HyperAIHyperAI

Command Palette

Search for a command to run...

Schätzung von Pose und Aktion

Abschätzung der Körperhaltung des Menschen (Positionen der Schlüsselpunkte) und Erkennung menschlicher Aktionen oder Aktivitäten aus Bildern oder Videos.

Leaderboard

Insgesamt 66 Modelle

Benchmarks

something-something-v2
MSNet-R50En (8+16 ensemble, ImageNet pretrained)
charades
TokenLearner
kinetics-600
MViT-B-24, 32x3
COCO test-dev
HigherHRNet (HR-Net-48)
hico-det
CDN (ResNet101)
hmdb51
MSQNet
Kinetics-Skeleton dataset
PoseC3D (SlowOnly-346)
AVA v2.2
VideoMAE (K700 pretrain+finetune, ViT-L, 16x4)
kinetics-700
ActivityNet-1.3
AVFusion
COCO
CholecT50 (Challenge)
Team Trequartista
AFLW2000
OpNet
N-UCLA
DSCNet (RGB + Pose)
NTU RGB+D 120
Diving-48
Volleyball
activitynet
Text4Vis (w/ ViT-L)
AP-10K
CrowdPose
PoseTrack2017
breakfast
thumos-14
3C-Net
HMDB51 (finetuned)
BraVe:V-FA (TSM-50x2)
Human-Art
Deep-Fashion
DIOR
AIC
coco-val2017
MogaNet-B (384x288)
DHG-14
RWTH-PHOENIX-Weather 2014 T
MSKA-SLT
sbu
ISTA-Net
AViD
TokenLearner
COCO-WholeBody
fineaction
BMN (i3d feaure)
Assembly101
EV-Action
TCN (Skeleton Kinect)
MPII Multi-Person
AlphaPose
NTU RGB+D
NTU RGB+D 60
SYSU 3D
SGN
CAD-120
csl-daily
TwoStream-SLT
HICO
DEFR
Human3.6M
LineMOD
HRNet+DSNT+BPnP
Multi-THUMOS
MLAD
NTU RGB+D 120
MotionBERT (Finetune)
wlasl-2000
crosstask
VideoCLIP
DHG-28
FPPR-PCD
Florence 3D
IEMOCAP-4
PATHOSnet v2
PASCAL-Part
CDCL+Pascal
PKU-MMD
TriMouse-161
BUCTD-CoAM-W48 (DLCRNet)
UT-Kinect
Temporal Subspace Clustering
WLASL100
Youtube INRIA Instructional
HVQ
4d-dress
Graphonomy_Inner
aflw
MNN
charades-ego
LaViLa (Finetuned, TimeSformer-L)
COCO test-challenge
MSPN+*
Collective Activity
Gaming 3D (G3D)
MSR Daily Activity3D dataset
NTU-120
NTU-60
NTU Hand Digit
GestureGAN
PoseTrack2018
RWF-2000
Senz3D
CholecT45 (cross-val)
COCO minival
HRNet-W48plus
egogesture
ResNeXt-101
H2O
ikea-asm
HVQ
NVGesture
MTUT
NW-UCLA
PoPArt
HRNet-w32
300W-Face
Animal Kingdom
AVA-Speech
CNN-BiLSTM_best
bar
Carfusion
CholecT50 (cross-val)
DAAD
DF2
egoexolearn
Action anticipation baseline (co-training, with gaze)
Fish-100
Fly
FPHA
H2O (2 Hands and Objects)
CHASE(STSA-Net)
HDM05
Humans-5K
KPT-5
MacaquePose
Marmoset-8K
msr-action3d
Temporal K-Means Clustering + Temporal Subspace Clustering
OneHand10K
PoseTrack21
SALSA
SubdivNet
THUMOS' 14
MAT (Ours) Trans
ut
VIVA Hand Gestures Dataset
MTUT
WLASL
ActivityNet-1.2
W-TALC
Airport
Animal Kingdom
behave
bit
Brain4Cars
ChaLearn val
cholect45
Rendezvous
COCO Val
CoRA
Countix
RepNet
Disease
egtea
Filtered NTU RGB+D
GTA-IM Dataset
Xing et al.
Kinetics-Skeleton
LboroHAR
LSA16
MAMEM-SSVEPII
market-1501
Progressive Pose Attention
mpi-sintel
MPII
MSRC-12
NTU-RGB+D 120
NTU60
OAD dataset
ESTIE + VGG16 (transfer-learning)
pamap2
Selective HAR Clustering
PKU-MMD II
PubMed
Real Life Violence Situations Dataset
DeVTr
RepCount
ESCounts
thumos14
3C-Net
TTStroke-21 ME22
RGB and PRGB
UPenn Action
UNIK
UWA3D
