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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos
JOADAA: joint online action detection and action anticipation
Grounded Language Acquisition From Object and Action Imagery
ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Space
SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition
Unified Contrastive Fusion Transformer for Multimodal Human Action Recognition
Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation
CDFSL-V: Cross-Domain Few-Shot Learning for Videos
EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding
Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning
SOAR: Scene-debiasing Open-set Action Recognition
SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition
B2C-AFM: Bi-Directional Co-Temporal and Cross-Spatial Attention Fusion Model for Human Action Recognition
IndGIC: Supervised Action Recognition under Low Illumination
Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition
Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds
Sparse Models for Machine Learning
Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons
Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers
EventTransAct: A video transformer-based framework for Event-camera based action recognition
DD-GCN: Directed Diffusion Graph Convolutional Network for Skeleton-based Human Action Recognition
POCO: 3D Pose and Shape Estimation with Confidence
MOFO: MOtion FOcused Self-Supervision for Video Understanding
Are current long-term video understanding datasets long-term?
Video BagNet: short temporal receptive fields increase robustness in long-term action recognition
Opening the Vocabulary of Egocentric Actions
Joint learning of images and videos with a single Vision Transformer
Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition
Temporal-Distributed Backdoor Attack Against Video Based Action Recognition
Spatial-Temporal Alignment Network for Action Recognition
Eva-KELLM: A New Benchmark for Evaluating Knowledge Editing of LLMs
TTPOINT: A Tensorized Point Cloud Network for Lightweight Action Recognition with Event Cameras
Unlimited Knowledge Distillation for Action Recognition in the Dark
Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching
PMET: Precise Model Editing in a Transformer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.