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/jaulin-bage/task-adapter-pp

공식 코드

Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition

https://github.com/jayleicn/singularity

공식 코드

Revealing Single Frame Bias for Video-and-Language Learning

https://github.com/jeffhernandez1995/vic-mae

공식 코드

ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders

https://github.com/jemoka/dropfree

공식 코드

Drop Dropout on Single-Epoch Language Model Pretraining

https://github.com/jfzhang95/pytorch-video-recognition

공식 코드

Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity Recognition

https://github.com/jhang2020/pcm3

공식 코드

Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond

https://github.com/jhong93/vpd

공식 코드

Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition

https://github.com/jia-wei-zheng/alignment-over-probabilistic-events

공식 코드

Alignment-based conformance checking over probabilistic events

https://github.com/jiaangl/elder

공식 코드

ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA

https://github.com/jiakuan929/superficial-editing

공식 코드

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing

https://github.com/jianghoucheng/alphaedit

공식 코드

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

https://github.com/jianghoucheng/nse

공식 코드

Neuron-Level Sequential Editing for Large Language Models

https://github.com/jianglongye/cgf

공식 코드

Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations

https://github.com/jiany-ctrl/Crossmodal-KD-for-Vision-to-Sensor-HAR

공식 코드

Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition

https://github.com/jiaozizhao/Two-in-One-ActionDetection

공식 코드

Dance with Flow: Two-in-One Stream Action Detection

https://github.com/jiazheng-xing/gghm

공식 코드

Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching

https://github.com/jie-su/bpd

공식 코드

Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition

https://github.com/jindongwang/transferlearning

공식 코드

Cross-domain Activity Recognition via Substructural Optimal Transport

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/jingyaojade/SpSt-GCN

공식 코드

Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution

https://github.com/jiutian-vl/star

공식 코드

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

https://github.com/jiyanggao/TURN-TAP

공식 코드

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

https://github.com/jkini/Meccano

공식 코드

Ensemble Modeling for Multimodal Visual Action Recognition

https://github.com/jls2007/primask

공식 코드

PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference

https://github.com/jnnan/chairs

공식 코드

Full-Body Articulated Human-Object Interaction

https://github.com/joeybgofficial/through-the-wall-radar-human-activity-recognition-without-using-neural-networks

공식 코드

Through-the-Wall Radar Human Activity Recognition WITHOUT Using Neural Networks

https://github.com/john-hewitt/model-editing-canonical-examples

공식 코드

Model Editing with Canonical Examples

https://github.com/john828/mifi

공식 코드

MIFI: MultI-camera Feature Integration for Roust 3D Distracted Driver Activity Recognition

https://github.com/johnnychanv/JailbreakEdit

공식 코드

Injecting Universal Jailbreak Backdoors into LLMs in Minutes

https://github.com/jometeorie/multihopshortcuts

공식 코드

Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models

https://github.com/joslefaure/hit

공식 코드

Holistic Interaction Transformer Network for Action Detection

https://github.com/ju-chen/Efficient-Prompt

공식 코드

Prompting Visual-Language Models for Efficient Video Understanding

https://github.com/juliendenize/eztorch

공식 코드

Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning

https://github.com/jun-cen/psl

공식 코드

Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition

https://github.com/junweiliang/multitrain

공식 코드

Multi-dataset Training of Transformers for Robust Action Recognition

https://github.com/jx-zhong-for-academic-purpose/kinet

공식 코드

No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces

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