List your company

Action Anticipation on Epic-Kitchen 55 (val)

22.7Top-1 AccS-GEAR
5.11369.679314.24518.8107May 26, 2021Mar 12, 2022Dec 27, 2022Oct 13, 2023Jul 29, 2024May 15, 2025Mar 2, 2026

Evaluation results

MethodLinks
S-GEARModalities=RGB+Obj+Flow2024.0722.743.2———————
Our modelBackbone=Resnet18(2D+1D), Temporal gap (dt)=1.0s, Input modalities=rgb+optical flow+object, Losses=JVS, JCC, JFIP2021.0520.3539.15———————
AVHNTemporal gap (dt)=1.0s2021.0519.2935.91———————
Ego-OMGModalities=RGB+HOI+NAO2024.0719.2————————
DCRModalities=RGB+Obj+Flow2024.0719.241.2———————
AVT+Modalities=RGB+Obj2024.0716.637.6———————
AGABackbone=Swin-B, Resolution=224x2242026.0316.337.4——————16.6
S-GEARModality=RGB, Encoder=irCSN, Initialization=IG65M2024.0716.233.1———————
S-GEARBackbone=irCSN1522026.0316.233.1———————
DCRModality=RGB, Encoder=TSM, Initialization=K4002024.0716.133.1———————
DCRBackbone=TSM2026.0316.133.1———————
S-GEARModality=RGB, Encoder=ViT-B, Initialization=IN21K2024.0715.834.5———————
S-GEARBackbone=ViT-B2026.0315.834.5———————
S-GEARModality=RGB, Encoder=TSN, Initialization=IN1K2024.0715.632.8———————
S-GEARBackbone=TSN, Resolution=384x3842026.0315.632.8———————
RU-LSTMModalities=RGB+Obj+Flow2024.0715.335.3———————
ImaginationModalities=RGB+Obj+Flow2024.0715.235.4———————
TempAgg.Modalities=RGB+Obj+Flow2024.0715.135.6———————
DCRBackbone=irCSN1522026.0315.134———————
AVTModality=RGB, Encoder=irCSN, Initialization=IG65M2024.0714.431.7———————
DCRModality=RGB, Encoder=irCSN, Initialization=IG65M2024.0714.434———————
AVT-hBackbone=irCSN1522026.0314.431.7——————13.2
FIATemporal gap (dt)=1.0s2021.0514.0733.37———————
RAFTformerBackbone=TSN2026.0313.8————————
ImagineRNNBackbone=TSN2026.0313.731.6———————
DCRModality=RGB, Encoder=TSN, Initialization=IN1K2024.0713.630.8———————
DCRBackbone=TSN2026.0313.630.8———————
AGABackbone=TSN, Resolution=224x2242026.0313.532.1——————14.3
RULSTMbackbone=TSN2022.0513.1————————
AVTbackbone=TSN2022.0513.1————————
RU LSTMModality=RGB, Encoder=TSN, Initialization=IN1K2024.0713.130.8———————
AVTModality=RGB, Encoder=TSN, Initialization=IN1K2024.0713.128.1———————
RULSTMBackbone=TSN2026.0313.130.8——————12.5
AVT-hBackbone=TSN2026.0313.128.1——————13.5
AVTModality=RGB, Encoder=ViT-B, Initialization=IN21K2024.0712.530.1———————
AVT-hBackbone=AVT-b2026.0312.530.1——————13.6
S-GEARModality=Obj, Encoder=FRCNN, Initialization=IN1K2024.0712.4530.4———————
Temporal Agg.backbone=TSN2022.0512.3————————
FUTRbackbone=TSN2022.0512.3————————
TempAggBackbone=TSN2026.0312.328.5——————13.1
DCRModality=Obj, Encoder=FRCNN, Initialization=IN1K2024.0711.530.5———————
SVM-TOP3Temporal gap (dt)=1.0s2021.0511.0925.42———————
S-GEARModality=Flow, Encoder=TSN, Initialization=IN1K2024.0710.825.8———————
BaselineBackbone=Resnet18(2D+1D), Temporal gap (dt)=1.0s, Input modalities=rgb+optical flow+object2021.0510.4425.63———————
RULSTMModality=Obj, Encoder=FRCNN, Initialization=IN1K2024.071029.8———————
DCRModality=Flow, Encoder=TSN, Initialization=IN1K2024.078.922.7———————
RULSTMModality=Flow, Encoder=TSN, Initialization=IN1K2024.078.721.4———————
VN-CETemporal gap (dt)=1.0s2021.055.7917.31———————
ActionBanks2021.06——35.88023.452.815.135.6—
ATSN2021.06———77.3—39.9—16.3—
AVT+backbone=irCSN-152, late fusion=true2021.06——32.579.924.45416.637.6—
DMR2021.06———73.7—30—16.9—
ED2021.06———75.5—43—25.8—
EL2021.06———75.7—43.7—28.6—
FHOIbackbone=I3D2021.06——30.776.517.442.610.425.5—
FN2021.06———74.8—40.9—26.3—
HROModalities=RGB+Obj+Flow2024.07—37.4———————
ImagineRNN2021.06———————35.6—
MCE2021.06———73.4—38.9—26.1—
RLTemporal gap (dt)=1.0s2021.05—29.61———————
RL2021.06———76.8—44.5—29.6—
RU LSTMTemporal gap (dt)=1.0s2021.05—35.32———————
RULSTM2021.06——32.479.623.551.815.335.3—
SRLModality=RGB, Encoder=TSN, Initialization=IN1K2024.07—31.7———————
SRLModalities=RGB+Obj+Flow2024.07—35.5———————
SRLBackbone=TSN2026.03—31.7——————13.2