{"list":"other","total":78,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255},{"id":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"1910.03814","title":"Exploring Hate Speech Detection in Multimodal Publications","created":"2019-10-09","cited_by_count":103},{"id":"2407.10920","title":"Benchmarking Vision Language Models for Cultural Understanding","created":"2024-07-15","cited_by_count":101},{"id":"2109.05184","title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets","created":"2021-09-11","cited_by_count":86},{"id":"2008.03781","title":"SemEval-2020 Task 8: Memotion Analysis -- The Visuo-Lingual Metaphor!","created":"2020-08-09","cited_by_count":78},{"id":"2411.00238","title":"Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem","created":"2024-10-31","cited_by_count":75},{"id":"2302.04156","title":"Prompting for Multimodal Hateful Meme Classification","created":"2023-02-08","cited_by_count":69},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66},{"id":"2205.04274","title":"Detecting and Understanding Harmful Memes: A Survey","created":"2022-05-09","cited_by_count":58},{"id":"2210.05916","title":"Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features","created":"2022-10-12","cited_by_count":56},{"id":"2012.07788","title":"Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes","created":"2020-12-14","cited_by_count":51},{"id":"1804.11147","title":"FIRST: A Framework for Optimizing Information Quality in Mobile Crowdsensing Systems","created":"2018-04-30","cited_by_count":50},{"id":"2308.08088","title":"Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection","created":"2023-08-16","cited_by_count":47},{"id":"2305.13703","title":"MemeCap: A Dataset for Captioning and Interpreting Memes","created":"2023-05-23","cited_by_count":46},{"id":"1603.02814","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","created":"2016-03-09","cited_by_count":44},{"id":"2109.08013","title":"Detecting Propaganda Techniques in Memes","created":"2021-08-07","cited_by_count":44},{"id":"2012.11528","title":"Overcoming Language Priors with Self-supervised Learning for Visual Question Answering","created":"2020-12-17","cited_by_count":43},{"id":"1511.06973","title":"Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources","created":"2015-11-22","cited_by_count":42},{"id":"2305.17678","title":"Decoding the Underlying Meaning of Multimodal Hateful Memes","created":"2023-05-28","cited_by_count":39},{"id":"2012.13235","title":"Detecting Hateful Memes Using a Multimodal Deep Ensemble","created":"2020-12-24","cited_by_count":30},{"id":"2011.12870","title":"Multimodal Learning for Hateful Memes Detection","created":"2020-11-25","cited_by_count":29},{"id":"2401.16727","title":"Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models","created":"2024-01-30","cited_by_count":26},{"id":"2410.02657","title":"Hate Personified: Investigating the role of LLMs in content moderation","created":"2024-10-03","cited_by_count":25},{"id":"1808.00300","title":"Learning Visual Question Answering by Bootstrapping Hard Attention","created":"2018-08-01","cited_by_count":24},{"id":"2205.05738","title":"DISARM: Detecting the Victims Targeted by Harmful Memes","created":"2022-05-11","cited_by_count":20},{"id":"2210.13626","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","created":"2022-10-24","cited_by_count":20},{"id":"2212.00715","title":"What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memes","created":"2022-12-01","cited_by_count":18},{"id":"2206.04007","title":"Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization","created":"2022-06-08","cited_by_count":17},{"id":"2010.04377","title":"Hate is the New Infodemic: A Topic-aware Modeling of Hate Speech Diffusion on Twitter","created":"2020-10-09","cited_by_count":16},{"id":"2312.05434","title":"Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models","created":"2023-12-09","cited_by_count":15},{"id":"2301.03344","title":"Universal Multimodal Representation for Language Understanding","created":"2023-01-09","cited_by_count":14},{"id":"2310.20159","title":"Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts","created":"2023-10-31","cited_by_count":14},{"id":"2405.08815","title":"Efficient Vision-Language Pre-training by Cluster Masking","created":"2024-05-14","cited_by_count":13},{"id":"2406.07353","title":"Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities","created":"2024-06-11","cited_by_count":13},{"id":"2305.17911","title":"TotalDefMeme: A Multi-Attribute Meme dataset on Total Defence in Singapore","created":"2023-05-29","cited_by_count":12},{"id":"2311.06737","title":"Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model","created":"2023-11-12","cited_by_count":12},{"id":"2405.11215","title":"MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing","created":"2024-05-18","cited_by_count":12},{"id":"2202.12626","title":"Joint Answering and Explanation for Visual Commonsense Reasoning","created":"2022-02-25","cited_by_count":11},{"id":"2406.03953","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","created":"2024-06-06","cited_by_count":11},{"id":"1609.08409","title":"Modelling Radiological Language with Bidirectional Long Short-Term Memory Networks","created":"2016-09-27","cited_by_count":9},{"id":"2206.08406","title":"Predicting Hate Intensity of Twitter Conversation Threads","created":"2022-06-16","cited_by_count":7},{"id":"2311.11157","title":"Contextualizing Internet Memes Across Social Media Platforms","created":"2023-11-18","cited_by_count":5},{"id":"2312.06093","title":"PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models","created":"2023-12-11","cited_by_count":5},{"id":"2302.02479","title":"Hatemongers ride on echo chambers to escalate hate speech diffusion","created":"2023-02-05","cited_by_count":4},{"id":"2402.02144","title":"Probing Critical Learning Dynamics of PLMs for Hate Speech Detection","created":"2024-02-03","cited_by_count":3}],"next_cursor":null}