Papers with Code 아카이브

Activity Recognition

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 11
평가표: 4
보존된 평가 기록: 10

Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.

Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters

코드

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

https://github.com/bornabr/rscnet

공식 코드

RSCNet: Dynamic CSI Compression for Cloud-based WiFi Sensing

https://github.com/brjathu/LART

공식 코드

On the Benefits of 3D Pose and Tracking for Human Action Recognition

https://github.com/brown-palm/AntGPT

공식 코드

AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?

https://github.com/brown-palm/ObjectPrompt

공식 코드

Object-centric Video Representation for Long-term Action Anticipation

https://github.com/bruceyo/V-PETL

공식 코드

Towards a Unified View on Visual Parameter-Efficient Transfer Learning

https://github.com/bruthyu/melo

공식 코드

MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA

https://github.com/bryant1410/fitclip

공식 코드

FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks

https://github.com/bryant1410/tclip

공식 코드

FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks

https://github.com/bryanyzhu/Hidden-Two-Stream

공식 코드

Hidden Two-Stream Convolutional Networks for Action Recognition

https://github.com/bulatkh/csshar_tfa

공식 코드

Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity Recognition

https://github.com/buptsjzhang/std-cl

공식 코드

Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action Recognition

https://github.com/buptsjzhang/ta-mlp

공식 코드

SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition

https://github.com/byronbbl/deck

공식 코드

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts

https://github.com/calvintanama/qd-driver-activity-reco

공식 코드

Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained Environments

https://github.com/camma-public/attention-tripnet

공식 코드

Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos

https://github.com/camma-public/cholectriplet2022

공식 코드

CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection

https://github.com/camma-public/ivtmetrics

공식 코드

Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets

https://github.com/camma-public/multibypass140

공식 코드

Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass Surgery

https://github.com/camma-public/rendezvous-in-time

공식 코드

Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition

https://github.com/camma-public/selfsupsurg

공식 코드

Dissecting Self-Supervised Learning Methods for Surgical Computer Vision

https://github.com/camma-public/surglatentgraph

공식 코드

Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning

https://github.com/camma-public/tripnet

공식 코드

Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets

https://github.com/canbaoburen/CoDT

공식 코드

Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition

https://github.com/cap-ntu/ML-Model-CI

공식 코드

ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale

https://github.com/carlobretti/object-scene-compositions-for-actions

공식 코드

Zero-Shot Action Recognition from Diverse Object-Scene Compositions

https://github.com/carloscaetano/skeleton-images

공식 코드

SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition

https://github.com/cascip/seg2act

공식 코드

Seg2Act: Global Context-aware Action Generation for Document Logical Structuring

https://github.com/caskcsg/lyaplock

공식 코드

LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing

https://github.com/cdjkim/respec

공식 코드

ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams

https://github.com/changchangsun/forget-vector

공식 코드

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

https://github.com/chaoyuaw/lvu

공식 코드

Towards Long-Form Video Understanding

https://github.com/chenhaoxing/etl4video

공식 코드

Efficient Transfer Learning for Video-language Foundation Models

https://github.com/chenhsing/svformer

공식 코드

SVFormer: Semi-supervised Video Transformer for Action Recognition

https://github.com/chenhuihu/knowledge_in_superposition

공식 코드

Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models

https://github.com/chenhuihu/wilke

공식 코드

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing

https://github.com/chenmientan/malmen

공식 코드

Massive Editing for Large Language Models via Meta Learning

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