{"list":"other","total":53,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2411.15098","title":"OminiControl: Minimal and Universal Control for Diffusion Transformer","created":"2024-11-22","cited_by_count":340},{"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":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"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":"2306.06101","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","created":"2023-06-09","cited_by_count":133},{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131},{"id":"2003.06473","title":"Self-supervised Single-view 3D Reconstruction via Semantic Consistency","created":"2020-03-13","cited_by_count":127},{"id":"2105.01905","title":"4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface","created":"2021-05-05","cited_by_count":124},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112},{"id":"2007.10982","title":"Shape and Viewpoint without Keypoints","created":"2020-07-21","cited_by_count":92},{"id":"2504.16915","title":"DreamO: A Unified Framework for Image Customization","created":"2025-04-23","cited_by_count":83},{"id":"2504.15009","title":"Insert Anything: Image Insertion via In-Context Editing in DiT","created":"2025-04-21","cited_by_count":61},{"id":"2401.02460","title":"Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions","created":"2024-01-04","cited_by_count":54},{"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":"2105.09396","title":"Birds of a Feather: Capturing Avian Shape Models from Images","created":"2021-05-19","cited_by_count":30},{"id":"2006.09205","title":"Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning","created":"2020-06-16","cited_by_count":26},{"id":"2311.00750","title":"Are These the Same Apple? Comparing Images Based on Object Intrinsics","created":"2023-11-01","cited_by_count":19},{"id":"2406.09211","title":"WildlifeReID-10k: Wildlife re-identification dataset with 10k individual animals","created":"2024-06-13","cited_by_count":19},{"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":"2407.13555","title":"PetFace: A Large-Scale Dataset and Benchmark for Animal Identification","created":"2024-07-18","cited_by_count":16},{"id":"2207.10664","title":"Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset","created":"2022-07-21","cited_by_count":12},{"id":"2307.14127","title":"Creative Birds: Self-Supervised Single-View 3D Style Transfer","created":"2023-07-26","cited_by_count":9},{"id":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9},{"id":"1608.00486","title":"Exploiting Temporal Information for DCNN-based Fine-Grained Object Classification","created":"2016-08-01","cited_by_count":7},{"id":"2108.04628","title":"Learning Canonical 3D Object Representation for Fine-Grained Recognition","created":"2021-08-10","cited_by_count":7},{"id":"2408.00160","title":"Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution","created":"2024-07-31","cited_by_count":7},{"id":"2506.01923","title":"TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation","created":"2025-06-02","cited_by_count":7},{"id":"2402.18331","title":"FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 Classes","created":"2024-02-28","cited_by_count":5},{"id":"2409.00317","title":"FBD-SV-2024: Flying Bird Object Detection Dataset in Surveillance Video","created":"2024-08-31","cited_by_count":5},{"id":"2304.11662","title":"AirBirds: A Large-scale Challenging Dataset for Bird Strike Prevention in Real-world Airports","created":"2023-04-23","cited_by_count":4},{"id":"2501.08931","title":"Visual WetlandBirds Dataset: Bird Species Identification and Behavior Recognition in Videos","created":"2025-01-15","cited_by_count":4},{"id":"2501.06031","title":"Generate, Transduct, Adapt: Iterative Transduction with VLMs","created":"2025-01-10","cited_by_count":2},{"id":"2408.13629","title":"Temporally-consistent 3D Reconstruction of Birds","created":"2024-08-24","cited_by_count":1},{"id":"2412.16511","title":"Context-Aware Outlier Rejection for Robust Multi-View 3D Tracking of Similar Small Birds in An Outdoor Aviary","created":"2024-12-21","cited_by_count":1},{"id":"2501.04144","title":"Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generation","created":"2025-01-07","cited_by_count":1},{"id":"2504.08046","title":"Teaching Humans Subtle Differences with DIFFusion","created":"2025-04-10","cited_by_count":1}],"next_cursor":null}