{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"1611.07700","title":"3D Menagerie: Modeling the 3D shape and pose of animals","created":"2016-11-23","cited_by_count":312},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197},{"id":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146},{"id":"2003.06473","title":"Self-supervised Single-view 3D Reconstruction via Semantic Consistency","created":"2020-03-13","cited_by_count":127},{"id":"1604.02748","title":"TGIF: A New Dataset and Benchmark on Animated GIF Description","created":"2016-04-10","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":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112},{"id":"1908.05806","title":"Cross-Domain Adaptation for Animal Pose Estimation","created":"2019-08-16","cited_by_count":108},{"id":"1908.07201","title":"Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images \"In the Wild\"","created":"2019-08-20","cited_by_count":106},{"id":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103},{"id":"1811.05804","title":"Creatures great and SMAL: Recovering the shape and motion of animals from video","created":"2018-11-14","cited_by_count":84},{"id":"2004.00614","title":"Articulation-aware Canonical Surface Mapping","created":"2020-04-01","cited_by_count":81},{"id":"2007.11110","title":"Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop","created":"2020-07-21","cited_by_count":81},{"id":"2007.01216","title":"Spot the conversation: speaker diarisation in the wild","created":"2020-07-02","cited_by_count":79},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"1907.10043","title":"Canonical Surface Mapping via Geometric Cycle Consistency","created":"2019-07-23","cited_by_count":63},{"id":"2107.10844","title":"DOVE: Learning Deformable 3D Objects by Watching Videos","created":"2021-07-22","cited_by_count":61},{"id":"2401.02400","title":"Learning the 3D Fauna of the Web","created":"2024-01-04","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":"2203.15536","title":"BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information","created":"2022-03-29","cited_by_count":51},{"id":"2308.11737","title":"Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape","created":"2023-08-22","cited_by_count":44},{"id":"2008.06133","title":"3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View","created":"2020-08-13","cited_by_count":40},{"id":"2004.07788","title":"RGBD-Dog: Predicting Canine Pose from RGBD Sensors","created":"2020-04-16","cited_by_count":35},{"id":"2105.09396","title":"Birds of a Feather: Capturing Avian Shape Models from Images","created":"2021-05-19","cited_by_count":30},{"id":"2412.00837","title":"AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer","created":"2024-12-01","cited_by_count":20},{"id":"2103.16352","title":"Learning monocular 3D reconstruction of articulated categories from motion","created":"2021-03-30","cited_by_count":18},{"id":"2303.13174","title":"3D-POP -- An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion capture","created":"2023-03-23","cited_by_count":18},{"id":"2111.08176","title":"Coarse-to-fine Animal Pose and Shape Estimation","created":"2021-11-16","cited_by_count":16},{"id":"2411.11409","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","created":"2024-11-18","cited_by_count":12},{"id":"2311.03312","title":"A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation","created":"2023-11-06","cited_by_count":11},{"id":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","cited_by_count":11},{"id":"2212.00741","title":"OpenApePose: a database of annotated ape photographs for pose estimation","created":"2022-11-30","cited_by_count":10},{"id":"2411.10275","title":"4DPV: 4D Pet from Videos by Coarse-to-Fine Non-Rigid Radiance Fields","created":"2024-11-15","cited_by_count":5},{"id":"2506.03868","title":"Animal Pose Labeling Using General-Purpose Point Trackers","created":"2025-06-04","cited_by_count":2},{"id":"2210.08562","title":"A New Spatio-Temporal Loss Function for 3D Motion Reconstruction and Extended Temporal Metrics for Motion Evaluation","created":"2022-10-16","cited_by_count":1}],"next_cursor":null}