VA-fusion (aug.)
WEAR
50-salads
TOT+TCL
AIDE
Ambiguious-HOI
DJ-RN
BRACE
HRNet fine-tuned on BRACE
Café
cambridge
Key Frames + Feature Fusion
COCO val2017
COCO 2017 val
LOGO-CAP (Ours) HRNet-W48
COCO-UniHuman
CrowdPose testing set
DensePose-COCO
Parsing R-CNN + ResNext101
Diving48
DNA-Rendering dataset
Drive&Act
dyalyt
EHPT-XC
ExLPose-test
har
LMSS
ICVL-4
iemocap
CORECT (4-class)
industreal
B3
IRD
JHMDB (2D poses only)
DD-Net
jrdb
Kinetics-200
Kinetics-400
Mimetics
JMRN
miniSports
Mo-capade3.0
MSASL
muses
TemporalMaxer
NMFs-CSL
NoW
NTU-RGB+D 60
NTU-RGBD 120
NTU-RGBD 60
Nurse Care Activity Recognition Challenge
OCCLUSION
Single-shot Deep CNN
OCHuman
okutama-action
Penn Action
PoseTrack2021
RWTH-PHOENIX Handshapes dev set
DenseNet
Slovo
TCG-dataset
Bidirectional LSTM
TTStroke-21 ME21
uav-human
AlphaPose
ucf101
R3D-18
UCFRep
ESCounts
v-coco
QPIC + CPC
3DGait
3DPW
50-Salads
ActEV
Next
ade20k
SCAM
AirDOS Shibuya [34]
amass
Animal-Pose Dataset
SuperAnimal-AnimalTokenPose
APT-36K
ASLG-PC12
Transformer Ens.
BEAHM
BJUT-3D
Ours DLDL (KL)
Bonn [31]
Bonn crowd2
Briareo
BUAA
cape
CapgMyo DB-a
2SRNN
CapgMyo DB-b
CapgMyo DB-c
CASME II
celebv-hq
ChaLean test
8-MFFs-3f1c
ChaLearn 2013
3S Net TTM
Chalearn 2014
3D-CNN + LSTM
ChaLearn 2016
Challenging-PoseTrack
CholecT40
Tripnet
CholecT50(cross-val)
CIFAR-10-LT (IF=100)
CIFAR-100-LT (IF=100)
CMU Mocap
ODMO
CMU-MOSEI-Sentiment
CMU-MOSEI-Sentiment-3
GraphSmile
CMU Multi-Modal Activity (CMU-MMAC)
CMU Panoptic + 300W-LP
6DRepNet360
COCO
CMU-Pose
Composite
CSDD
DogCentric
VTFSA
drone-action
EGait
emdb
Emilya
EPIC Fields
epic-kitchens
EWalk
ExLPose-LL-E
DA-LLPose
ExLPose-LL-H
ExLPose-LL-N
ExLPose-OCN
ExLPose-OCN-A7M3
ExLPose-OCN-RICOH3
FDMSE-ISL
HWGAT
FineGYM
HDD
Hockey
HumanAct12
HuPR
ImageNet-LT
JAAD_all
Jester test
Kinetics
Kinetics-400-LT
LIBRAS-UFOP
MA-Gait
meccano
SlowFast
Mediapi-RGB
Transformer Baseline
meld
GraphSmile
MELD-Sentiment
MEXaction2
S-CNN
MGB
F-BLSTM
MICA
MINDS-Libras
MiniKinetics
MARS+RGB+Flow (16 frames)
Mixamo
MM-Fi
MM-WLAuslan
MMEW
MMHPSD
Montalbano
Temp Conv + LSTM
MPI-INF-3DHP
Pr-VIPE
ms-coco
UniHCP (finetune)
MSR ActionPairs
Temporal Subspace Clustering
MTV-Test
multithumos
NBA
Ninapro DB-1 12 gestures
Ninapro DB-1 8 gestures
Northwestern-UCLA
Northwestern University
NTU 120
NTU 60
NTU-120-LT
NTU-60-LT
NTU-C 60 xsub
NTU-Inter
NTU-Inter 120
NTU120
NVGesture
pascal-context
PASCAL-Person-Part
DPC
PDGait
PIE
Pointing'04
Ours DLDL (KL)
Posetics
PoseTrack2017 Val Set
PoseTrack2018 Val Set
PoseTrack2021 Val Set
ProGait
proprietary cattle behavior dataset
PSI
RA-GAR
Real-World
rocog-v2
SAMM
SBU
LSTM-IRN'fc1inter+intra
Skeleton-Mimetics
SmartWatch
SMG
SMIC
Sub-JHMDB
SUN-Mem
TIP-sum PPM-GGM-DDM-DF
Surreal
THP-F
THUMOS14
Toyota Smarthome
Toyota Smarthome dataset
Trans4SOAR (Pose)
TransHuPR
TST
ucf-101
R3D-18
UCF 101
UESTC RGB-D
ODMO
unseen activities
utd-mhad
VIENA^2
ViMo
WAF
Generative Partition Networks
XRF55
ZJU-Mocap dataset