{"list":"other","total":55,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1904.10098","title":"DAG-GNN: DAG Structure Learning with Graph Neural Networks","created":"2019-04-22","cited_by_count":331},{"id":"1903.11960","title":"Learning Discrete Structures for Graph Neural Networks","created":"2019-03-28","cited_by_count":231},{"id":"2006.13009","title":"Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings","created":"2020-06-21","cited_by_count":214},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2002.10698","title":"Hierarchical Conditional Relation Networks for Video Question Answering","created":"2020-02-25","cited_by_count":163},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157},{"id":"1606.03777","title":"Neural Belief Tracker: Data-Driven Dialogue State Tracking","created":"2016-06-12","cited_by_count":143},{"id":"2105.02605","title":"GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph","created":"2021-05-06","cited_by_count":143},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"1410.0210","title":"A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input","created":"2014-10-01","cited_by_count":112},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"1805.00145","title":"Dialog-based Interactive Image Retrieval","created":"2018-05-01","cited_by_count":84},{"id":"1907.07421","title":"SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking","created":"2019-07-17","cited_by_count":63},{"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":"1907.01166","title":"Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems","created":"2019-07-02","cited_by_count":52},{"id":"1806.08409","title":"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features","created":"2018-06-21","cited_by_count":37},{"id":"2006.01460","title":"Situated and Interactive Multimodal Conversations","created":"2020-06-02","cited_by_count":35},{"id":"1805.01555","title":"An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking","created":"2018-05-03","cited_by_count":27},{"id":"1911.06394","title":"The Eighth Dialog System Technology Challenge","created":"2019-11-14","cited_by_count":25},{"id":"2010.10095","title":"BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues","created":"2020-10-20","cited_by_count":22},{"id":"2305.14839","title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","created":"2023-05-24","cited_by_count":19},{"id":"2212.05765","title":"Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue","created":"2022-12-12","cited_by_count":18},{"id":"2103.13361","title":"Structured Co-reference Graph Attention for Video-grounded Dialogue","created":"2021-03-24","cited_by_count":17},{"id":"2006.15319","title":"Video-Grounded Dialogues with Pretrained Generation Language Models","created":"2020-06-27","cited_by_count":16},{"id":"2002.08024","title":"Non-Autoregressive Dialog State Tracking","created":"2020-02-19","cited_by_count":15},{"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":"1911.07928","title":"Visual Dialogue State Tracking for Question Generation","created":"2019-11-12","cited_by_count":13},{"id":"2101.00151","title":"DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue","created":"2021-01-01","cited_by_count":13},{"id":"1901.03461","title":"Dialog System Technology Challenge 7","created":"2019-01-11","cited_by_count":11},{"id":"2001.06206","title":"Multi-step Joint-Modality Attention Network for Scene-Aware Dialogue System","created":"2020-01-17","cited_by_count":11},{"id":"2103.00820","title":"Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues","created":"2021-03-01","cited_by_count":11},{"id":"2207.03656","title":"Video Dialog as Conversation about Objects Living in Space-Time","created":"2022-07-08","cited_by_count":11},{"id":"2007.09903","title":"Multimodal Dialogue State Tracking By QA Approach with Data Augmentation","created":"2020-07-20","cited_by_count":7},{"id":"2206.07898","title":"Multimodal Dialogue State Tracking","created":"2022-06-16","cited_by_count":6},{"id":"2210.14512","title":"End-to-End Multimodal Representation Learning for Video Dialog","created":"2022-10-26","cited_by_count":5},{"id":"2310.16590","title":"$\\mathbb{VD}$-$\\mathbb{GR}$: Boosting $\\mathbb{V}$isual $\\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\\mathbb{GR}$aphs","created":"2023-10-25","cited_by_count":4},{"id":"2402.13146","title":"OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog","created":"2024-02-20","cited_by_count":3}],"next_cursor":null}