List your company

Relation Detection on VRD (test)

63.4R@50GPS-Net
-2.463214.635931.73548.8341Feb 27, 2017Dec 14, 2017Oct 1, 2018Jul 19, 2019May 5, 2020Feb 20, 2021Dec 8, 2021

Evaluation results

MethodLinks
GPS-Netshared object detector=true, backbone pre-training=COCO2020.0363.4———————————————
GPS-Netshared object detector=true, backbone pre-training=ImageNet2020.0358.7———————————————
MF-URLN2020.0358.2———————————————
CAI + SCA-Mshared object detector=true2020.0356———————————————
KL distillation2020.0355.2———————————————
Ours [S+A] + LanguageSupervision=Full sup., Method components=[S+A] + Language2017.0752.6———————————————
Zoom-Netshared object detector=true2020.0350.7———————————————
Ours [S+A]Supervision=Full sup., Method components=[S+A]2017.0750.4———————————————
Language (full)Supervision=Full sup.2017.0748.4———————————————
Visual + LanguageSupervision=Full sup.2017.0747.9———————————————
Ours [S+A]Supervision=Weak sup., Method components=[S+A]2017.0746.8———————————————
Ours [S+A] - NoisySupervision=Weak sup., Method components=[S+A] - Noisy2017.0746.4———————————————
Ours [A]Supervision=Full sup., Method components=Appearance [A]2017.0746.3———————————————
VTransE2020.0344.8———————————————
Ours [S]Supervision=Full sup., Method components=Spatial [S]2017.0742.2———————————————
GPS-Netshared object detector=true, backbone pre-training=COCO2020.0327.831.7——————————————
RelDNshared object detector=true2020.0325.328.6——————————————
MF-URLN2020.0323.926.8——————————————
Yu et. alExternal data=true2019.0122.6831.89——————————————
GPS-Netshared object detector=true, backbone pre-training=ImageNet2020.0321.524.3——————————————
VidVRD-IIVisual Feature=RoI, Motion Feature=true2021.1219.6322.92—————————————29.37
CAI + SCA-Mshared object detector=true2020.0319.522.4——————————————
VTransE2020.0319.422.4——————————————
KL distillation2020.0319.221.3——————————————
BLOCKExternal data=false2019.0119.0620.96——————————————
Zoom-Netshared object detector=true2020.0318.921.4——————————————
VRL2020.0318.220.8——————————————
Language (likelihood)Supervision=Full sup.2017.0718.2———————————————
VRLZero-shot=false2017.0318.1920.79——————————————
Liang et. alExternal data=false2019.0118.1920.79——————————————
Dai et. alExternal data=false2019.0117.7320.88——————————————
Li et. alExternal data=false2019.0117.3220.01——————————————
ViP-CNN2020.0317.320——————————————
Ours [S+A] + LanguageSupervision=Full sup., Method components=[S+A] + Language2017.0715.8———————————————
Peyre et. alExternal data=false2019.0115.817.1——————————————
Ours [S+A]Supervision=Full sup., Method components=[S+A]2017.0714.9———————————————
BIG-CVisual Feature=RoI (using tracklets/features from MEGA), Motion Feature=true2021.1214.116.25—————————————26.08
Ours [S+A]Supervision=Weak sup., Method components=[S+A]2017.0714.1———————————————
VTransEModel type=end-to-end2017.0214.0715.2——————————————
Zhang et. alExternal data=false2019.0114.0715.2——————————————
Visual + LanguageSupervision=Full sup.2017.0713.9———————————————
Language (full)Supervision=Full sup.2017.0713.9———————————————
Lu’s-VLKObject detector=R-CNN, Language priors=word2vec2017.0213.8614.7——————————————
Lu et al.Zero-shot=false2017.0313.8614.7——————————————
Lu et. alExternal data=false2019.0113.8614.7——————————————
Chen et al.Visual Feature=RoI+I3D, Motion Feature=true2021.1213.7316.88—————————————20.08
Ours [S+A] - NoisySupervision=Weak sup., Method components=[S+A] - Noisy2017.0713.4———————————————
VTransE-2stageModel type=two-stage, Object detector=Faster-RCNN2017.0213.314.64——————————————
Ours [A]Supervision=Full sup., Method components=Appearance [A]2017.0712.9———————————————
