{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"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":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"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":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"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":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"1803.10082","title":"Efficient parametrization of multi-domain deep neural networks","created":"2018-03-27","cited_by_count":168},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"id":"2001.08740","title":"Audiovisual SlowFast Networks for Video Recognition","created":"2020-01-23","cited_by_count":146},{"id":"2007.10558","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","created":"2020-07-21","cited_by_count":146},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"2010.05466","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","created":"2020-10-12","cited_by_count":104},{"id":"2206.08356","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","created":"2022-06-16","cited_by_count":99},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86},{"id":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","cited_by_count":82},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"2203.16691","title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer","created":"2022-03-30","cited_by_count":82},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73},{"id":"1902.07473","title":"Dual-modality seq2seq network for audio-visual event localization","created":"2019-02-20","cited_by_count":72},{"id":"2104.00239","title":"Positive Sample Propagation along the Audio-Visual Event Line","created":"2021-04-01","cited_by_count":69},{"id":"2104.02026","title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation","created":"2021-04-05","cited_by_count":59},{"id":"2111.12993","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","created":"2021-11-25","cited_by_count":58},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54},{"id":"1904.05876","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","created":"2019-04-11","cited_by_count":52},{"id":"2012.04124","title":"Parameter Efficient Multimodal Transformers for Video Representation Learning","created":"2020-12-08","cited_by_count":52},{"id":"2210.03265","title":"Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks","created":"2022-10-07","cited_by_count":52},{"id":"2111.12374","title":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","created":"2021-11-24","cited_by_count":39},{"id":"2204.02874","title":"ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound","created":"2022-04-06","cited_by_count":39},{"id":"2203.14240","title":"Audio-Adaptive Activity Recognition Across Video Domains","created":"2022-03-27","cited_by_count":35},{"id":"2003.04298","title":"On Compositions of Transformations in Contrastive Self-Supervised Learning","created":"2020-03-09","cited_by_count":34},{"id":"1911.09649","title":"Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications","created":"2019-11-20","cited_by_count":31},{"id":"2204.11573","title":"Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing","created":"2022-04-25","cited_by_count":29},{"id":"2210.05060","title":"AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization","created":"2022-10-11","cited_by_count":28},{"id":"2209.14156","title":"TVLT: Textless Vision-Language Transformer","created":"2022-09-28","cited_by_count":22}],"next_cursor":null}