Papers with Code 아카이브
Action Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 9
- 보존된 평가 기록
- 120
Action Segmentation is a challenging problem in high-level video understanding. In its simplest form, Action Segmentation aims to segment a temporally untrimmed video by time and label each segmented part with one of pre-defined action labels. The results of Action Segmentation can be further used as input to various applications, such as video-to-text and action localization.
Source: TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models
M2R2: MulitModal Robotic Representation for Temporal Action Segmentation
Uni4D: A Unified Self-Supervised Learning Framework for Point Cloud Videos
Towards Generalizing Temporal Action Segmentation to Unseen Views
What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning
Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentation
Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation
Condensing Action Segmentation Datasets via Generative Network Inversion
End-to-End Action Segmentation Transformer
Improving action segmentation via explicit similarity measurement
TimeLogic: A Temporal Logic Benchmark for Video QA
Temporal Context Consistency Above All: Enhancing Long-Term Anticipation by Learning and Enforcing Temporal Constraints
Hierarchical Vector Quantization for Unsupervised Action Segmentation
Stitch Contrast and Segment_Learning a Human Action Segmentation Model Using Trimmed Skeleton Videos
2by2: Weakly-Supervised Learning for Global Action Segmentation
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
Video LLMs for Temporal Reasoning in Long Videos
OnlineTAS: An Online Baseline for Temporal Action Segmentation
ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding
Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network
Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation
ASQuery: A Query-based Model for Action Segmentation
Temporal2Seq: A Unified Framework for Temporal Video Understanding Tasks
Transformer with Controlled Attention for Synchronous Motion Captioning
3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach
Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment
Faster Diffusion Action Segmentation
A study of animal action segmentation algorithms across supervised, unsupervised, and semi-supervised learning paradigms
Efficient Temporal Action Segmentation via Boundary-aware Query Voting
MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models
Snippet-Aware Transformer With Multiple Action Elements for Skeleton-Based Action Segmentation
HOIST-Former: Hand-held Objects Identification, Segmentation, and Tracking in the Wild
O-TALC: Steps Towards Combating Oversegmentation within Online Action Segmentation
LOGO: A Long-Form Video Dataset for Group Action Quality Assessment
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.