Papers with Code 아카이브

Action Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/google-research/scenic

공식 코드

UnLoc: A Unified Framework for Video Localization Tasks

https://github.com/haozheng-sjtu/3d-airway-segmentation

공식 코드

Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation

https://github.com/hitcbw/lpl

공식 코드

Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation

https://github.com/iai-hrc/ha-vid

공식 코드

HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding

https://github.com/isee-laboratory/cvpr24_atba

공식 코드

Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment

https://github.com/jinglinglingling/x4d

공식 코드

X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer

https://github.com/kimihiroh/promqa

공식 코드

ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding

https://github.com/kpeng9510/hopadiff

공식 코드

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

https://github.com/laurenok24/nsaqa

공식 코드

Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment

https://github.com/ld-ing/TCFPN-ISBA

공식 코드

Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment

https://github.com/leolyliu/HOI4D-Instructions

공식 코드

HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction

https://github.com/likenneth/acton

공식 코드

Towards Tokenized Human Dynamics Representation

https://github.com/liuqi-creat/sigformer

공식 코드

SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation

https://github.com/ltcontext/ltcontext

공식 코드

How Much Temporal Long-Term Context is Needed for Action Segmentation?

https://github.com/lyhisme/dest

공식 코드

A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation

https://github.com/microsoft/UniVL

공식 코드

UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation

https://github.com/mingu6/action_seg_ot

공식 코드

Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation

https://github.com/nus-cvml/awesome-temporal-action-segmentation

공식 코드

Temporal Action Segmentation: An Analysis of Modern Techniques

https://github.com/pangzhan27/CSL_LT-TAS

공식 코드

Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentation

https://github.com/pangzhan27/GTLA

공식 코드

Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment

https://github.com/peiyao-w/baformer

공식 코드

Efficient Temporal Action Segmentation via Boundary-aware Query Voting

https://github.com/pytorch/fairseq

공식 코드

VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding

https://github.com/rd20karim/synch-transformer

공식 코드

Transformer with Controlled Attention for Synchronous Motion Captioning

https://github.com/redwang/DTGRM

공식 코드

Temporal Relational Modeling with Self-Supervision for Action Segmentation

https://github.com/rezaghoddoosian/hierarchical-task-modeling

공식 코드

Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos

https://github.com/ryota-skating/fs-jump3d

공식 코드

3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach

https://github.com/sauradip/fewshotQAT

공식 코드

Few-Shot Temporal Action Localization with Query Adaptive Transformer

https://github.com/shiyi-zh0408/logo

공식 코드

LOGO: A Long-Form Video Dataset for Group Action Quality Assessment

https://github.com/ssarfraz/FINCH-CLustering

공식 코드

Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation

https://github.com/sthoduka/handover_failure_detection

공식 코드

A Multimodal Handover Failure Detection Dataset and Baselines

https://github.com/trquhuytin/TOT-CVPR22

공식 코드

Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering

https://github.com/ttlmh/bridge-prompt

공식 코드

Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos

https://github.com/yabufarha/ms-tcn

공식 코드

MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation

https://github.com/yassersouri/MuCon

공식 코드

Fast Weakly Supervised Action Segmentation Using Mutual Consistency

https://github.com/yiskw713/asrf

공식 코드

Alleviating Over-segmentation Errors by Detecting Action Boundaries

https://github.com/yl596/otas

공식 코드

OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.