{"total":109,"rows":[{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183,"area":null},{"id":"2103.05399","title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","created":"2021-03-09","cited_by_count":147,"area":null},{"id":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135,"area":null},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120,"area":null},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114,"area":null},{"id":"2108.05077","title":"Mining the Benefits of Two-stage and One-stage HOI Detection","created":"2021-08-11","cited_by_count":103,"area":null},{"id":"2103.05983","title":"Reformulating HOI Detection as Adaptive Set Prediction","created":"2021-03-10","cited_by_count":95,"area":null},{"id":"2112.01838","title":"Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer","created":"2021-12-03","cited_by_count":91,"area":null},{"id":"2103.08214","title":"Detecting Human-Object Interaction via Fabricated Compositional Learning","created":"2021-03-15","cited_by_count":79,"area":null},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2104.05269","title":"Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection","created":"2021-04-12","cited_by_count":58,"area":null},{"id":"2308.06202","title":"Exploring Predicate Visual Context in Detecting Human-Object Interactions","created":"2023-08-11","cited_by_count":56,"area":null},{"id":"2209.03299","title":"Multimodal learning with graphs","created":"2022-09-07","cited_by_count":54,"area":null},{"id":"2206.06291","title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","created":"2022-06-13","cited_by_count":47,"area":null},{"id":"2308.09351","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","created":"2023-08-18","cited_by_count":45,"area":null},{"id":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42,"area":null},{"id":"2304.08114","title":"ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection","created":"2023-04-17","cited_by_count":41,"area":null},{"id":"2204.07718","title":"Interactiveness Field in Human-Object Interactions","created":"2022-04-16","cited_by_count":40,"area":null},{"id":"2204.09290","title":"Human-Object Interaction Detection via Disentangled Transformer","created":"2022-04-20","cited_by_count":40,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2309.03696","title":"Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory","created":"2023-09-07","cited_by_count":38,"area":null},{"id":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","cited_by_count":37,"area":null},{"id":"2304.04997","title":"Relational Context Learning for Human-Object Interaction Detection","created":"2023-04-11","cited_by_count":36,"area":null},{"id":"2204.00746","title":"What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions","created":"2022-04-02","cited_by_count":35,"area":null},{"id":"2203.14709","title":"MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection","created":"2022-03-28","cited_by_count":34,"area":null},{"id":"2311.03799","title":"Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models","created":"2023-11-07","cited_by_count":34,"area":null},{"id":"2105.02170","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","created":"2021-05-05","cited_by_count":31,"area":null},{"id":"2301.04019","title":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","created":"2023-01-08","cited_by_count":30,"area":null},{"id":"2112.08647","title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","created":"2021-12-16","cited_by_count":28,"area":null},{"id":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28,"area":null},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25,"area":null},{"id":"2404.06194","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2202.00259","title":"Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics","created":"2022-02-01","cited_by_count":22,"area":null},{"id":"2204.04911","title":"Category-Aware Transformer Network for Better Human-Object Interaction Detection","created":"2022-04-11","cited_by_count":22,"area":null},{"id":"2303.14005","title":"Category Query Learning for Human-Object Interaction Classification","created":"2023-03-24","cited_by_count":21,"area":null},{"id":"2311.17048","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","created":"2023-11-28","cited_by_count":21,"area":null},{"id":"2401.12275","title":"Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation","created":"2024-01-22","cited_by_count":20,"area":null},{"id":"2203.10537","title":"Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows","created":"2022-03-20","cited_by_count":19,"area":null},{"id":"2204.04836","title":"Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection","created":"2022-04-11","cited_by_count":16,"area":null},{"id":"2112.07383","title":"Improving Human-Object Interaction Detection via Phrase Learning and Label Composition","created":"2021-12-14","cited_by_count":15,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14,"area":null},{"id":"2206.01908","title":"Video-based Human-Object Interaction Detection from Tubelet Tokens","created":"2022-06-04","cited_by_count":13,"area":null},{"id":"2303.08998","title":"Unified Visual Relationship Detection with Vision and Language Models","created":"2023-03-16","cited_by_count":13,"area":null},{"id":"2307.13529","title":"Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection","created":"2023-07-25","cited_by_count":13,"area":null},{"id":"2108.08633","title":"Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2112.05585","title":"Discrete neural representations for explainable anomaly detection","created":"2021-12-10","cited_by_count":12,"area":null},{"id":"2207.05293","title":"Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2109.04047","title":"ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection","created":"2021-09-09","cited_by_count":11,"area":null},{"id":"2303.01313","title":"Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2308.08529","title":"Diagnosing Human-object Interaction Detectors","created":"2023-08-16","cited_by_count":11,"area":null},{"id":"2408.05974","title":"Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection","created":"2024-08-12","cited_by_count":11,"area":null},{"id":"2106.08856","title":"X-MAN: