Papers with Code 아카이브

Human-Object Interaction Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 6
보존된 평가 기록: 103

Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels.

코드

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

https://github.com/birlrobotics/vs-gats

공식 코드

Visual-Semantic Graph Attention Networks for Human-Object Interaction Detection

https://github.com/bobwan1995/PMFNet

공식 코드

Pose-aware Multi-level Feature Network for Human Object Interaction Detection

https://github.com/bobwan1995/zeroshot-hoi-with-clip

공식 코드

Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levels

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

공식 코드

Object-centric Video Representation for Long-term Action Anticipation

https://github.com/byz0e/glance-focus

공식 코드

Glance and Focus: Memory Prompting for Multi-Event Video Question Answering

https://github.com/caoyichao/unihoi

공식 코드

Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models

https://github.com/charles-xie/cql

공식 코드

Category Query Learning for Human-Object Interaction Classification

https://github.com/chelsielei/ez-hoi

공식 코드

EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection

https://github.com/chenyi99/egoplan

공식 코드

EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning

https://github.com/cjw2021/QAHOI

공식 코드

QAHOI: Query-Based Anchors for Human-Object Interaction Detection

https://github.com/cjw2021/sov-stg

공식 코드

Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor

https://github.com/cjw2021/sov-stg-vla

공식 코드

Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor

https://github.com/coldmanck/VidHOI

공식 코드

ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos

https://github.com/daoyuan98/odm

공식 코드

Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection

https://github.com/daoyuan98/sdt-hoi

공식 코드

Distance Matters in Human-Object Interaction Detection

https://github.com/dirtyharrylyl/hake-ava

공식 코드

Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions

https://github.com/dominickrei/egoexo4adl

공식 코드

From My View to Yours: Ego-Augmented Learning in Large Vision Language Models for Understanding Exocentric Daily Living Activities

https://github.com/ehsanik/touchTorch

공식 코드

Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects

https://github.com/enlighten0707/body-part-map-for-interactiveness

공식 코드

Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection

https://github.com/facebookresearch/d3d-hoi

공식 코드

D3D-HOI: Dynamic 3D Human-Object Interactions from Videos

https://github.com/facebookresearch/phosa

공식 코드

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

https://github.com/foruck/oc-immunity

공식 코드

Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection

https://github.com/fpv-iplab/HOI-Synth

공식 코드

Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?

https://github.com/fpv-iplab/MECCANO

공식 코드

The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain

https://github.com/fredzzhang/hicodet

공식 코드

Spatially Conditioned Graphs for Detecting Human-Object Interactions

https://github.com/fredzzhang/pvic

공식 코드

Exploring Predicate Visual Context in Detecting Human-Object Interactions

https://github.com/fredzzhang/spatially-conditioned-graphs

공식 코드

Spatially Conditioned Graphs for Detecting Human-Object Interactions

https://github.com/fredzzhang/upt

공식 코드

Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

https://github.com/fubel/stmodeling

공식 코드

Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos

https://github.com/fujitsuresearch/hoi_sg

공식 코드

HICO-DET-SG and V-COCO-SG: New Data Splits for Evaluating the Systematic Generalization Performance of Human-Object Interaction Detection Models

https://github.com/gengzichen/ARDHOI

공식 코드

Auto-Regressive Diffusion for Generating 3D Human-Object Interactions

https://github.com/gkioxari/RstarCNN

공식 코드

Contextual Action Recognition with R*CNN

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

공식 코드

Unified Visual Relationship Detection with Vision and Language Models

https://github.com/hcplab-sysu/3daffordsplat

공식 코드

3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians

https://github.com/hellog2n/b-right

공식 코드

B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction Testing

https://github.com/hitachi-rd-cv/qpic

공식 코드

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information

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