — | — | 1.85 | 0.9 | — | — | — | — | |
| R. Krishna et al.context=with context2018.02 | 4.82 | 17.95 | 7.69 | 3.86 | 2.2 | 17.29 | — | — | — | |
| R. Krishna et al.context=no context2018.02 | 3.76 | 12.23 | 3.48 | 2.1 | 0.88 | 12.34 | — | — | — | |
| LVCLive=true, Delta t=150, Features=TSP2024.06 | 1.56 | — | — | — | 2.01 | — | 2.08 | — | — | |
| LVCLive=true, Delta t=120, Features=TSP2024.06 | 1.27 | — | — | — | 1.55 | — | 1.63 | — | — | |
| LVCLive=true, Delta t=96, Features=TSP2024.06 | 1.03 | — | — | — | 1.21 | — | 1.29 | — | — | |
| LVCLive=true, Delta t=72, Features=TSP2024.06 | 0.75 | — | — | — | 0.85 | — | 0.91 | — | — | |
| LVCLive=true, Delta t=48, Features=TSP2024.06 | 0.45 | — | — | — | 0.47 | — | 0.51 | — | — | |
| LVCLive=true, Delta t=24, Features=TSP2024.06 | 0.14 | — | — | — | 0.13 | — | 0.15 | — | — | |
| UEDVC2024.03 | — | — | — | — | — | — | 59 | 60.32 | 5.5 | |
| Vid2seqPre-training=None2024.03 | — | — | — | — | — | 18.8 | — | — | 5.4 |