姿态与动作估计

MSNet-R50En (8+16 ensemble, ImageNet pretrained)

TokenLearner

MViT-B-24, 32x3

HigherHRNet (HR-Net-48)

CDN (ResNet101)

MSQNet

PoseC3D (SlowOnly-346)

VideoMAE (K700 pretrain+finetune, ViT-L, 16x4)

AVFusion

Team Trequartista

OpNet

DSCNet (RGB + Pose)

Text4Vis (w/ ViT-L)

3C-Net

BraVe:V-FA (TSM-50x2)

DIOR

MogaNet-B (384x288)

MSKA-SLT

ISTA-Net

TokenLearner

BMN (i3d feaure)

TCN (Skeleton Kinect)

AlphaPose

SGN

TwoStream-SLT

DEFR

HRNet+DSNT+BPnP

MLAD

MotionBERT (Finetune)

VideoCLIP

FPPR-PCD

PATHOSnet v2

CDCL+Pascal

BUCTD-CoAM-W48 (DLCRNet)

Temporal Subspace Clustering

HVQ

Graphonomy_Inner

MNN

LaViLa (Finetuned, TimeSformer-L)

MSPN+*

GestureGAN

HRNet-W48plus

ResNeXt-101

HVQ

MTUT

HRNet-w32

CNN-BiLSTM_best

Action anticipation baseline (co-training, with gaze)

CHASE(STSA-Net)

Temporal K-Means Clustering + Temporal Subspace Clustering

SubdivNet

MAT (Ours) Trans

MTUT

W-TALC

Rendezvous

RepNet

Xing et al.

Progressive Pose Attention

ESTIE + VGG16 (transfer-learning)

Selective HAR Clustering

DeVTr

ESCounts

3C-Net

RGB and PRGB

UNIK

VA-fusion (aug.)

TOT+TCL

DJ-RN

HRNet fine-tuned on BRACE

Key Frames + Feature Fusion

LOGO-CAP (Ours) HRNet-W48

Parsing R-CNN + ResNext101

dyalyt

LMSS

CORECT (4-class)

B3

DD-Net

JMRN

TemporalMaxer

Single-shot Deep CNN

DenseNet

Bidirectional LSTM

AlphaPose

R3D-18

ESCounts

QPIC + CPC

Next

SCAM

SuperAnimal-AnimalTokenPose

Transformer Ens.

Ours DLDL (KL)

2SRNN

8-MFFs-3f1c

3S Net TTM

3D-CNN + LSTM

Tripnet

ODMO

GraphSmile

6DRepNet360

CMU-Pose

VTFSA

DA-LLPose

HWGAT

SlowFast

Transformer Baseline

GraphSmile

S-CNN

F-BLSTM

MARS+RGB+Flow (16 frames)

Temp Conv + LSTM

Pr-VIPE

UniHCP (finetune)

Temporal Subspace Clustering

DPC

Ours DLDL (KL)

LSTM-IRN'fc1inter+intra

TIP-sum PPM-GGM-DDM-DF

Trans4SOAR (Pose)

R3D-18

ODMO

Generative Partition Networks