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/hengrui-gu/pokemqa
공식 코드PokeMQA: Programmable knowledge editing for Multi-hop Question Answering
https://github.com/hengrui-gu/t2iknowledgeediting
공식 코드https://github.com/hepta-col/videofightdetection
공식 코드Weakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection Model
https://github.com/hfawaz/dl-4-tsc
공식 코드https://github.com/hfawaz/ijcnn19attacks
공식 코드Adversarial Attacks on Deep Neural Networks for Time Series Classification
https://github.com/hfawaz/miccai18
공식 코드https://github.com/hhyhrhy/owmm-agent
공식 코드OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
https://github.com/hi-archers/mlake
공식 코드MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
https://github.com/hikvision-research/cost
공식 코드Collaborative Spatio-temporal Feature Learning for Video Action Recognition
https://github.com/hikvision-research/skelact
공식 코드Skeleton-based Action Recognition with Convolutional Neural Networks
https://github.com/hitottiez/mht-paf
공식 코드Multiple Human Tracking using Multi-Cues including Primitive Action Features
https://github.com/hiyouga/llama-factory
공식 코드Time Sensitive Knowledge Editing through Efficient Finetuning
https://github.com/hlcdyy/pan-motion-retargeting
공식 코드Pose-aware Attention Network for Flexible Motion Retargeting by Body Part
https://github.com/hmorimitsu/ptlflow
공식 코드DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
https://github.com/hnuzhy/fcos_pose
공식 코드https://github.com/hoagyc/sparse_coding
공식 코드Sparse Autoencoders Find Highly Interpretable Features in Language Models
https://github.com/holi-lab/core
공식 코드https://github.com/holistic-video-understanding/HVU-Dataset
공식 코드https://github.com/holzbock/st_mlp
공식 코드A Spatio-Temporal Multilayer Perceptron for Gesture Recognition
https://github.com/hongguangzhang/mlso-tmm-master
공식 코드https://github.com/hongluzhou/composer
공식 코드COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
https://github.com/hongyan1123/skeletonmae
공식 코드SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
https://github.com/hotfinda/videomambapro
공식 코드https://github.com/houshd/MLSTM-FCN
공식 코드https://github.com/howardzh01/ppma
공식 코드Learning Human Action Recognition Representations Without Real Humans
https://github.com/hren20/naivibridger
공식 코드Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models
https://github.com/hri-eu/flow_matching
공식 코드https://github.com/hrishavbakulbarua/darkbert
공식 코드MD-BERT: Action Recognition in Dark Videos via Dynamic Multi-Stream Fusion and Temporal Modeling
https://github.com/htwang14/PA-HMDB51
공식 코드Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset
https://github.com/huangshk/wimans
공식 코드WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing
https://github.com/huangxiusheng/dem
공식 코드https://github.com/huggingface/lerobot
공식 코드SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
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/hustyyq/where-to-edit
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.