{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2309.03882","title":"Large Language Models Are Not Robust Multiple Choice Selectors","created":"2023-09-07","cited_by_count":486},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2308.11483","title":"Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions","created":"2023-08-22","cited_by_count":263},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"2411.10442","title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","created":"2024-11-15","cited_by_count":239},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183},{"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":"2003.14023","title":"Learning Human-Object Interaction Detection using Interaction Points","created":"2020-03-31","cited_by_count":108},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95},{"id":"2004.08154","title":"Detailed 2D-3D Joint Representation for Human-Object Interaction","created":"2020-04-17","cited_by_count":93},{"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":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88},{"id":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"2402.11690","title":"Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning","created":"2024-02-18","cited_by_count":73},{"id":"2407.06192","title":"Multi-Object Hallucination in Vision-Language Models","created":"2024-07-08","cited_by_count":60},{"id":"2209.01814","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","created":"2022-09-05","cited_by_count":55},{"id":"2501.05952","title":"Scalable Vision Language Model Training via High Quality Data Curation","created":"2025-01-10","cited_by_count":55},{"id":"2004.11822","title":"3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training","created":"2020-04-07","cited_by_count":54},{"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":"2309.03696","title":"Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory","created":"2023-09-07","cited_by_count":38},{"id":"1609.00288","title":"A Unified View of Multi-Label Performance Measures","created":"2016-09-01","cited_by_count":36},{"id":"2304.04997","title":"Relational Context Learning for Human-Object Interaction Detection","created":"2023-04-11","cited_by_count":36},{"id":"2407.09519","title":"Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency","created":"2024-06-19","cited_by_count":31},{"id":"2501.15140","title":"Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models","created":"2025-01-25","cited_by_count":31},{"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":"2112.08647","title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","created":"2021-12-16","cited_by_count":28},{"id":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","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":"2408.02484","title":"Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection","created":"2024-08-05","cited_by_count":26},{"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":"2012.11806","title":"Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos","created":"2020-12-22","cited_by_count":23},{"id":"2203.14272","title":"Discovering Human-Object Interaction Concepts via Self-Compositional Learning","created":"2022-03-27","cited_by_count":15},{"id":"2410.20155","title":"Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models","created":"2024-10-26","cited_by_count":15},{"id":"2306.16048","title":"Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity","created":"2023-06-28","cited_by_count":14},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14},{"id":"2502.02589","title":"COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation","created":"2025-02-04","cited_by_count":12},{"id":"2507.15542","title":"HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation","created":"2025-07-21","cited_by_count":12},{"id":"2404.01725","title":"Disentangled Pre-training for Human-Object Interaction Detection","created":"2024-04-02","cited_by_count":10},{"id":"2501.15046","title":"Evaluating Hallucination in Large Vision-Language Models based on Context-Aware Object Similarities","created":"2025-01-25","cited_by_count":7},{"id":"2507.12441","title":"Describe Anything Model for Visual Question Answering on Text-rich Images","created":"2025-07-16","cited_by_count":5},{"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}