{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"2203.11876","title":"Open-Vocabulary DETR with Conditional Matching","created":"2022-03-22","cited_by_count":220},{"id":"1804.03142","title":"Markerless tracking of user-defined features with deep learning","created":"2018-04-09","cited_by_count":206},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","created":"2022-09-20","cited_by_count":176},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"1901.07973","title":"DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images","created":"2019-01-23","cited_by_count":134},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"1908.05806","title":"Cross-Domain Adaptation for Animal Pose Estimation","created":"2019-08-16","cited_by_count":108},{"id":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"2303.02760","title":"Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes","created":"2023-03-05","cited_by_count":68},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51},{"id":"2302.01593","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","created":"2023-02-03","cited_by_count":48},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45},{"id":"2201.07412","title":"Poseur: Direct Human Pose Regression with Transformers","created":"2022-01-19","cited_by_count":43},{"id":"2207.10387","title":"Pose for Everything: Towards Category-Agnostic Pose Estimation","created":"2022-07-21","cited_by_count":36},{"id":"1910.00216","title":"Revisiting Fine-tuning for Few-shot Learning","created":"2019-10-01","cited_by_count":29},{"id":"1909.04951","title":"AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces","created":"2019-09-11","cited_by_count":28},{"id":"2112.06183","title":"Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species","created":"2021-12-12","cited_by_count":27},{"id":"2308.07313","title":"Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation","created":"2023-08-14","cited_by_count":26},{"id":"2206.11752","title":"CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose","created":"2022-06-23","cited_by_count":25},{"id":"2305.12252","title":"Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model","created":"2023-05-20","cited_by_count":22},{"id":"1604.08685","title":"Single Image 3D Interpreter Network","created":"2016-04-29","cited_by_count":19},{"id":"2306.07879","title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","created":"2023-06-13","cited_by_count":13},{"id":"2308.10174","title":"Neural Interactive Keypoint Detection","created":"2023-08-20","cited_by_count":12},{"id":"2304.04140","title":"Semantic Human Parsing via Scalable Semantic Transfer over Multiple Label Domains","created":"2023-04-09","cited_by_count":11},{"id":"2206.10571","title":"Toward Unpaired Multi-modal Medical Image Segmentation via Learning Structured Semantic Consistency","created":"2022-06-21","cited_by_count":10},{"id":"2308.09953","title":"UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning","created":"2023-08-19","cited_by_count":7},{"id":"2112.02763","title":"MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samples","created":"2021-12-06","cited_by_count":6},{"id":"2303.17216","title":"Few-shot Geometry-Aware Keypoint Localization","created":"2023-03-30","cited_by_count":6}],"next_cursor":null}