{"list":"other","total":68,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136},{"id":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110},{"id":"2401.16423","title":"Synchformer: Efficient Synchronization from Sparse Cues","created":"2024-01-29","cited_by_count":97},{"id":"2211.03089","title":"I Hear Your True Colors: Image Guided Audio Generation","created":"2022-11-06","cited_by_count":92},{"id":"1412.0623","title":"Material Recognition in the Wild with the Materials in Context Database","created":"2014-12-01","cited_by_count":79},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65},{"id":"1511.07404","title":"Learning Visual Predictive Models of Physics for Playing Billiards","created":"2015-11-23","cited_by_count":58},{"id":"2410.10815","title":"Depth Any Video with Scalable Synthetic Data","created":"2024-10-14","cited_by_count":57},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56},{"id":"2406.00320","title":"Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching","created":"2024-06-01","cited_by_count":53},{"id":"2409.13689","title":"Temporally Aligned Audio for Video with Autoregression","created":"2024-09-20","cited_by_count":52},{"id":"2404.04242","title":"Physical Property Understanding from Language-Embedded Feature Fields","created":"2024-04-05","cited_by_count":48},{"id":"2407.05551","title":"Read, Watch and Scream! Sound Generation from Text and Video","created":"2024-07-08","cited_by_count":48},{"id":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41},{"id":"2306.09126","title":"STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events","created":"2023-06-15","cited_by_count":41},{"id":"2208.06787","title":"HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields","created":"2022-08-14","cited_by_count":40},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34},{"id":"2309.10724","title":"Sound Source Localization is All about Cross-Modal Alignment","created":"2023-09-19","cited_by_count":31},{"id":"2303.16897","title":"Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos","created":"2023-03-29","cited_by_count":22},{"id":"2407.13442","title":"BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models","created":"2024-07-18","cited_by_count":18},{"id":"2503.20308","title":"Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics","created":"2025-03-26","cited_by_count":10},{"id":"2504.05684","title":"TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis","created":"2025-04-08","cited_by_count":10},{"id":"2401.05516","title":"FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields","created":"2024-01-10","cited_by_count":9},{"id":"2410.02130","title":"MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation","created":"2024-10-03","cited_by_count":9},{"id":"2409.14759","title":"VLM's Eye Examination: Instruct and Inspect Visual Competency of Vision Language Models","created":"2024-09-23","cited_by_count":8},{"id":"2403.17779","title":"Optical Flow Based Detection and Tracking of Moving Objects for Autonomous Vehicles","created":"2024-03-26","cited_by_count":6},{"id":"1802.07094","title":"Camera-based vehicle velocity estimation from monocular video","created":"2018-02-20","cited_by_count":5},{"id":"2405.07089","title":"SonifyAR: Context-Aware Sound Generation in Augmented Reality","created":"2024-05-11","cited_by_count":5},{"id":"2412.06209","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","created":"2024-12-09","cited_by_count":5},{"id":"2112.12984","title":"Doppler velocity-based algorithm for Clustering and Velocity Estimation of moving objects","created":"2021-12-24","cited_by_count":4},{"id":"2508.02905","title":"How Would It Sound? Material-Controlled Multimodal Acoustic Profile Generation for Indoor Scenes","created":"2025-08-04","cited_by_count":4},{"id":"2509.18272","title":"StereoFoley: Object-Aware Stereo Audio Generation from Video","created":"2025-09-22","cited_by_count":4},{"id":"2510.08054","title":"RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models","created":"2025-10-09","cited_by_count":4},{"id":"2508.12918","title":"FoleySpace: Vision-Aligned Binaural Spatial Audio Generation","created":"2025-08-18","cited_by_count":2}],"next_cursor":null}