{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148},{"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":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135},{"id":"2007.12407","title":"Visual Compositional Learning for Human-Object Interaction Detection","created":"2020-07-24","cited_by_count":130},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"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":"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":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61},{"id":"2308.14960","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","created":"2023-08-29","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":"2209.01814","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","created":"2022-09-05","cited_by_count":55},{"id":"1904.03181","title":"Detecting Human-Object Interactions via Functional Generalization","created":"2019-04-05","cited_by_count":53},{"id":"2308.09351","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","created":"2023-08-18","cited_by_count":45},{"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":"2204.07718","title":"Interactiveness Field in Human-Object Interactions","created":"2022-04-16","cited_by_count":40},{"id":"2402.04630","title":"LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors","created":"2024-02-07","cited_by_count":40},{"id":"2309.03696","title":"Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory","created":"2023-09-07","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":"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},{"id":"2309.03406","title":"Distribution-Aware Prompt Tuning for Vision-Language Models","created":"2023-09-06","cited_by_count":35},{"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":"2204.03541","title":"End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation","created":"2022-04-01","cited_by_count":30},{"id":"2308.11186","title":"Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models","created":"2023-08-22","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":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25},{"id":"2404.06194","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","created":"2024-04-09","cited_by_count":25},{"id":"2303.14005","title":"Category Query Learning for Human-Object Interaction Classification","created":"2023-03-24","cited_by_count":21},{"id":"2203.14272","title":"Discovering Human-Object Interaction Concepts via Self-Compositional Learning","created":"2022-03-27","cited_by_count":15},{"id":"2007.06317","title":"IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos","created":"2020-07-13","cited_by_count":12},{"id":"2308.08370","title":"Agglomerative Transformer for Human-Object Interaction Detection","created":"2023-08-16","cited_by_count":8},{"id":"2407.15451","title":"Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions","created":"2024-07-22","cited_by_count":7},{"id":"2312.10586","title":"Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI","created":"2023-12-17","cited_by_count":3}],"next_cursor":null}