Explaining multiple sources of anomalies in video","created":"2021-06-16","cited_by_count":10,"area":null},{"id":"2208.05470","title":"EvolveHypergraph: Group-Aware Dynamic Relational Reasoning for Trajectory Prediction","created":"2022-08-10","cited_by_count":10,"area":null},{"id":"2202.09492","title":"Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection","created":"2022-02-19","cited_by_count":9,"area":null},{"id":"2207.02400","title":"Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection","created":"2022-07-06","cited_by_count":9,"area":null},{"id":"2308.10158","title":"HODN: Disentangling Human-Object Feature for HOI Detection","created":"2023-08-20","cited_by_count":9,"area":null},{"id":"2108.00596","title":"GTNet:Guided Transformer Network for Detecting Human-Object Interactions","created":"2021-08-02","cited_by_count":8,"area":null},{"id":"2112.06392","title":"The Overlooked Classifier in Human-Object Interaction Recognition","created":"2021-12-13","cited_by_count":8,"area":null},{"id":"2207.01869","title":"Distance Matters in Human-Object Interaction Detection","created":"2022-07-05","cited_by_count":8,"area":null},{"id":"2308.08370","title":"Agglomerative Transformer for Human-Object Interaction Detection","created":"2023-08-16","cited_by_count":8,"area":null},{"id":"2407.10860","title":"Human-Centric Transformer for Domain Adaptive Action Recognition","created":"2024-07-15","cited_by_count":8,"area":null},{"id":"2508.03207","title":"Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration","created":"2025-08-05","cited_by_count":8,"area":null},{"id":"2201.04906","title":"Hand-Object Interaction Reasoning","created":"2022-01-13","cited_by_count":7,"area":null},{"id":"2401.05676","title":"Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection","created":"2024-01-11","cited_by_count":7,"area":null},{"id":"2407.21438","title":"A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap","created":"2024-07-31","cited_by_count":6,"area":null},{"id":"2112.00492","title":"Human-Object Interaction Detection via Weak Supervision","created":"2021-12-01","cited_by_count":5,"area":null},{"id":"2408.10641","title":"A Review of Human-Object Interaction Detection","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2510.18357","title":"Learning Human-Object Interaction as Groups","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2308.02606","title":"Improving Human-Object Interaction Detection via Virtual Image Learning","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2312.07740","title":"HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group Activity Scene Graph Generation in Videos","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2407.00917","title":"From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2408.07430","title":"UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detection","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2107.13083","title":"Is Object Detection Necessary for Human-Object Interaction Recognition?","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2207.05733","title":"A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection","created":"2022-07-11","cited_by_count":3,"area":null},{"id":"2301.07666","title":"DDS: Decoupled Dynamic Scene-Graph Generation Network","created":"2023-01-18","cited_by_count":3,"area":null},{"id":"2503.00414","title":"SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection","created":"2025-03-01","cited_by_count":3,"area":null},{"id":"2506.14189","title":"Egocentric Human-Object Interaction Detection: A New Benchmark and Method","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2509.00760","title":"No More Sibling Rivalry: Debiasing Human-Object Interaction Detection","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2202.11998","title":"Effective Actor-centric Human-object Interaction Detection","created":"2022-02-24","cited_by_count":2,"area":null},{"id":"2303.08920","title":"EgoViT: Pyramid Video Transformer for Egocentric Action Recognition","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2406.18691","title":"Geometric Features Enhanced Human-Object Interaction Detection","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2408.08305","title":"Towards Flexible Visual Relationship Segmentation","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2507.17456","title":"Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2603.27500","title":"Streamlined Open-Vocabulary Human-Object Interaction Detection","created":"2026-03-29","cited_by_count":2,"area":null},{"id":"2101.10292","title":"Transferable Interactiveness Knowledge for Human-Object Interaction Detection","created":"2021-01-25","cited_by_count":1,"area":null},{"id":"2303.04253","title":"TMHOI: Translational Model for Human-Object Interaction Detection","created":"2023-03-07","cited_by_count":1,"area":null},{"id":"2305.02673","title":"Modelling Spatio-Temporal Interactions For Compositional Action Recognition","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2305.09948","title":"HICO-DET-SG and V-COCO-SG: New Data Splits for Evaluating the Systematic Generalization Performance of Human-Object Interaction Detection Models","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2511.18811","title":"Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2604.02071","title":"Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2605.05057","title":"ScriptHOI: Learning Scripted State Transitions for Open-Vocabulary Human-Object Interaction Detection","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2203.05676","title":"The Overlooked Classifier in Human-Object Interaction Recognition","created":"2022-03-10","cited_by_count":0,"area":null},{"id":"2206.06346","title":"Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2207.07979","title":"Knowledge Guided Bidirectional Attention Network for Human-Object Interaction Detection","created":"2022-07-16","cited_by_count":0,"area":null},{"id":"2307.10499","title":"Mining Conditional Part Semantics with Occluded Extrapolation for Human-Object Interaction Detection","created":"2023-07-19","cited_by_count":0,"area":null}],"next_cursor":"100"}