List your company
ResearchFormerly WizWand

Visual Dialog on VisDial

62.27MRRAMEM+SEQ-QI
6.31820.84435.3749.896Sep 23, 2017Oct 2, 2018Oct 12, 2019Oct 21, 2020Oct 31, 2021Nov 10, 2022Nov 20, 2023
Updated 8mo ago

Evaluation results

MethodLinks
AMEM+SEQ-QIHistory embedding (+H)=false, Attention mechanism (ATT)=true, Number of parameters=1.7 M (0.7x)2017.0962.2748.5378.6687.434.86
AMEM+SEQ-QIHHistory embedding (+H)=true, Attention mechanism (ATT)=true, Number of parameters=2.3 M (1.0x)2017.0962.148.478.3987.124.92
AMEM-QIHistory embedding (+H)=false, Attention mechanism (ATT)=true, Number of parameters=1.7 M (0.7x)2017.0961.9648.2478.3387.114.92
AMEM-QIHHistory embedding (+H)=true, Attention mechanism (ATT)=true, Number of parameters=2.3 M (1.0x)2017.0961.9248.0578.3987.124.88
MN-QIHHistory embedding (+H)=true, Attention mechanism (ATT)=true, Number of parameters=14.7 M (6.4x)2017.0959.6545.5576.2285.375.46
HREA-QIHHistory embedding (+H)=true, Attention mechanism (ATT)=true, Number of parameters=16.8 M (7.3x)2017.0958.6844.8274.8184.365.66
MN-QHHistory embedding (+H)=true, Attention mechanism (ATT)=false, Number of parameters=12.4 M (5.4x)2017.0958.4944.0375.2684.495.68
HRE-QIHHistory embedding (+H)=true, Attention mechanism (ATT)=true, Number of parameters=16.8 M (7.3x)2017.0958.4644.6774.584.225.72
LF-QIHHistory embedding (+H)=true, Attention mechanism (ATT)=true, Number of parameters=14.5 M (6.3x)2017.0958.0743.8274.6884.075.78
HieCoAtt-QIHistory embedding (+H)=false, Attention mechanism (ATT)=true, Number of parameters=n/a2017.0957.8843.5174.4983.965.84
SAN-QIHistory embedding (+H)=false, Attention mechanism (ATT)=true, Number of parameters=n/a2017.0957.6443.4474.2683.725.88
LF-QIHistory embedding (+H)=false, Attention mechanism (ATT)=true, Number of parameters=10.4 M (4.6x)2017.0957.5943.3374.2783.685.87
HRE-QHHistory embedding (+H)=true, Attention mechanism (ATT)=false, Number of parameters=15.0 M (6.5x)2017.0956.9542.773.2582.976.11
LF-QHHistory embedding (+H)=true, Attention mechanism (ATT)=false, Number of parameters=12.4 M (5.4x)2017.0955.7841.7571.4580.946.74
LF-QHistory embedding (+H)=false, Attention mechanism (ATT)=false, Number of parameters=8.3 M (3.6x)2017.0955.0841.2470.4579.837.08
LION-12Bparameters=12B2023.1150.42————
InstructBLIP (T5XXL)backbone=T5XXL2023.1150.41————
LION-4Bparameters=4B2023.1150.02————
InstructBLIP (T5XL)backbone=T5XL2023.1148.75————
InstructBLIPzero-shot=true, backbone=FlanT5-XXL2023.0548.5————
InstructBLIP+ (T5XXL)backbone=T5XXL, uses_in-house_data=true2023.1148.5————
Flamingo-9Bparameters=9B2023.1148————
BLIP-2zero-shot=true, backbone=FlanT5-XXL2023.0546.9————
InstructBLIPzero-shot=true, backbone=FlanT5-XL2023.0546.6————
InstructBLIP+ (T5XL)backbone=T5XL, uses_in-house_data=true2023.1146.6————
Flamingo-3Bparameters=3B2023.1146.1————
BLIP-2zero-shot=true, backbone=FlanT5-XL2023.0545.7————
BLIVA2023.1145.63————
InstructBLIPzero-shot=true, backbone=Vicuna-13B2023.0545.4————
InstructBLIPzero-shot=true, backbone=Vicuna-7B2023.0545.2————
BLIP-2zero-shot=true, backbone=Vicuna-13B2023.0545.1————
BLIP-2zero-shot=true, backbone=Vicuna-7B2023.0544.9————
Answer priorHistory embedding (+H)=false, Attention mechanism (ATT)=false, Number of parameters=n/a2017.0937.3523.5548.5253.2326.5
MiniGPT4evaluated_by_authors=true2023.1116.52————
LLaVAevaluated_by_authors=true2023.118.65————
MiniGPTV2evaluated_by_authors=true2023.118.47————