https://github.com/sjtuwxz/loconet_asd
공식 코드LoCoNet: Long-Short Context Network for Active Speaker Detection
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/skelemoa/ntu-x
공식 코드NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actions
https://github.com/skelemoa/psumnet
공식 코드PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition
https://github.com/skelemoa/quovadis
공식 코드https://github.com/sming256/OpenTAD
공식 코드End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
https://github.com/sming256/etad
공식 코드https://github.com/smy-nec/aapl
공식 코드Action-Agnostic Point-Level Supervision for Temporal Action Detection
https://github.com/soccernet/sn-spotting
공식 코드https://github.com/sovan-biswas/MultiLabelActorActionAssignment
공식 코드Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting
https://github.com/sperimental3/charon
공식 코드Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning
https://github.com/sqiangcao99/e2e-load
공식 코드https://github.com/sra2/spell
공식 코드Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection
https://github.com/srijandas07/VPN
공식 코드VPN: Learning Video-Pose Embedding for Activities of Daily Living
https://github.com/srijandas07/vpnplusplus
공식 코드VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
https://github.com/srvCodes/continual-learning-benchmark
공식 코드Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis
https://github.com/sshao2013/convboost
공식 코드ConvBoost: Boosting ConvNets for Sensor-based Activity Recognition
https://github.com/sssste/react
공식 코드https://github.com/steveliao93/gcn_logsigrnn
공식 코드Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition
https://github.com/stilllearningsoumya/acconotate
공식 코드Accoustate: Auto-annotation of IMU-generated Activity Signatures under Smart Infrastructure
https://github.com/stnoah1/infogcn2
공식 코드https://github.com/stnoah1/sode
공식 코드https://github.com/stoa-xh91/acfl
공식 코드Skeleton-based Action Recognition via Adaptive Cross-Form Learning
https://github.com/stoneMo/YOWOv2
공식 코드Towards Improving Spatiotemporal Action Recognition in Videos
https://github.com/strohmayerj/datta
공식 코드https://github.com/strohmayerj/wiflexformer
공식 코드https://github.com/superz678/mg-had
공식 코드https://github.com/svip-lab/SVIP-Sequence-VerIfication-for-Procedures-in-Videos
공식 코드https://github.com/t-hasegawa-fu/easy-ensemble
공식 코드Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition
https://github.com/taeiin/aaai2025-jovale
공식 코드JoVALE: Detecting Human Actions in Video Using Audiovisual and Language Contexts
https://github.com/tailin1009/dualhead-network
공식 코드Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
https://github.com/tecsar-uncc/adg-pose
공식 코드ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation
https://github.com/tencentyouturesearch/actiondetection-lstc
공식 코드LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
https://github.com/thanhhff/HOTAD
공식 코드https://github.com/the-sky001/widistill
공식 코드WiDistill: Distilling Large-scale Wi-Fi Datasets with Trajectory Matching
https://github.com/thearkaprava/ms-temba
공식 코드MS-Temba : Multi-Scale Temporal Mamba for Efficient Temporal Action Detection
https://github.com/themaxiao/ditmos
공식 코드DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.