https://github.com/rijuldhir/TSM
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
Papers with Code 아카이브
Activity Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 11
- 평가표
- 4
- 보존된 평가 기록
- 10
Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.
Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/rinnakk/japanese-clip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/rishikksh20/ViViT-pytorch
https://github.com/rk68657/AutoEncoders
https://github.com/rkahani/FirstPersonActivityRecognition
A Correlation Based Feature Representation for First-Person Activity Recognition
https://github.com/rlaengud123/CMC_LRCN
UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
https://github.com/rll/rllab
Benchmarking Deep Reinforcement Learning for Continuous Control
https://github.com/rlleshi/sensor-har
Human Activity Recognition from Wearable Sensor Data Using Self-Attention
https://github.com/rlworkgroup/garage
Benchmarking Deep Reinforcement Learning for Continuous Control
https://github.com/rmwkwok/product_visual_search
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/rohanshad/cmr_transformer
https://github.com/rohitgirdhar/AttentionalPoolingAction
https://github.com/rohitgr7/tvmodels
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/romaintha/pytorch_pointnet
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/rort1989/HDM
https://github.com/rowanz/verb-attributes
Zero-Shot Activity Recognition with Verb Attribute Induction
https://github.com/rruschel/bload
Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
https://github.com/ruotianluo/coco-caption
https://github.com/russellmendonca/maesn_suite
Benchmarking Deep Reinforcement Learning for Continuous Control
https://github.com/rwightman/efficientnet-jax
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/rwightman/gen-efficientnet-pytorch
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/ryanchesler/comma-speed-challenge
UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
https://github.com/s-a-malik/multi-few
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/s-gupta/v-coco
https://github.com/saaries/PointNet
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/sadari1/TumorDetectionDeepLearning
Temporal Convolutional Networks for Action Segmentation and Detection
https://github.com/saikasyap/Video-Embeddings
https://github.com/sair-lab/ni-slam
https://github.com/sajjjadayobi/CLIPfa
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/salaniz/pycocoevalcap
https://github.com/salesforce/pb-ovd
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/salinasJJ/BBaction
Video Classification with Channel-Separated Convolutional Networks
https://github.com/salmank255/ROADSlowFast
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
https://github.com/samson6460/tf-keras-gradcamplusplus
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
https://github.com/samson6460/tf.keras-gradcamplusplus
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
https://github.com/samson6460/tf_keras_gradcamplusplus
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.