{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"2107.07567","title":"Beyond Goldfish Memory: Long-Term Open-Domain Conversation","created":"2021-07-15","cited_by_count":267},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256},{"id":"1901.06706","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","created":"2019-01-20","cited_by_count":252},{"id":"1603.06155","title":"A Persona-Based Neural Conversation Model","created":"2016-03-19","cited_by_count":223},{"id":"2106.14843","title":"CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders","created":"2021-06-28","cited_by_count":187},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180},{"id":"1905.00641","title":"RetinaFace: Single-stage Dense Face Localisation in the Wild","created":"2019-05-02","cited_by_count":165},{"id":"1905.01969","title":"Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring","created":"2019-04-22","cited_by_count":165},{"id":"1811.00671","title":"Dialogue Natural Language Inference","created":"2018-11-01","cited_by_count":135},{"id":"1809.01984","title":"Training Millions of Personalized Dialogue Agents","created":"2018-09-06","cited_by_count":126},{"id":"1903.03094","title":"Learning to Speak and Act in a Fantasy Text Adventure Game","created":"2019-03-07","cited_by_count":122},{"id":"2203.05797","title":"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory","created":"2022-03-11","cited_by_count":108},{"id":"2109.05433","title":"Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search","created":"2021-09-12","cited_by_count":90},{"id":"1811.00945","title":"Image Chat: Engaging Grounded Conversations","created":"2018-11-02","cited_by_count":77},{"id":"1901.09672","title":"Personalized Dialogue Generation with Diversified Traits","created":"2019-01-28","cited_by_count":74},{"id":"1911.04700","title":"A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data","created":"2019-11-12","cited_by_count":74},{"id":"2205.13115","title":"Fine-grained Image Captioning with CLIP Reward","created":"2022-05-26","cited_by_count":69},{"id":"2210.08750","title":"Keep Me Updated! Memory Management in Long-term Conversations","created":"2022-10-17","cited_by_count":63},{"id":"1701.08251","title":"Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation","created":"2017-01-28","cited_by_count":59},{"id":"2004.12316","title":"Towards Persona-Based Empathetic Conversational Models","created":"2020-04-26","cited_by_count":53},{"id":"2010.03205","title":"Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions","created":"2020-10-07","cited_by_count":49},{"id":"2204.08128","title":"Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation","created":"2022-04-18","cited_by_count":47},{"id":"2108.01453","title":"PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modeling","created":"2021-07-06","cited_by_count":43},{"id":"2203.08075","title":"Things not Written in Text: Exploring Spatial Commonsense from Visual Signals","created":"2022-03-15","cited_by_count":41},{"id":"2205.01850","title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","created":"2022-05-04","cited_by_count":39},{"id":"1909.03042","title":"Uncertain Natural Language Inference","created":"2019-09-06","cited_by_count":35},{"id":"2108.07154","title":"MMChat: Multi-Modal Chat Dataset on Social Media","created":"2021-08-16","cited_by_count":30},{"id":"2112.08619","title":"Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge","created":"2021-12-16","cited_by_count":30},{"id":"2012.15015","title":"OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts","created":"2020-12-30","cited_by_count":27},{"id":"2107.08685","title":"Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images","created":"2021-07-19","cited_by_count":26},{"id":"2204.09867","title":"A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation","created":"2022-04-21","cited_by_count":25},{"id":"2009.09680","title":"Profile Consistency Identification for Open-domain Dialogue Agents","created":"2020-09-21","cited_by_count":22},{"id":"2204.07721","title":"TVShowGuess: Character Comprehension in Stories as Speaker Guessing","created":"2022-04-16","cited_by_count":17},{"id":"2212.04119","title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset","created":"2022-12-08","cited_by_count":17},{"id":"1910.08293","title":"ALOHA: Artificial Learning of Human Attributes for Dialogue Agents","created":"2019-10-18","cited_by_count":16},{"id":"2106.15846","title":"Automatically Select Emotion for Response via Personality-affected Emotion Transition","created":"2021-06-30","cited_by_count":15},{"id":"2203.07519","title":"Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-modal Knowledge Transfer","created":"2022-03-14","cited_by_count":10},{"id":"2010.05001","title":"Beyond Language: Learning Commonsense from Images for Reasoning","created":"2020-10-10","cited_by_count":3}],"next_cursor":null}