{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"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":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"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":"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":"2007.12720","title":"MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines","created":"2020-07-10","cited_by_count":204},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"1902.10909","title":"BERT for Joint Intent Classification and Slot Filling","created":"2019-02-28","cited_by_count":196},{"id":"1609.01454","title":"Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling","created":"2016-09-06","cited_by_count":137},{"id":"2202.02519","title":"Intent Contrastive Learning for Sequential Recommendation","created":"2022-02-05","cited_by_count":91},{"id":"2111.02735","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","created":"2021-11-04","cited_by_count":82},{"id":"1909.03862","title":"Out-of-domain Detection for Natural Language Understanding in Dialog Systems","created":"2019-09-09","cited_by_count":62},{"id":"2106.08616","title":"Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training","created":"2021-06-16","cited_by_count":42},{"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":"2211.00385","title":"Behavioral Intention Prediction in Driving Scenes: A Survey","created":"2022-11-01","cited_by_count":30},{"id":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","cited_by_count":26},{"id":"2501.17546","title":"Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant","created":"2025-01-29","cited_by_count":26},{"id":"1708.06578","title":"Cascade and Parallel Convolutional Recurrent Neural Networks on EEG-based Intention Recognition for Brain Computer Interface","created":"2017-08-22","cited_by_count":24},{"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":"2407.02751","title":"Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking Dataset","created":"2024-07-03","cited_by_count":15},{"id":"2108.02598","title":"Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification","created":"2021-08-05","cited_by_count":14},{"id":"2203.11396","title":"Towards Textual Out-of-Domain Detection without In-Domain Labels","created":"2022-03-22","cited_by_count":14},{"id":"2504.13592","title":"Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling","created":"2025-04-18","cited_by_count":12},{"id":"1907.02426","title":"Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction","created":"2019-07-04","cited_by_count":11},{"id":"2210.16663","title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","created":"2022-10-29","cited_by_count":11},{"id":"2403.16504","title":"LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification","created":"2024-03-25","cited_by_count":10},{"id":"2405.03901","title":"OmniActions: Predicting Digital Actions in Response to Real-World Multimodal Sensory Inputs with LLMs","created":"2024-05-06","cited_by_count":10},{"id":"2503.19474","title":"A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition","created":"2025-03-25","cited_by_count":10},{"id":"2105.07071","title":"Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End","created":"2021-05-14","cited_by_count":8},{"id":"2303.00362","title":"How to Communicate Robot Motion Intent: A Scoping Review","created":"2023-03-01","cited_by_count":8},{"id":"2212.07542","title":"Build-a-Bot: Teaching Conversational AI Using a Transformer-Based Intent Recognition and Question Answering Architecture","created":"2022-12-14","cited_by_count":7},{"id":"2401.00424","title":"SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection","created":"2023-12-31","cited_by_count":7},{"id":"1406.5472","title":"Predicting Motivations of Actions by Leveraging Text","created":"2014-06-20","cited_by_count":6},{"id":"2412.12453","title":"Multimodal Classification and Out-of-distribution Detection for Multimodal Intent Understanding","created":"2024-12-17","cited_by_count":6},{"id":"2412.15603","title":"Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification","created":"2024-12-20","cited_by_count":6},{"id":"2503.04201","title":"Knowledge-Decoupled Synergetic Learning: An MLLM based Collaborative Approach to Few-shot Multimodal Dialogue Intention Recognition","created":"2025-03-06","cited_by_count":5},{"id":"2210.12134","title":"Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR","created":"2022-10-21","cited_by_count":4},{"id":"2404.14415","title":"Domain Adaptation in Intent Classification Systems: A Review","created":"2024-03-26","cited_by_count":4},{"id":"2409.09504","title":"Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language","created":"2024-09-14","cited_by_count":2},{"id":"2005.08706","title":"Towards Better Graph Representation: Two-Branch Collaborative Graph Neural Networks for Multimodal Marketing Intention Detection","created":"2020-05-13","cited_by_count":1},{"id":"2311.02482","title":"Generalized zero-shot audio-to-intent classification","created":"2023-11-04","cited_by_count":1},{"id":"2412.08529","title":"TECO: Improving Multimodal Intent Recognition with Text Enhancement through Commonsense Knowledge Extraction","created":"2024-12-11","cited_by_count":1},{"id":"2504.18201","title":"Multi-Grained Compositional Visual Clue Learning for Image Intent Recognition","created":"2025-04-25","cited_by_count":1}],"next_cursor":null}