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.

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Action Recognition

논문

DeepSTEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans

A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains

Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment

EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception

Feature Hallucination for Self-supervised Action Recognition

CARMA: Context-Aware Situational Grounding of Human-Robot Group Interactions by Combining Vision-Language Models with Object and Action Recognition

Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm

Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition

Adapting Vision-Language Models for Evaluating World Models

Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs

Active Multimodal Distillation for Few-shot Action Recognition

DualEdit: Dual Editing for Knowledge Updating in Vision-Language Models

Model Merging for Knowledge Editing

Mitigating Negative Interference in Multilingual Sequential Knowledge Editing through Null-Space Constraints

An Effective End-to-End Solution for Multimodal Action Recognition

Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation

HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

PropMEND: Hypernetworks for Knowledge Propagation in LLMs

SoK: Machine Unlearning for Large Language Models

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs

The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing

Lifelong Evolution: Collaborative Learning between Large and Small Language Models for Continuous Emergent Fake News Detection

MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs

Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models

3D Skeleton-Based Action Recognition: A Review

A Review on Coarse to Fine-Grained Animal Action Recognition

On Fairness of Task Arithmetic: The Role of Task Vectors

EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding

Model Unlearning via Sparse Autoencoder Subspace Guided Projections

Drop Dropout on Single-Epoch Language Model Pretraining

Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition

Context Robust Knowledge Editing for Language Models

ScEdit: Script-based Assessment of Knowledge Editing