{"list":"other","total":60,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"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":"1711.06721","title":"Learning SO(3) Equivariant Representations with Spherical CNNs","created":"2017-11-17","cited_by_count":248},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2203.02891","title":"Multi-class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2022-03-06","cited_by_count":138},{"id":"2107.06592","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","created":"2021-07-14","cited_by_count":113},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"2106.05969","title":"Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation","created":"2021-06-10","cited_by_count":101},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","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":"1901.01342","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","created":"2019-01-05","cited_by_count":83},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81},{"id":"1912.09390","title":"Tangent Images for Mitigating Spherical Distortion","created":"2019-12-19","cited_by_count":79},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72},{"id":"2005.01616","title":"VisualEchoes: Spatial Image Representation Learning through Echolocation","created":"2020-05-04","cited_by_count":55},{"id":"2303.17056","title":"Audio-Visual Grouping Network for Sound Localization from Mixtures","created":"2023-03-29","cited_by_count":52},{"id":"2208.04464","title":"In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation","created":"2022-08-08","cited_by_count":51},{"id":"2303.11302","title":"Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning","created":"2023-03-20","cited_by_count":47},{"id":"2306.05526","title":"Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment","created":"2023-06-08","cited_by_count":46},{"id":"1603.07763","title":"Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video","created":"2016-03-24","cited_by_count":45},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41},{"id":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40},{"id":"2210.14395","title":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","created":"2022-10-26","cited_by_count":37},{"id":"2108.03256","title":"The Right to Talk: An Audio-Visual Transformer Approach","created":"2021-08-06","cited_by_count":33},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","cited_by_count":32},{"id":"2107.04174","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","created":"2021-07-09","cited_by_count":31},{"id":"1805.02838","title":"A Memory Network Approach for Story-based Temporal Summarization of 360{\\deg} Videos","created":"2018-05-08","cited_by_count":29},{"id":"2303.12408","title":"Balanced Spherical Grid for Egocentric View Synthesis","created":"2023-03-22","cited_by_count":29},{"id":"2104.05167","title":"Egocentric Pose Estimation from Human Vision Span","created":"2021-04-12","cited_by_count":27},{"id":"2201.01928","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","created":"2022-01-06","cited_by_count":27},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25},{"id":"1612.02335","title":"Pano2Vid: Automatic Cinematography for Watching 360$^{\\circ}$ Videos","created":"2016-12-07","cited_by_count":22},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22},{"id":"2108.07640","title":"Look Who's Talking: Active Speaker Detection in the Wild","created":"2021-08-17","cited_by_count":21},{"id":"2303.16342","title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","created":"2023-03-28","cited_by_count":20},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18},{"id":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18},{"id":"2203.11305","title":"Generative Adversarial Network for Future Hand Segmentation from Egocentric Video","created":"2022-03-21","cited_by_count":16},{"id":"2209.08956","title":"Panoramic Vision Transformer for Saliency Detection in 360{\\deg} Videos","created":"2022-09-19","cited_by_count":15},{"id":"2303.06357","title":"CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective","created":"2023-03-11","cited_by_count":15},{"id":"2210.05043","title":"Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling","created":"2022-10-10","cited_by_count":14},{"id":"2312.12870","title":"The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective","created":"2023-12-20","cited_by_count":14},{"id":"2401.08972","title":"Hearing Loss Detection from Facial Expressions in One-on-one Conversations","created":"2024-01-17","cited_by_count":2}],"next_cursor":null}