{"list":"other","total":66,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2006.10637","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","created":"2020-06-18","cited_by_count":530},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1908.01207","title":"Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks","created":"2019-08-03","cited_by_count":448},{"id":"1902.10191","title":"EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs","created":"2019-02-26","cited_by_count":447},{"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":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"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":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"2010.10915","title":"Contrastive Learning of General-Purpose Audio Representations","created":"2020-10-21","cited_by_count":169},{"id":"2006.09199","title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","created":"2020-06-16","cited_by_count":111},{"id":"2104.10353","title":"Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning","created":"2021-04-21","cited_by_count":106},{"id":"2212.05767","title":"A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal","created":"2022-12-12","cited_by_count":106},{"id":"2112.14772","title":"Deep Graph Clustering via Dual Correlation Reduction","created":"2021-12-29","cited_by_count":97},{"id":"2002.12177","title":"Evolving Losses for Unsupervised Video Representation Learning","created":"2020-02-26","cited_by_count":74},{"id":"2207.10564","title":"Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression","created":"2022-07-21","cited_by_count":73},{"id":"2207.10434","title":"DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network","created":"2022-07-21","cited_by_count":69},{"id":"1610.00087","title":"Very Deep Convolutional Neural Networks for Raw Waveforms","created":"2016-10-01","cited_by_count":68},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"2301.01098","title":"Cluster-guided Contrastive Graph Clustering Network","created":"2023-01-03","cited_by_count":60},{"id":"2205.07865","title":"Simple Contrastive Graph Clustering","created":"2022-05-11","cited_by_count":56},{"id":"2007.08742","title":"A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation","created":"2020-07-17","cited_by_count":51},{"id":"2204.12768","title":"Masked Spectrogram Prediction For Self-Supervised Audio Pre-Training","created":"2022-04-27","cited_by_count":51},{"id":"2203.14303","title":"TREND: TempoRal Event and Node Dynamics for Graph Representation Learning","created":"2022-03-27","cited_by_count":50},{"id":"2003.13962","title":"Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text","created":"2020-03-31","cited_by_count":46},{"id":"2211.10738","title":"Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure","created":"2022-11-19","cited_by_count":43},{"id":"2106.00327","title":"Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs","created":"2021-06-01","cited_by_count":39},{"id":"2305.18405","title":"Dink-Net: Neural Clustering on Large Graphs","created":"2023-05-28","cited_by_count":38},{"id":"2303.15689","title":"Deep Incomplete Multi-view Clustering with Cross-view Partial Sample and Prototype Alignment","created":"2023-03-28","cited_by_count":33},{"id":"2110.15064","title":"Towards Fine-Grained Reasoning for Fake News Detection","created":"2021-09-13","cited_by_count":32},{"id":"2305.10738","title":"Deep Temporal Graph Clustering","created":"2023-05-18","cited_by_count":28},{"id":"2302.07491","title":"Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment","created":"2023-02-15","cited_by_count":25},{"id":"2304.01563","title":"Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment","created":"2023-04-04","cited_by_count":24},{"id":"2202.11915","title":"Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning","created":"2022-02-24","cited_by_count":23},{"id":"2206.02796","title":"Mixed Graph Contrastive Network for Semi-Supervised Node Classification","created":"2022-06-06","cited_by_count":21},{"id":"2303.01983","title":"Auto-weighted Multi-view Clustering for Large-scale Data","created":"2023-01-21","cited_by_count":20},{"id":"2110.00267","title":"Inductive Representation Learning in Temporal Networks via Mining Neighborhood and Community Influences","created":"2021-10-01","cited_by_count":19},{"id":"2307.03476","title":"Unpaired Multi-View Graph Clustering with Cross-View Structure Matching","created":"2023-07-07","cited_by_count":19},{"id":"2211.14751","title":"Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning","created":"2022-11-27","cited_by_count":18},{"id":"2106.06233","title":"Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling","created":"2021-06-11","cited_by_count":15},{"id":"2306.02259","title":"Predicting Information Pathways Across Online Communities","created":"2023-06-04","cited_by_count":15},{"id":"2302.01859","title":"Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs","created":"2023-02-03","cited_by_count":14},{"id":"2103.07016","title":"On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions","created":"2021-03-12","cited_by_count":10},{"id":"2207.06041","title":"Multiple Kernel Clustering with Dual Noise Minimization","created":"2022-07-13","cited_by_count":10},{"id":"2211.13638","title":"Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizes","created":"2022-11-24","cited_by_count":10},{"id":"2007.04134","title":"Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision","created":"2020-07-08","cited_by_count":9},{"id":"2202.00097","title":"Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data","created":"2022-01-31","cited_by_count":8},{"id":"2305.14074","title":"Message Intercommunication for Inductive Relation Reasoning","created":"2023-05-23","cited_by_count":8},{"id":"2307.03591","title":"Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning","created":"2023-07-06","cited_by_count":8},{"id":"2207.07935","title":"Visually-aware Acoustic Event Detection using Heterogeneous Graphs","created":"2022-07-16","cited_by_count":4},{"id":"2304.10013","title":"HTNet: Dynamic WLAN Performance Prediction using Heterogenous Temporal GNN","created":"2023-04-19","cited_by_count":4},{"id":"1607.02383","title":"Acoustic scene classification using convolutional neural network and multiple-width frequency-delta data augmentation","created":"2016-07-08","cited_by_count":3},{"id":"2201.03346","title":"Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning","created":"2022-01-10","cited_by_count":2},{"id":"2303.02665","title":"Heterogeneous Graph Learning for Acoustic Event Classification","created":"2023-03-05","cited_by_count":2}],"next_cursor":null}