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.
TAXI: Evaluating Categorical Knowledge Editing for Language Models
Combating Missing Modalities in Egocentric Videos at Test Time
Interactive Generation of Laparoscopic Videos with Diffusion Models
CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment
Attack on Scene Flow using Point Clouds
Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition
Aligning Actions and Walking to LLM-Generated Textual Descriptions
Lower Limb Movements Recognition Based on Feature Recursive Elimination and Backpropagation Neural Network
Decomposing and Editing Predictions by Modeling Model Computation
VG4D: Vision-Language Model Goes 4D Video Recognition
MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory
MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition
Learning to Score Sign Language with Two-stage Method
HumMUSS: Human Motion Understanding using State Space Models
Leveraging Temporal Contextualization for Video Action Recognition
In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition
A Survey on Multimodal Wearable Sensor-based Human Action Recognition
Exploring Explainability in Video Action Recognition
Multimodal Attack Detection for Action Recognition Models
MSSTNet: A Multi-Scale Spatio-Temporal CNN-Transformer Network for Dynamic Facial Expression Recognition
Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition
Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos
An Animation-based Augmentation Approach for Action Recognition from Discontinuous Video
O-TALC: Steps Towards Combating Oversegmentation within Online Action Segmentation
Gaze-Guided Graph Neural Network for Action Anticipation Conditioned on Intention
DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs
ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos
TIM: A Time Interval Machine for Audio-Visual Action Recognition
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model
Learning Correlation Structures for Vision Transformers
Koala: Key frame-conditioned long video-LLM
PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos
Locating and Editing Factual Associations in Mamba
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.