{"list":"other","total":67,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183},{"id":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"id":"1504.02863","title":"Appearance-Based Gaze Estimation in the Wild","created":"2015-04-11","cited_by_count":153},{"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},{"id":"1912.12898","title":"PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection","created":"2019-12-30","cited_by_count":143},{"id":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"id":"2003.05541","title":"VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions","created":"2020-03-11","cited_by_count":115},{"id":"1908.05005","title":"Benchmarking the Robustness of Semantic Segmentation Models","created":"2019-08-14","cited_by_count":111},{"id":"2003.14023","title":"Learning Human-Object Interaction Detection using Interaction Points","created":"2020-03-31","cited_by_count":108},{"id":"2108.05077","title":"Mining the Benefits of Two-stage and One-stage HOI Detection","created":"2021-08-11","cited_by_count":103},{"id":"2311.10081","title":"DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback","created":"2023-11-16","cited_by_count":103},{"id":"2401.08573","title":"WAVES: Benchmarking the Robustness of Image Watermarks","created":"2024-01-16","cited_by_count":97},{"id":"2012.06060","title":"Spatially Conditioned Graphs for Detecting Human-Object Interactions","created":"2020-12-11","cited_by_count":93},{"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},{"id":"1909.08453","title":"Pose-aware Multi-level Feature Network for Human Object Interaction Detection","created":"2019-09-18","cited_by_count":88},{"id":"2302.14301","title":"A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking","created":"2023-02-28","cited_by_count":85},{"id":"2010.16219","title":"HOI Analysis: Integrating and Decomposing Human-Object Interaction","created":"2020-10-30","cited_by_count":81},{"id":"2103.08214","title":"Detecting Human-Object Interaction via Fabricated Compositional Learning","created":"2021-03-15","cited_by_count":79},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79},{"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},{"id":"2308.06202","title":"Exploring Predicate Visual Context in Detecting Human-Object Interactions","created":"2023-08-11","cited_by_count":56},{"id":"2106.04531","title":"RobustNav: Towards Benchmarking Robustness in Embodied Navigation","created":"2021-06-08","cited_by_count":54},{"id":"2206.06291","title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","created":"2022-06-13","cited_by_count":47},{"id":"2308.09351","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","created":"2023-08-18","cited_by_count":45},{"id":"2405.17426","title":"Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving","created":"2024-05-27","cited_by_count":41},{"id":"2003.04262","title":"Cascaded Human-Object Interaction Recognition","created":"2020-03-09","cited_by_count":40},{"id":"1805.04771","title":"Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings","created":"2018-05-12","cited_by_count":38},{"id":"2304.04997","title":"Relational Context Learning for Human-Object Interaction Detection","created":"2023-04-11","cited_by_count":36},{"id":"1807.10889","title":"Pairwise Body-Part Attention for Recognizing Human-Object Interactions","created":"2018-07-28","cited_by_count":34},{"id":"2203.14709","title":"MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection","created":"2022-03-28","cited_by_count":34},{"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},{"id":"2312.12664","title":"UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection","created":"2023-12-19","cited_by_count":31},{"id":"1808.09796","title":"Interact as You Intend: Intention-Driven Human-Object Interaction Detection","created":"2018-08-29","cited_by_count":30},{"id":"2301.04019","title":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","created":"2023-01-08","cited_by_count":30},{"id":"2303.17096","title":"ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing","created":"2023-03-30","cited_by_count":30},{"id":"2112.08647","title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","created":"2021-12-16","cited_by_count":28},{"id":"2406.12214","title":"Is Your HD Map Constructor Reliable under Sensor Corruptions?","created":"2024-06-18","cited_by_count":28},{"id":"2410.23904","title":"EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection","created":"2024-10-31","cited_by_count":28},{"id":"2203.00927","title":"TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration","created":"2022-03-02","cited_by_count":25},{"id":"2406.06979","title":"AudioMarkBench: Benchmarking Robustness of Audio Watermarking","created":"2024-06-11","cited_by_count":23},{"id":"2305.12252","title":"Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model","created":"2023-05-20","cited_by_count":22},{"id":"2410.20155","title":"Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models","created":"2024-10-26","cited_by_count":15},{"id":"2501.01037","title":"MSC-Bench: Benchmarking and Analyzing Multi-Sensor Corruption for Driving Perception","created":"2025-01-02","cited_by_count":15},{"id":"2202.11423","title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","created":"2022-02-23","cited_by_count":13},{"id":"2301.04075","title":"Benchmarking Robustness in Neural Radiance Fields","created":"2023-01-10","cited_by_count":13},{"id":"2306.09278","title":"Robustness Analysis on Foundational Segmentation Models","created":"2023-06-15","cited_by_count":13},{"id":"2403.14442","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","created":"2024-03-21","cited_by_count":13},{"id":"2403.20254","title":"Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions","created":"2024-03-29","cited_by_count":12},{"id":"2407.03386","title":"Visual Robustness Benchmark for Visual Question Answering (VQA)","created":"2024-07-03","cited_by_count":12},{"id":"2308.08370","title":"Agglomerative Transformer for Human-Object Interaction Detection","created":"2023-08-16","cited_by_count":8},{"id":"2310.18626","title":"Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness","created":"2023-10-28","cited_by_count":7},{"id":"2503.18134","title":"An Image-like Diffusion Method for Human-Object Interaction Detection","created":"2025-03-23","cited_by_count":5},{"id":"2406.14367","title":"PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions","created":"2024-06-20","cited_by_count":4},{"id":"2408.07430","title":"UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detection","created":"2024-08-14","cited_by_count":4},{"id":"2411.14865","title":"Towards Dependable Optical Flow: Benchmarks for Real-World Spatiotemporal Corruptions","created":"2024-11-22","cited_by_count":3},{"id":"2411.18038","title":"VLM-HOI: Vision Language Models for Interpretable Human-Object Interaction Analysis","created":"2024-11-27","cited_by_count":1}],"next_cursor":null}