List your company

Video Captioning on YouCook2 (test)

190CIDErUniVL + MELTR
2.17650.93899.7148.462Nov 25, 2021Feb 27, 2022Jun 2, 2022Sep 4, 2022Dec 8, 2022Mar 12, 2023Jun 15, 2023

Evaluation results

MethodLinks
UniVL + MELTRModality=V+T2023.0319017.9247.0422.56—24.12
UniVLModality=V+T2023.0318117.3546.5222.35—23.87
UniVL#VideoPT=1.2M, ASR=Yes, Evaluation Protocol=Fine-tuning2022.05176.816.645.721.6106.2—
Pretrained FT SOTAFT=true, Shot=10K2022.04138.7—————
UniVL + MELTRModality=V2023.0313811.9841.2818.19—17.35
COSA (1.2B)Parameters=415M2023.06131.310.1————
GIT2Parameters=12.9B2023.06131.29.4————
VALUEParameters=136M, Additional modalities=true2023.06130.312.4————
GITParameters=1.7B2023.06129.810.3————
UniVLModality=V2023.0312711.1740.0917.57—16.46
UniVL#VideoPT=1.2M, ASR=No, Evaluation Protocol=Fine-tuning2022.0512711.240.117.670.2—
COSA-LParameters=417M2023.06125.810.2————
Flamingo(80B)Parameters=2.3B2023.06118.6—————
AT+VideoModality=V+T2023.03112—36.6517.77—9.01
VidIL#VideoPT=0, ASR=Yes, Evaluation Protocol=Few-shot, Num Shots=102022.05111.610.735.919.475.3—
SWINBERTframes=642021.11109—————
COSA-BParameters=17M2023.06106.28.6————
COSA-BParameters=5M2023.06100.97.8————
FlamingoFT=false, Shot=322022.0486.8—————
Flamingo-80B#VideoPT=27M, ASR=No, Evaluation Protocol=Few-shot, Num Shots=162022.0584.2—————
Flamingo-9BFT=false, Shot=322022.0477.3—————
Flamingo-3BFT=false, Shot=322022.0476.7—————
FlamingoFT=false, Shot=42022.0474.5—————
Flamingo-3B#VideoPT=27M, ASR=No, Evaluation Protocol=Few-shot, Num Shots=162022.0573.2—————
Flamingo-9BFT=false, Shot=42022.0470.8—————
ActBERTModality=V2023.03655.4130.5613.3—8.66
Flamingo-3BFT=false, Shot=42022.0464.6—————
CBTModality=V2023.03645.1230.4412.97——
FlamingoFT=false, Shot=02022.0460.1—————
COOTModality=V2023.035711.337.9419.85—17.97
Flamingo-3BFT=false, Shot=02022.0455.8—————
Flamingo-9BFT=false, Shot=02022.0455—————
VideoBERTModality=V+T2023.03554.3328.811.94—7.59
SOTA2021.1153.6—————
UniVL#VideoPT=1.2M, ASR=Yes, Evaluation Protocol=Few-shot, Num Shots=102022.0548.64.326.412.226—
VideoBERTModality=V2023.03473.8127.1410.81—6.33
EMTModality=V2023.03384.3827.4411.55—7.53
UniVL#VideoPT=1.2M, ASR=No, Evaluation Protocol=Few-shot, Num Shots=102022.0534.13.325.311.613.3—
VidIL#VideoPT=0, ASR=No, Evaluation Protocol=Few-shot, Num Shots=102022.05272.622.99.533.3—
Zero/Few shot SOTAFT=false, Shot=02022.0411.6—————
BLIP#VideoPT=0, ASR=No, Evaluation Protocol=Few-shot, Num Shots=102022.0511.50.793.423.9—
BLIP_cap#VideoPT=0, ASR=No, Evaluation Protocol=Few-shot, Num Shots=102022.059.43.78.63.822.8—
DPCModality=V+T2023.03—2.76—18.08—7.6