{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"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":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"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":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"id":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109},{"id":"2108.05077","title":"Mining the Benefits of Two-stage and One-stage HOI Detection","created":"2021-08-11","cited_by_count":103},{"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":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61},{"id":"2308.06202","title":"Exploring Predicate Visual Context in Detecting Human-Object Interactions","created":"2023-08-11","cited_by_count":56},{"id":"2101.00588","title":"Style Normalization and Restitution for Domain Generalization and Adaptation","created":"2021-01-03","cited_by_count":46},{"id":"2308.09351","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","created":"2023-08-18","cited_by_count":45},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44},{"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},{"id":"2307.12730","title":"COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts","created":"2023-07-24","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":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25},{"id":"2403.18775","title":"ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object","created":"2024-03-27","cited_by_count":22},{"id":"2303.14005","title":"Category Query Learning for Human-Object Interaction Classification","created":"2023-03-24","cited_by_count":21},{"id":"2410.20155","title":"Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models","created":"2024-10-26","cited_by_count":15},{"id":"2410.19635","title":"Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models","created":"2024-10-25","cited_by_count":13},{"id":"2209.01121","title":"Back-to-Bones: Rediscovering the Role of Backbones in Domain Generalization","created":"2022-09-02","cited_by_count":12},{"id":"2308.08529","title":"Diagnosing Human-object Interaction Detectors","created":"2023-08-16","cited_by_count":11},{"id":"2404.01725","title":"Disentangled Pre-training for Human-Object Interaction Detection","created":"2024-04-02","cited_by_count":10},{"id":"2006.14863","title":"Domain Contrast for Domain Adaptive Object Detection","created":"2020-06-26","cited_by_count":9},{"id":"2308.10158","title":"HODN: Disentangling Human-Object Feature for HOI Detection","created":"2023-08-20","cited_by_count":9},{"id":"2207.01869","title":"Distance Matters in Human-Object Interaction Detection","created":"2022-07-05","cited_by_count":8},{"id":"2404.11903","title":"Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition","created":"2024-04-18","cited_by_count":8},{"id":"2310.13040","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","created":"2023-10-19","cited_by_count":6},{"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},{"id":"2308.05961","title":"Compositional Learning in Transformer-Based Human-Object Interaction Detection","created":"2023-08-11","cited_by_count":2}],"next_cursor":null}