{"list":"other","total":70,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1707.07250","title":"Tensor Fusion Network for Multimodal Sentiment Analysis","created":"2017-07-23","cited_by_count":433},{"id":"2003.04807","title":"Efficient Intent Detection with Dual Sentence Encoders","created":"2020-03-10","cited_by_count":433},{"id":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1805.10190","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","created":"2018-05-25","cited_by_count":377},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"1806.00064","title":"Efficient Low-rank Multimodal Fusion with Modality-Specific Factors","created":"2018-05-31","cited_by_count":270},{"id":"2005.03545","title":"MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis","created":"2020-05-07","cited_by_count":265},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1811.00405","title":"DialogueRNN: An Attentive RNN for Emotion Detection in Conversations","created":"2018-11-01","cited_by_count":218},{"id":"1606.06259","title":"MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos","created":"2016-06-20","cited_by_count":194},{"id":"1908.11540","title":"DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation","created":"2019-08-30","cited_by_count":186},{"id":"1911.01255","title":"pyannote.audio: neural building blocks for speaker diarization","created":"2019-11-04","cited_by_count":181},{"id":"2102.04830","title":"Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis","created":"2021-02-09","cited_by_count":180},{"id":"1802.00927","title":"Memory Fusion Network for Multi-view Sequential Learning","created":"2018-02-03","cited_by_count":168},{"id":"1708.05237","title":"S$^3$FD: Single Shot Scale-invariant Face Detector","created":"2017-08-17","cited_by_count":142},{"id":"2010.02795","title":"COSMIC: COmmonSense knowledge for eMotion Identification in Conversations","created":"2020-10-06","cited_by_count":136},{"id":"2109.00412","title":"Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis","created":"2021-09-01","cited_by_count":131},{"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":"1709.08716","title":"DOC: Deep Open Classification of Text Documents","created":"2017-09-25","cited_by_count":109},{"id":"2107.06779","title":"MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation","created":"2021-07-14","cited_by_count":99},{"id":"2105.11333","title":"Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training","created":"2021-05-24","cited_by_count":96},{"id":"2104.04045","title":"End-to-end speaker segmentation for overlap-aware resegmentation","created":"2021-04-08","cited_by_count":80},{"id":"1812.09471","title":"Joint Slot Filling and Intent Detection via Capsule Neural Networks","created":"2018-12-22","cited_by_count":73},{"id":"2012.08987","title":"Discovering New Intents with Deep Aligned Clustering","created":"2020-12-16","cited_by_count":68},{"id":"1906.00434","title":"Deep Unknown Intent Detection with Margin Loss","created":"2019-06-02","cited_by_count":66},{"id":"1505.04868","title":"Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors","created":"2015-05-19","cited_by_count":58},{"id":"1911.08891","title":"Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement","created":"2019-11-20","cited_by_count":56},{"id":"2012.10209","title":"Deep Open Intent Classification with Adaptive Decision Boundary","created":"2020-12-18","cited_by_count":56},{"id":"2104.08667","title":"SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations","created":"2021-04-18","cited_by_count":56},{"id":"1812.10235","title":"A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling","created":"2018-12-26","cited_by_count":53},{"id":"2103.03095","title":"A Survey on Spoken Language Understanding: Recent Advances and New Frontiers","created":"2021-03-04","cited_by_count":53},{"id":"2203.02385","title":"MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations","created":"2022-03-04","cited_by_count":52},{"id":"2206.02187","title":"M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation","created":"2022-06-05","cited_by_count":47},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41},{"id":"1904.09073","title":"Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts","created":"2019-04-19","cited_by_count":37},{"id":"2205.12914","title":"New Intent Discovery with Pre-training and Contrastive Learning","created":"2022-05-25","cited_by_count":28},{"id":"2110.15063","title":"TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition","created":"2021-09-13","cited_by_count":24},{"id":"2011.05558","title":"Intentonomy: a Dataset and Study towards Human Intent Understanding","created":"2020-11-11","cited_by_count":22},{"id":"2010.05256","title":"Few-shot Learning for Multi-label Intent Detection","created":"2020-10-11","cited_by_count":20},{"id":"2312.14667","title":"Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition","created":"2023-12-22","cited_by_count":18},{"id":"2203.05823","title":"Learning Discriminative Representations and Decision Boundaries for Open Intent Detection","created":"2022-03-11","cited_by_count":15},{"id":"2009.13902","title":"Utterance-level Dialogue Understanding: An Empirical Study","created":"2020-09-29","cited_by_count":10},{"id":"2304.07699","title":"A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery","created":"2023-04-16","cited_by_count":9},{"id":"2204.07804","title":"Learning to Classify Open Intent via Soft Labeling and Manifold Mixup","created":"2022-04-16","cited_by_count":5}],"next_cursor":null}