{"list":"other","total":70,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"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":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"1905.08233","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","created":"2019-05-20","cited_by_count":284},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"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":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","cited_by_count":114},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"1804.04121","title":"The Conversation: Deep Audio-Visual Speech Enhancement","created":"2018-04-11","cited_by_count":109},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75},{"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":"2007.09902","title":"Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation","created":"2020-07-20","cited_by_count":55},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54},{"id":"1908.11602","title":"Recursive Visual Sound Separation Using Minus-Plus Net","created":"2019-08-30","cited_by_count":53},{"id":"1904.05876","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","created":"2019-04-11","cited_by_count":52},{"id":"2202.10910","title":"Sound Adversarial Audio-Visual Navigation","created":"2022-02-22","cited_by_count":48},{"id":"2006.14348","title":"Audeo: Audio Generation for a Silent Performance Video","created":"2020-06-23","cited_by_count":47},{"id":"2104.06162","title":"Visually Informed Binaural Audio Generation without Binaural Audios","created":"2021-04-13","cited_by_count":46},{"id":"1904.09013","title":"Self-Supervised Audio-Visual Co-Segmentation","created":"2019-04-18","cited_by_count":44},{"id":"2111.14843","title":"Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds","created":"2021-11-29","cited_by_count":41},{"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":"2105.05165","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","created":"2021-05-11","cited_by_count":36},{"id":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","cited_by_count":35},{"id":"2209.14275","title":"Audio Retrieval with WavText5K and CLAP Training","created":"2022-09-28","cited_by_count":35},{"id":"2112.11749","title":"Class-aware Sounding Objects Localization via Audiovisual Correspondence","created":"2021-12-22","cited_by_count":32},{"id":"1911.09649","title":"Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications","created":"2019-11-20","cited_by_count":31},{"id":"2203.15537","title":"On Metric Learning for Audio-Text Cross-Modal Retrieval","created":"2022-03-29","cited_by_count":30},{"id":"2109.11955","title":"Visual Scene Graphs for Audio Source Separation","created":"2021-09-24","cited_by_count":29},{"id":"2204.11573","title":"Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing","created":"2022-04-25","cited_by_count":29},{"id":"2104.02775","title":"Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation","created":"2021-03-25","cited_by_count":27},{"id":"1907.04975","title":"My lips are concealed: Audio-visual speech enhancement through obstructions","created":"2019-07-11","cited_by_count":26},{"id":"2102.06291","title":"A Multi-View Approach To Audio-Visual Speaker Verification","created":"2021-02-11","cited_by_count":23},{"id":"1906.10042","title":"Who said that?: Audio-visual speaker diarisation of real-world meetings","created":"2019-06-24","cited_by_count":22},{"id":"1801.02200","title":"Cross-modal Embeddings for Video and Audio Retrieval","created":"2018-01-07","cited_by_count":21},{"id":"1811.10813","title":"Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion","created":"2018-11-27","cited_by_count":21},{"id":"2303.02344","title":"Improving Audio-Visual Video Parsing with Pseudo Visual Labels","created":"2023-03-04","cited_by_count":18},{"id":"2111.08046","title":"Beyond Mono to Binaural: Generating Binaural Audio from Mono Audio with Depth and Cross Modal Attention","created":"2021-11-15","cited_by_count":17},{"id":"2110.06894","title":"Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning","created":"2021-10-13","cited_by_count":15},{"id":"2002.05314","title":"Self-supervised learning for audio-visual speaker diarization","created":"2020-02-13","cited_by_count":14},{"id":"2105.00708","title":"Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation","created":"2021-05-03","cited_by_count":14},{"id":"1911.03930","title":"Robust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders","created":"2019-11-10","cited_by_count":8},{"id":"2104.02656","title":"Collaborative Learning to Generate Audio-Video Jointly","created":"2021-04-01","cited_by_count":6},{"id":"1811.06234","title":"On Training Targets and Objective Functions for Deep-Learning-Based Audio-Visual Speech Enhancement","created":"2018-11-15","cited_by_count":5},{"id":"1708.05851","title":"Image2song: Song Retrieval via Bridging Image Content and Lyric Words","created":"2017-08-19","cited_by_count":3},{"id":"2202.00538","title":"The impact of removing head movements on audio-visual speech enhancement","created":"2022-02-01","cited_by_count":3}],"next_cursor":null}