https://github.com/facebookresearch/Motionformer
공식 코드Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
Papers with Code 아카이브
Action Localization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 0
- 보존된 평가 기록
- 0
Action Localization is finding the spatial and temporal co ordinates for an action in a video. An action localization model will identify which frame an action start and ends in video and return the x,y coordinates of an action. Further the co ordinates will change when the object performing action undergoes a displacement.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/facebookresearch/R2Plus1D
공식 코드A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/facebookresearch/co-tracker
공식 코드https://github.com/facebookresearch/vlamp
공식 코드Pretrained Language Models as Visual Planners for Human Assistance
https://github.com/fandulu/DD-Net
공식 코드Make Skeleton-based Action Recognition Model Smaller, Faster and Better
https://github.com/fandulu/asad
공식 코드Actor-identified Spatiotemporal Action Detection --- Detecting Who Is Doing What in Videos
https://github.com/fanglaosi/skeleton-in-context
공식 코드Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning
https://github.com/fau-is/next-best-action
공식 코드Prescriptive Business Process Monitoring for Recommending Next Best Actions
https://github.com/fau-is/xnap
공식 코드XNAP: Making LSTM-based Next Activity Predictions Explainable by Using LRP
https://github.com/fbarez/neuroplasticity
공식 코드https://github.com/fcntes/indoordepth
공식 코드Deeper into Self-Supervised Monocular Indoor Depth Estimation
https://github.com/fedespu/hvq
공식 코드Hierarchical Vector Quantization for Unsupervised Action Segmentation
https://github.com/feichtenhofer/st-resnet
공식 코드Spatiotemporal Residual Networks for Video Action Recognition
https://github.com/feichtenhofer/twostreamfusion
공식 코드Two-Stream Convolutional Networks for Action Recognition in Videos
https://github.com/feixiangzhou/smc-nca
공식 코드SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentation
https://github.com/fengzicai/awesomewmad
공식 코드https://github.com/fengzicai/wmad-benchmarks
공식 코드https://github.com/fepegar/gestures-miccai-2021
공식 코드Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures
https://github.com/feyzaakyurek/dune
공식 코드https://github.com/firework8/brl
공식 코드Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition
https://github.com/fjchange/him-net
공식 코드Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning
https://github.com/flamewei123/DEPN
공식 코드DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
https://github.com/fmthoker/skeleton-contrast
공식 코드https://github.com/fordcvresearch/fir-trajectory-prediction
공식 코드FIR-based Future Trajectory Prediction in Nighttime Autonomous Driving
https://github.com/fpv-iplab/rulstm
공식 코드https://github.com/fqhank/FuSTAL
공식 코드Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
https://github.com/franklear/lime
공식 코드https://github.com/frankniujc/kn_thesis
공식 코드What does the Knowledge Neuron Thesis Have to do with Knowledge?
https://github.com/frederico-klein/cad-gas
공식 코드https://github.com/furkanmumcu/vlad
공식 코드https://github.com/gaurav71531/spikeNetwork
공식 코드Data-driven Perception of Neuron Point Process with Unknown Unknowns
https://github.com/gbouritsas/cvpr18_multimodal_weakly_supervised_learning
공식 코드Multimodal Visual Concept Learning with Weakly Supervised Techniques
https://github.com/gd-goblin/NTU_DB_Data_Loader
공식 코드https://github.com/gebob19/m2a
공식 코드M2A: Motion Aware Attention for Accurate Video Action Recognition
https://github.com/geekfeiw/CSI-Net
공식 코드CSI-Net: Unified Human Body Characterization and Pose Recognition
https://github.com/geekfeiw/WiSLAR
공식 코드Temporal Unet: Sample Level Human Action Recognition using WiFi
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.