https://github.com/wuzhenyusjtu/Privacy-AdversarialLearning
공식 코드Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
Papers with Code 아카이브
Action Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 15
- 평가표
- 56
- 보존된 평가 기록
- 650
Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.
In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.
Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/wzmsltw/BSN-boundary-sensitive-network.pytorch
공식 코드BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
https://github.com/xacheng1996/sllm
공식 코드Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration
https://github.com/xbmxb/edit_analysis
공식 코드https://github.com/xh20/HAGCN
공식 코드Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network
https://github.com/xiaojiegu/ultraedit
공식 코드UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models
https://github.com/xingaoli/dp-hoi
공식 코드Disentangled Pre-training for Human-Object Interaction Detection
https://github.com/xingli1012/sequentialpointnet
공식 코드Real-time 3D human action recognition based on Hyperpoint sequence
https://github.com/xingyu-song/4a
공식 코드An Animation-based Augmentation Approach for Action Recognition from Discontinuous Video
https://github.com/xingyul/cpnet
공식 코드Learning Video Representations from Correspondence Proposals
https://github.com/xingyul/meteornet
공식 코드MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences
https://github.com/xinhaoyi/edit_bio_long_tail
공식 코드https://github.com/xinyusun/mme
공식 코드Masked Motion Encoding for Self-Supervised Video Representation Learning
https://github.com/xpq-tech/code-llmedit
공식 코드https://github.com/xpq-tech/keti
공식 코드Identifying Knowledge Editing Types in Large Language Models
https://github.com/xpq-tech/pmet
공식 코드https://github.com/xpq-tech/swea
공식 코드SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering
https://github.com/xuboshen/egoncepp
공식 코드EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?
https://github.com/xuyankun/stvig-for-reads-v
공식 코드VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG
https://github.com/xuyankun/vsvig
공식 코드VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG
https://github.com/xuyizdby/noiseerasar
공식 코드https://github.com/xuyu0010/atcon
공식 코드Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition
https://github.com/xuyu0010/awesome-video-domain-adaptation
공식 코드Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey
https://github.com/xyzforever/bevt
공식 코드https://github.com/yangliu9208/tcgl
공식 코드TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning
https://github.com/yangzhenkui/witalk
공식 코드Talk is Not Always Cheap: Promoting Wireless Sensing Models with Text Prompts
https://github.com/yanhui002/video_adv
공식 코드https://github.com/yaohui120/comprehendedit
공식 코드ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing
https://github.com/yaoli/arctic-capgen-vid
공식 코드https://github.com/ybdai7/NAMET-massive-editing
공식 코드NAMET: Robust Massive Model Editing via Noise-Aware Memory Optimization
https://github.com/ybhbingo/mmfi_dataset
공식 코드MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing
https://github.com/yellowtownhz/STIGCN
공식 코드Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
https://github.com/yfsong0709/EfficientGCNv1
공식 코드Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition
https://github.com/yfsong0709/RA-GCNv2
공식 코드Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition
https://github.com/yhZhai/SOAR
공식 코드https://github.com/yhZhai/WSCL
공식 코드Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.