Papers with Code 아카이브
Action Recognition In Videos
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 17
- 보존된 평가 기록
- 45
Action Recognition in Videos is a task in computer vision and pattern recognition where the goal is to identify and categorize human actions performed in a video sequence. The task involves analyzing the spatiotemporal dynamics of the actions and mapping them to a predefined set of action classes, such as running, jumping, or swimming.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
Action Anticipation By Predicting Future Dynamic Images
Motion Feature Network: Fixed Motion Filter for Action Recognition
Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks
Pose-Based Two-Stream Relational Networks for Action Recognition in Videos
DenseImage Network: Video Spatial-Temporal Evolution Encoding and Understanding
Visual Attribute-augmented Three-dimensional Convolutional Neural Network for Enhanced Human Action Recognition
Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
Video Representation Learning Using Discriminative Pooling
2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning
Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
Temporal Relational Reasoning in Videos
Two-stream Flow-guided Convolutional Attention Networks for Action Recognition
Visual Forecasting by Imitating Dynamics in Natural Sequences
Discriminative convolutional Fisher vector network for action recognition
RED: Reinforced Encoder-Decoder Networks for Action Anticipation
Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition
Temporal Segment Networks for Action Recognition in Videos
R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
Encouraging LSTMs to Anticipate Actions Very Early
Procedural Generation of Videos to Train Deep Action Recognition Networks
AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos
Spatiotemporal Residual Networks for Video Action Recognition
YouTube-8M: A Large-Scale Video Classification Benchmark
Pose from Action: Unsupervised Learning of Pose Features based on Motion
Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
Hierarchical Attention Network for Action Recognition in Videos
Action Recognition with Joint Attention on Multi-Level Deep Features
Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
Convolutional Two-Stream Network Fusion for Video Action Recognition
Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web
Action Recognition using Visual Attention
Towards Good Practices for Very Deep Two-Stream ConvNets
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.