{"list":"other","total":96,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"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":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"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":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"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":"1707.07250","title":"Tensor Fusion Network for Multimodal Sentiment Analysis","created":"2017-07-23","cited_by_count":433},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"1806.00064","title":"Efficient Low-rank Multimodal Fusion with Modality-Specific Factors","created":"2018-05-31","cited_by_count":270},{"id":"2305.15005","title":"Sentiment Analysis in the Era of Large Language Models: A Reality Check","created":"2023-05-24","cited_by_count":268},{"id":"2005.03545","title":"MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis","created":"2020-05-07","cited_by_count":265},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"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":"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":"1906.01815","title":"Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)","created":"2019-06-05","cited_by_count":174},{"id":"1802.00927","title":"Memory Fusion Network for Multi-view Sequential Learning","created":"2018-02-03","cited_by_count":168},{"id":"1704.01074","title":"Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory","created":"2017-04-04","cited_by_count":167},{"id":"2302.10198","title":"Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT","created":"2023-02-19","cited_by_count":155},{"id":"1904.06618","title":"UR-FUNNY: A Multimodal Language Dataset for Understanding Humor","created":"2019-04-14","cited_by_count":132},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103},{"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":"2304.04339","title":"Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study","created":"2023-04-10","cited_by_count":96},{"id":"1709.00893","title":"Interactive Attention Networks for Aspect-Level Sentiment Classification","created":"2017-09-04","cited_by_count":91},{"id":"1811.09362","title":"Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors","created":"2018-11-23","cited_by_count":89},{"id":"1911.03977","title":"Multimodal Intelligence: Representation Learning, Information Fusion, and Applications","created":"2019-11-10","cited_by_count":89},{"id":"1512.01100","title":"Effective LSTMs for Target-Dependent Sentiment Classification","created":"2015-12-03","cited_by_count":82},{"id":"1911.05544","title":"Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis","created":"2019-11-13","cited_by_count":82},{"id":"2112.02690","title":"Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classification","created":"2021-12-05","cited_by_count":67},{"id":"1909.03477","title":"Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks","created":"2019-09-08","cited_by_count":63},{"id":"2304.09582","title":"Is ChatGPT Equipped with Emotional Dialogue Capabilities?","created":"2023-04-19","cited_by_count":54},{"id":"2205.10237","title":"M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database","created":"2022-05-09","cited_by_count":50},{"id":"1911.07848","title":"Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion","created":"2019-11-18","cited_by_count":45},{"id":"1608.02289","title":"Detecting Sarcasm in Multimodal Social Platforms","created":"2016-08-08","cited_by_count":44},{"id":"2209.02604","title":"Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module","created":"2022-08-22","cited_by_count":44},{"id":"1802.00924","title":"Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning","created":"2018-02-03","cited_by_count":43},{"id":"1802.07862","title":"Multimodal Named Entity Recognition for Short Social Media Posts","created":"2018-02-22","cited_by_count":43},{"id":"2108.01682","title":"Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation","created":"2021-08-03","cited_by_count":41},{"id":"2109.01797","title":"Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis","created":"2021-09-04","cited_by_count":41},{"id":"2103.09666","title":"Multimodal End-to-End Sparse Model for Emotion Recognition","created":"2021-03-17","cited_by_count":40},{"id":"1805.02856","title":"Reasoning with Sarcasm by Reading In-between","created":"2018-05-08","cited_by_count":38},{"id":"2102.02967","title":"RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER","created":"2021-02-05","cited_by_count":37},{"id":"1909.01700","title":"DurIAN: Duration Informed Attention Network For Multimodal Synthesis","created":"2019-09-04","cited_by_count":33},{"id":"2304.08981","title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning","created":"2023-04-18","cited_by_count":33},{"id":"2307.07135","title":"MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System","created":"2023-07-14","cited_by_count":31},{"id":"2205.02455","title":"COGMEN: COntextualized GNN based Multimodal Emotion recognitioN","created":"2022-05-05","cited_by_count":29},{"id":"2404.17113","title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition","created":"2024-04-26","cited_by_count":23},{"id":"2204.05515","title":"CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection","created":"2022-04-12","cited_by_count":21},{"id":"2204.07955","title":"Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment Analysis","created":"2022-04-17","cited_by_count":21},{"id":"2308.11578","title":"Refashioning Emotion Recognition Modelling: The Advent of Generalised Large Models","created":"2023-08-21","cited_by_count":16},{"id":"2401.06659","title":"WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge","created":"2024-01-12","cited_by_count":16},{"id":"2405.07229","title":"MM-InstructEval: Zero-Shot Evaluation of (Multimodal) Large Language Models on Multimodal Reasoning Tasks","created":"2024-05-12","cited_by_count":11},{"id":"1909.00415","title":"Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training","created":"2019-09-01","cited_by_count":10},{"id":"2305.10169","title":"Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt","created":"2023-05-17","cited_by_count":9},{"id":"2306.01004","title":"AoM: Detecting Aspect-oriented Information for Multimodal Aspect-Based Sentiment Analysis","created":"2023-05-31","cited_by_count":9},{"id":"2405.00390","title":"CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models","created":"2024-05-01","cited_by_count":8},{"id":"2203.00257","title":"Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors","created":"2022-03-01","cited_by_count":7},{"id":"2306.14913","title":"FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction","created":"2023-06-19","cited_by_count":7},{"id":"2310.14225","title":"Customising General Large Language Models for Specialised Emotion Recognition Tasks","created":"2023-10-22","cited_by_count":7},{"id":"2210.14556","title":"Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis","created":"2022-10-26","cited_by_count":6},{"id":"2310.14605","title":"M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis","created":"2023-10-23","cited_by_count":6},{"id":"1811.09789","title":"Senti-Attend: Image Captioning using Sentiment and Attention","created":"2018-11-24","cited_by_count":5},{"id":"2104.06308","title":"SFE-Net: EEG-based Emotion Recognition with Symmetrical Spatial Feature Extraction","created":"2021-04-09","cited_by_count":4},{"id":"2312.08084","title":"A Novel Energy based Model Mechanism for Multi-modal Aspect-Based Sentiment Analysis","created":"2023-12-13","cited_by_count":3},{"id":"2405.13059","title":"RNG: Reducing Multi-level Noise and Multi-grained Semantic Gap for Joint Multimodal Aspect-Sentiment Analysis","created":"2024-05-20","cited_by_count":3}],"next_cursor":null}