https://github.com/holzbock/st_mlp
공식 코드A Spatio-Temporal Multilayer Perceptron for Gesture Recognition
Papers with Code 아카이브
Action Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 8
- 평가표
- 11
- 보존된 평가 기록
- 81
Action Detection aims to find both where and when an action occurs within a video clip and classify what the action is taking place. Typically results are given in the form of action tublets, which are action bounding boxes linked across time in the video. This is related to temporal localization, which seeks to identify the start and end frame of an action, and action recognition, which seeks only to classify which action is taking place and typically assumes a trimmed video.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/hongyan1123/skeletonmae
공식 코드SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
https://github.com/huiguanlab/hico
공식 코드Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning
https://github.com/hulianyuyy/STGAT
공식 코드Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition
https://github.com/hutchresearch/fine-grained-cad
공식 코드Fine-Grained Classroom Activity Detection from Audio with Neural Networks
https://github.com/hypjudy/Decouple-SSAD
공식 코드Decoupling Localization and Classification in Single Shot Temporal Action Detection
https://github.com/iantangc/ContrastiveLearningHAR
공식 코드Exploring Contrastive Learning in Human Activity Recognition for Healthcare
https://github.com/iantangc/SelfHAR
공식 코드SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
https://github.com/ideal-idea/sap
공식 코드https://github.com/idiap/bert-text-diarization-atc
공식 코드https://github.com/idiap/zff_vad
공식 코드https://github.com/iesymiao/cd-gcn
공식 코드A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition
https://github.com/iiscleap/DIHARD_2019_baseline_alltracks
공식 코드The Second DIHARD Diarization Challenge: Dataset, task, and baselines
https://github.com/iit-pavis/uhar_skeletal_laplacian
공식 코드https://github.com/imatge-upc/activitynet-2016-cvprw
공식 코드Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks
https://github.com/ina-foss/InaGVAD
공식 코드https://github.com/information-fusion-lab-umass/multiwave
공식 코드https://github.com/intelligent-computing-lab-yale/snn_har
공식 코드Wearable-based Human Activity Recognition with Spatio-Temporal Spiking Neural Networks
https://github.com/izakariyya/idg-dp
공식 코드https://github.com/jackyjsy/CVPR21Chal-SLR
공식 코드https://github.com/jackyjsy/sam-slr-v2
공식 코드Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble
https://github.com/jacobchalk/tim
공식 코드TIM: A Time Interval Machine for Audio-Visual Action Recognition
https://github.com/jalayrac/weakactionloc
공식 코드A flexible model for training action localization with varying levels of supervision
https://github.com/jhong93/spot
공식 코드https://github.com/jiany-ctrl/Crossmodal-KD-for-Vision-to-Sensor-HAR
공식 코드Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition
https://github.com/jiaozizhao/Two-in-One-ActionDetection
공식 코드https://github.com/jie-su/bpd
공식 코드Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition
https://github.com/jindongwang/transferlearning
공식 코드Cross-domain Activity Recognition via Substructural Optimal Transport
https://github.com/jingyaojade/SpSt-GCN
공식 코드Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution
https://github.com/jls2007/primask
공식 코드PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference
https://github.com/joeybgofficial/through-the-wall-radar-human-activity-recognition-without-using-neural-networks
공식 코드Through-the-Wall Radar Human Activity Recognition WITHOUT Using Neural Networks
https://github.com/joslefaure/hit
공식 코드Holistic Interaction Transformer Network for Action Detection
https://github.com/jsvir/vad
공식 코드https://github.com/juliendenize/eztorch
공식 코드COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers
https://github.com/junhua-liao/light-asd
공식 코드https://github.com/junshan233/brem
공식 코드Estimation of Reliable Proposal Quality for Temporal Action Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.