{"list":"other","total":52,"rows":[{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2010.00747","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","created":"2020-10-02","cited_by_count":641},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2212.09478","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","created":"2022-12-19","cited_by_count":227},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"2305.08275","title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","created":"2023-05-14","cited_by_count":202},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"2112.00431","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","created":"2021-12-01","cited_by_count":108},{"id":"2010.05466","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","created":"2020-10-12","cited_by_count":104},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"2211.03089","title":"I Hear Your True Colors: Image Guided Audio Generation","created":"2022-11-06","cited_by_count":92},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72},{"id":"2001.04758","title":"Deep Audio-Visual Learning: A Survey","created":"2020-01-14","cited_by_count":69},{"id":"2006.14348","title":"Audeo: Audio Generation for a Silent Performance Video","created":"2020-06-23","cited_by_count":47},{"id":"2206.07771","title":"Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation","created":"2022-06-15","cited_by_count":44},{"id":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41},{"id":"2202.03007","title":"Learning Sound Localization Better From Semantically Similar Samples","created":"2022-02-07","cited_by_count":32},{"id":"2202.06406","title":"Visual Sound Localization in the Wild by Cross-Modal Interference Erasing","created":"2022-02-13","cited_by_count":19},{"id":"1908.03737","title":"Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval","created":"2019-08-10","cited_by_count":18},{"id":"2108.00443","title":"A Survey on Audio Synthesis and Audio-Visual Multimodal Processing","created":"2021-08-01","cited_by_count":8},{"id":"2211.03434","title":"Complete Cross-triplet Loss in Label Space for Audio-visual Cross-modal Retrieval","created":"2022-11-07","cited_by_count":6}],"next_cursor":null}