IVRDVisual Feature=RoI, Motion Feature=true2021.1212.414.46—————————————22.97
Ours [S]Supervision=Full sup., Method components=Spatial [S]2017.0712.4———————————————
Liu et al.Visual Feature=RoI+I3D (using tracklets/features from [24]), Motion Feature=true2021.1211.2113.69—————————————18.38
BIG-CVisual Feature=RoI+I3D (using tracklets/features from [24]), Motion Feature=false2021.129.6311.29—————————————17.67
BIG-CVisual Feature=RoI (using tracklets/features from [24]), Motion Feature=false2021.129.5910.92—————————————17.56
MHAVisual Feature=iDT, Motion Feature=true2021.129.5310.38—————————————19.03
Liu et al.Visual Feature=RoI+I3D (using tracklets/features from [24]), Motion Feature=false2021.129.1411.39—————————————14.81
TRACEVisual Feature=RoI+I3D, Motion Feature=false2021.129.0811.15—————————————17.57
Liu et al.Visual Feature=RoI (using tracklets/features from [24]), Motion Feature=false2021.128.4711—————————————14.01
VRD-GCNVisual Feature=iDT, Motion Feature=true2021.128.079.33—————————————16.26
VRLZero-shot=true2017.037.948.52——————————————
TRACEVisual Feature=RoI, Motion Feature=false2021.127.6710.32—————————————15.06
Random2017.027.141.43——————————————
VisualSupervision=Full sup.2017.077.1———————————————
GSTEGVisual Feature=iDT, Motion Feature=true2021.127.058.67—————————————9.52
VidVRDVisual Feature=iDT, Motion Feature=false2021.125.546.37—————————————8.58
Faster R-CNN V only2017.034.265.9——————————————
Lu et al.Zero-shot=true2017.033.133.28——————————————
Joint CNN+Trained RPN2017.031.982.22——————————————
VisualSupervision=Full sup.2017.071.6———————————————
Lu’s-VObject detector=R-CNN2017.021.581.85——————————————
Lu et al. V only2017.031.581.85——————————————
Joint CNN+RPN2017.031.151.17——————————————
Visual PhrasesSupervision=Full sup.2017.070.9———————————————
Language (likelihood)Supervision=Full sup.2017.070.08———————————————
Joint CNN+R-CNN2017.030.070.09——————————————
CAI + SCA-MObject Detector=same as [16]2020.03——————————5619.522.425.228.9—
CAI+SCA-MPretrained=ImageNet2020.03————5656——————————
CAI+SCA-MPretrained=ImageNet2020.03————22.419.5——28.522.3——————
GPS-NetBackbone=VGG-16 (ImageNet), Object Detector=same as [16]2020.03——————————58.721.524.328.934—
GPS-NetBackbone=VGG-16 (COCO), Object Detector=same as [16]2020.03——————————63.427.831.733.839.2—
GPS-NetPretrained=ImageNet2020.03————58.758.7——————————
GPS-NetPretrained=COCO2020.03————63.463.4——————————
GPS-NetPretrained=ImageNet2020.03————24.321.5——28.923.6——————
GPS-NetPretrained=COCO2020.03————31.727.8——3730.6——————
Joint CNNTraining images=VRD only2017.07————0.090.07——————————
KL distillation2020.03——————————55.219.221.323.124—
KL distillationPretrained=Unknown2020.03————55.255.2——————————
KL distillationPretrained=Unknown2020.03————21.319.2——31.922.7——————
Language (full)Supervision=Full sup.2017.07——48.412.9————————————
Language (full)Supervision=Full sup.2017.07——15.35.1————————————
Language (likelihood)Supervision=Full sup.2017.07——18.25.1————————————
Language (likelihood)Supervision=Full sup.2017.07——0.080.01————————————
Linguistic CuesTraining images=VRD only2017.07——————18.3715.08————————
MF-URLN2020.03——————————58.223.926.831.536.1—
MF-URLNPretrained=Unknown2020.03————58.258.2——————————
MF-URLNPretrained=Unknown2020.03————26.823.9——————————
Ours [A]Supervision=Full sup., Features=Appearance2017.07——46.316.1————————————
Ours [A]Supervision=Full sup., Features=Appearance2017.07——14.45.4————————————
Ours [S]Supervision=Full sup., Features=Spatial2017.07——42.222.2————————————
Ours [S]Supervision=Full sup., Features=Spatial2017.07——13.58.1————————————