{"list":"other","total":78,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"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":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"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":"2403.18814","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","created":"2024-03-27","cited_by_count":365},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1805.10483","title":"Look at Boundary: A Boundary-Aware Face Alignment Algorithm","created":"2018-05-26","cited_by_count":138},{"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":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131},{"id":"1704.00159","title":"Compositional Human Pose Regression","created":"2017-04-01","cited_by_count":124},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"2305.14167","title":"DetGPT: Detect What You Need via Reasoning","created":"2023-05-23","cited_by_count":112},{"id":"1908.05806","title":"Cross-Domain Adaptation for Animal Pose Estimation","created":"2019-08-16","cited_by_count":108},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"2304.04269","title":"HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation","created":"2023-04-09","cited_by_count":105},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103},{"id":"2305.18279","title":"Contextual Object Detection with Multimodal Large Language Models","created":"2023-05-29","cited_by_count":100},{"id":"1908.09220","title":"Single-Stage Multi-Person Pose Machines","created":"2019-08-24","cited_by_count":95},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90},{"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":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59},{"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":"2007.11864","title":"Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation","created":"2020-07-23","cited_by_count":52},{"id":"2302.01593","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","created":"2023-02-03","cited_by_count":48},{"id":"1903.09214","title":"Multi-person Articulated Tracking with Spatial and Temporal Embeddings","created":"2019-03-21","cited_by_count":38},{"id":"2207.10387","title":"Pose for Everything: Towards Category-Agnostic Pose Estimation","created":"2022-07-21","cited_by_count":36},{"id":"2406.05821","title":"F-LMM: Grounding Frozen Large Multimodal Models","created":"2024-06-09","cited_by_count":34},{"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":"2105.10154","title":"ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search","created":"2021-05-21","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":"2407.12435","title":"F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions","created":"2024-07-17","cited_by_count":24},{"id":"2112.05121","title":"Self-Supervised Keypoint Discovery in Behavioral Videos","created":"2021-12-09","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":"2406.04659","title":"LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model","created":"2024-06-07","cited_by_count":17},{"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":"2310.05056","title":"Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching","created":"2023-10-08","cited_by_count":11},{"id":"2205.15895","title":"From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery","created":"2022-05-31","cited_by_count":4}],"next_cursor":null}